Список публикаций
Наши публикации
1. Prospects for the Use of Intelligent Multi-agent Models for the Control of Objects of Deeply Integrated Power Systems
https://ieeexplore.ieee.org/document/10016945/
Khalyasmaa A.I., Eroshenko S.A., Mazunina M.V.
The paper considers the approach of using multi-agent models in simulation and decision making of complex systems. Furthermore, an overview of research in the field of multi-agent systems and software platforms for their implementation is carried out. In addition, an analysis of the applicability of intelligent multi-agent systems in the tasks of modelling, optimization and management of energy facilities is performed. This study shows that power industry can use intelligent multi-agent systems not only for the tasks of modelling the interaction of subjects as suppliers and consumers of electricity in the wholesale electricity market and other problems of game theory considering a small number of agents’ types. Moreover, intelligent multi-agent systems can be used to model power systems when it is necessary to take into account the deep integration of the systems. This is understood in the work as dependencies at the level of physical processes of generation, transmission, distribution and consumption of electricity, and at the level of interaction between large technological objects and economic entities. At the second level, it is necessary to consider infrastructure linkages and legal regulations for the economic interaction. As an example, the paper considers a hydropower plant. The entity that manages it must take into account not only the features of the station as a complex electrical facility itself, but also the features of the water usage regime, electricity consumption schedules, meteorological factors, etc. In turn, the use of water resources affects the interests of a large number of subjects, which also needs to be reckoned.
https://ieeexplore.ieee.org/document/10016945/
Khalyasmaa A.I., Eroshenko S.A., Mazunina M.V.
The paper considers the approach of using multi-agent models in simulation and decision making of complex systems. Furthermore, an overview of research in the field of multi-agent systems and software platforms for their implementation is carried out. In addition, an analysis of the applicability of intelligent multi-agent systems in the tasks of modelling, optimization and management of energy facilities is performed. This study shows that power industry can use intelligent multi-agent systems not only for the tasks of modelling the interaction of subjects as suppliers and consumers of electricity in the wholesale electricity market and other problems of game theory considering a small number of agents’ types. Moreover, intelligent multi-agent systems can be used to model power systems when it is necessary to take into account the deep integration of the systems. This is understood in the work as dependencies at the level of physical processes of generation, transmission, distribution and consumption of electricity, and at the level of interaction between large technological objects and economic entities. At the second level, it is necessary to consider infrastructure linkages and legal regulations for the economic interaction. As an example, the paper considers a hydropower plant. The entity that manages it must take into account not only the features of the station as a complex electrical facility itself, but also the features of the water usage regime, electricity consumption schedules, meteorological factors, etc. In turn, the use of water resources affects the interests of a large number of subjects, which also needs to be reckoned.
2. Data Processing Technology for the Forecasting of the Water Inflow into a Reservoir with the Use of Earth Remote Sensing and the Network of Meteorological and Hydrological Posts
https://ibn.idsi.md/vizualizare_articol/168372
Eroshenko S.A., Matrenin P.V., Khalyasmaa A.I., Klimenko D.E., Sidorova A.V.
Management of the hydropower plants requires the economically efficient use of water resources based on the forecasts and simulation models of the hydropower plant and the reservoir. There are various data sources for the water inflow forecasting: meteorological and hydrological posts, Earth remote sensing. However, the problem arises of combining the specified heterogeneous data for aggregated processing with the use of machine learning methods. The research goal is to design an architecture of a system for collecting and processing the data from various sources to operational forecast of the water inflow and the reservoir water-level. It was achieved by analyzing and selecting the sources and methods for the use of Earth remote sensing data; observing the main principles of hydrological modeling; assessing the availability of the different data; analyzing the ways of increasing the observability of the hydrological objects by installing additional meteorological and hydrological posts; and designing a technology for the automatic data collection and processing. The most significant results are developed architecture of the data collection and processing system and the technology for aggregating heterogeneous data with the use of machine learning methods. It is aimed to reduce the error of short-term forecasting of the water inflow to the reservoir. The significance of the results lies in the fact that the proposed technology was offered and justified for a real hydropower plant; and it can improve the water resources management efficiency: increase the energy generation, minimize the sterile spills, increase the flood forecasting horizon and reduce the risk of flooding during the spring high water.
https://ibn.idsi.md/vizualizare_articol/168372
Eroshenko S.A., Matrenin P.V., Khalyasmaa A.I., Klimenko D.E., Sidorova A.V.
Management of the hydropower plants requires the economically efficient use of water resources based on the forecasts and simulation models of the hydropower plant and the reservoir. There are various data sources for the water inflow forecasting: meteorological and hydrological posts, Earth remote sensing. However, the problem arises of combining the specified heterogeneous data for aggregated processing with the use of machine learning methods. The research goal is to design an architecture of a system for collecting and processing the data from various sources to operational forecast of the water inflow and the reservoir water-level. It was achieved by analyzing and selecting the sources and methods for the use of Earth remote sensing data; observing the main principles of hydrological modeling; assessing the availability of the different data; analyzing the ways of increasing the observability of the hydrological objects by installing additional meteorological and hydrological posts; and designing a technology for the automatic data collection and processing. The most significant results are developed architecture of the data collection and processing system and the technology for aggregating heterogeneous data with the use of machine learning methods. It is aimed to reduce the error of short-term forecasting of the water inflow to the reservoir. The significance of the results lies in the fact that the proposed technology was offered and justified for a real hydropower plant; and it can improve the water resources management efficiency: increase the energy generation, minimize the sterile spills, increase the flood forecasting horizon and reduce the risk of flooding during the spring high water.
3. Advanced Algorithms in Automatic Generation Control of Hydroelectric Power Plants
https://www.mdpi.com/2227-7390/10/24/4809
Kazantsev Y.V., Glazyrin G.V., Khalyasmaa A.I., Shayk S.M., Kuparev M.A.
The problem of load distribution between hydraulic units at hydropower plants is a difficult task due to the nonlinearity of hydro turbine characteristics and individual peculiarities of the generation units, in which operating conditions are often different. It is necessary to apply the most up-to-date optimization methods that take into account the nonlinearity of the turbine characteristics. The methods must also consider strict constraints on the operation conditions of the power equipment when searching for the extremum of the objective function specified in the form of equalities and inequalities. When solving the aforementioned optimization problem, the constraints on computing capacities of the digital automatic generation control systems that must operate in real-time mode were taken into account. To solve the optimization task, the interior point method was analyzed and the method of Lagrange multipliers was modified so that it could minimize turbine discharge and active energy losses in the windings of the power generators and unit power transformers. The article presents the simulation results of the developed optimization algorithms and the results of the field tests of the automatic generation control system executing the proposed algorithms. All of the tests showed a fairly high efficiency of the proposed optimization methods in real operation conditions.
https://www.mdpi.com/2227-7390/10/24/4809
Kazantsev Y.V., Glazyrin G.V., Khalyasmaa A.I., Shayk S.M., Kuparev M.A.
The problem of load distribution between hydraulic units at hydropower plants is a difficult task due to the nonlinearity of hydro turbine characteristics and individual peculiarities of the generation units, in which operating conditions are often different. It is necessary to apply the most up-to-date optimization methods that take into account the nonlinearity of the turbine characteristics. The methods must also consider strict constraints on the operation conditions of the power equipment when searching for the extremum of the objective function specified in the form of equalities and inequalities. When solving the aforementioned optimization problem, the constraints on computing capacities of the digital automatic generation control systems that must operate in real-time mode were taken into account. To solve the optimization task, the interior point method was analyzed and the method of Lagrange multipliers was modified so that it could minimize turbine discharge and active energy losses in the windings of the power generators and unit power transformers. The article presents the simulation results of the developed optimization algorithms and the results of the field tests of the automatic generation control system executing the proposed algorithms. All of the tests showed a fairly high efficiency of the proposed optimization methods in real operation conditions.
4. Development of Automatic Determination of Types of Damage System of the Main Equipment of HPP
https://ieeexplore.ieee.org/document/9923411
Lukuts I., Shirokov A., Sidorova A., Khalyasmaa A.
The paper deals with the problems of designing and development of digital twins of relay protection and automation, which allows automatically determination of the equipment failure type. The definition of the failure mode is based on the method of analysing analog and discrete signals that are present in the technological data transmission network. As a result of the research, the algorithm of the digital twin of relay protection and automation was developed and tested at the operating hydroelectric power station. The algorithm runs in the digital environment of the software package SCADA WinCC OA. The digital twin aimed at reducing the failure detection and localization time, and improving the information content about relay protection and automation devices operating modes. The results could be implemented in the existing automated control system of the hydroelectric power plants for improving the personnel decision-making process. The flexible configuration allows not only adapting algorithm to any equipment, but also extending their functionality.
https://ieeexplore.ieee.org/document/9923411
Lukuts I., Shirokov A., Sidorova A., Khalyasmaa A.
The paper deals with the problems of designing and development of digital twins of relay protection and automation, which allows automatically determination of the equipment failure type. The definition of the failure mode is based on the method of analysing analog and discrete signals that are present in the technological data transmission network. As a result of the research, the algorithm of the digital twin of relay protection and automation was developed and tested at the operating hydroelectric power station. The algorithm runs in the digital environment of the software package SCADA WinCC OA. The digital twin aimed at reducing the failure detection and localization time, and improving the information content about relay protection and automation devices operating modes. The results could be implemented in the existing automated control system of the hydroelectric power plants for improving the personnel decision-making process. The flexible configuration allows not only adapting algorithm to any equipment, but also extending their functionality.
5. Grey Wolf Optimizer for RES Capacity Factor Maximization at the Placement Planning Stage
https://www.mdpi.com/2227-7390/11/11/2545
Bramm A. M., Eroshenko S. A., Khalyasmaa A. I., Matrenin, P. V.
At the current stage of the integration of renewable energy sources into the power systems of many countries, requirements for compliance with established technical characteristics are being applied to power generation. One such requirement is the installed capacity utilization factor, which is extremely important for optimally placing power facilities based on renewable energy sources and for the successful development of renewable energy. Efficient placement maximizes the installed capacity utilization factor of a power facility, increasing energy efficiency and the payback period. The installed capacity utilization factor depends on the assumed meteorological factors relating to geographical location and the technical characteristics of power generation. However, the installed capacity utilization factor cannot be accurately predicted, since it is necessary to know the volume of electricity produced by the power facility. A novel approach to the optimization of placement of renewable energy source power plants and their capacity factor forecasting was proposed in this article. This approach combines a machine learning forecasting algorithm (random forest regressor) with a metaheuristic optimization algorithm (grey wolf optimizer). Although the proposed approach assumes the use of only open-source data, the simulations show better results than commonly used algorithms, such as random search, particle swarm optimizer, and firefly algorithm.
https://www.mdpi.com/2227-7390/11/11/2545
Bramm A. M., Eroshenko S. A., Khalyasmaa A. I., Matrenin, P. V.
At the current stage of the integration of renewable energy sources into the power systems of many countries, requirements for compliance with established technical characteristics are being applied to power generation. One such requirement is the installed capacity utilization factor, which is extremely important for optimally placing power facilities based on renewable energy sources and for the successful development of renewable energy. Efficient placement maximizes the installed capacity utilization factor of a power facility, increasing energy efficiency and the payback period. The installed capacity utilization factor depends on the assumed meteorological factors relating to geographical location and the technical characteristics of power generation. However, the installed capacity utilization factor cannot be accurately predicted, since it is necessary to know the volume of electricity produced by the power facility. A novel approach to the optimization of placement of renewable energy source power plants and their capacity factor forecasting was proposed in this article. This approach combines a machine learning forecasting algorithm (random forest regressor) with a metaheuristic optimization algorithm (grey wolf optimizer). Although the proposed approach assumes the use of only open-source data, the simulations show better results than commonly used algorithms, such as random search, particle swarm optimizer, and firefly algorithm.
6. Recurrent Neural Network-Based Autoencoder for Problems of Automatic Time Series Analysis at Power Facilities
https://ibn.idsi.md/ro/vizualizare_articol/180946
Matrenin P. V., Khalyasmaa A. I., Potachits, Y. V.
Digitalization of the energy sector leads to an increase in the volume and rate of data collection. A primary barrier to the proper management of the technological data is the lack of data labeling corresponding to emergency modes, power equipment technical state, etc. Thus, despite the large amount of data, there is a shortage of labeled data suitable for training, validating and testing the machine learning models. Labeling by an expert takes too much time, so there is an actual task to automatically identify data fragments that are potentially of interest. The aim of the work is to develop an algorithm for prioritizing the fragments of the time series using the compact recurrent autoencoder. To achieve the goal, a neural network architecture was developed based on recurrent encoding and decoding cells, ca-pable of unsupervised learning. The model was tested on two data sets: a synthetic sinusoidal signal with missing values and electric current measurements with thermal limit deviations. The substantial results of the work are the compact architecture of the autocoding model and the high interpretability of the output. The most significant achievements of the study are both the autocoding neural network model, which does not require initial assumption about the type of deviations, and the proposed algorithm for prioritizing the data fragments. The significance of the results is prooved by the reduction of the time for analyzing and labeling large data arrays with technological parameters of the electrical networks, which allows using these data for training, validating and testing.
https://ibn.idsi.md/ro/vizualizare_articol/180946
Matrenin P. V., Khalyasmaa A. I., Potachits, Y. V.
Digitalization of the energy sector leads to an increase in the volume and rate of data collection. A primary barrier to the proper management of the technological data is the lack of data labeling corresponding to emergency modes, power equipment technical state, etc. Thus, despite the large amount of data, there is a shortage of labeled data suitable for training, validating and testing the machine learning models. Labeling by an expert takes too much time, so there is an actual task to automatically identify data fragments that are potentially of interest. The aim of the work is to develop an algorithm for prioritizing the fragments of the time series using the compact recurrent autoencoder. To achieve the goal, a neural network architecture was developed based on recurrent encoding and decoding cells, ca-pable of unsupervised learning. The model was tested on two data sets: a synthetic sinusoidal signal with missing values and electric current measurements with thermal limit deviations. The substantial results of the work are the compact architecture of the autocoding model and the high interpretability of the output. The most significant achievements of the study are both the autocoding neural network model, which does not require initial assumption about the type of deviations, and the proposed algorithm for prioritizing the data fragments. The significance of the results is prooved by the reduction of the time for analyzing and labeling large data arrays with technological parameters of the electrical networks, which allows using these data for training, validating and testing.
7. Fluid Dynamics Calculation in SF6 Circuit Breaker during Breaking as a Prerequisite for the Digital Twin Creation
https://www.mdpi.com/2075-1680/12/7/623
Popovtsev V.V.; Khalyasmaa A.I.; Patrakov Y.V.
The requirements to switching the capacities of SF6 circuit breakers submitted by Russian Grid companies are difficult to satisfy. The first limitation is related to material and financial costs in order to create a new requirement-satisfying switching device. The second limitation is dictated by the necessity of calculating complex physical processes in a circuit braker interrupter during fault–current making or breaking before creating a prototype. The latter task is reduced to the problem of simulating the processes of interaction between the switching arc and the SF6 gas flow. This paper deals with the solution of the problem both analytically by a special method and numerically by a numerical software package through the creation of a mathematical model of the interaction process. The switching arc is taken into account as a form of a temperature source, based on experimental data on measuring the temperature of the arc column. The key feature of the research is to use the finite element method based on a moving mesh—the Arbitrary Lagrangian Eulerian (ALE) method. Such a problem statement allows us to take the contact separation curve of the circuit breaker into account as the input data of the model. The calculations were carried out during fault-current breaking by a 110 kV SF6 dead-tank circuit breaker. The calculations of pressure and mass flow in the under-piston volume change, gas flow speed, and temperature depending on the contact separation are given. The proposed model of the switching arc was used to simulate the process of 25 kA symmetrical fault–current breaking and was compared with an experiment.
https://www.mdpi.com/2075-1680/12/7/623
Popovtsev V.V.; Khalyasmaa A.I.; Patrakov Y.V.
The requirements to switching the capacities of SF6 circuit breakers submitted by Russian Grid companies are difficult to satisfy. The first limitation is related to material and financial costs in order to create a new requirement-satisfying switching device. The second limitation is dictated by the necessity of calculating complex physical processes in a circuit braker interrupter during fault–current making or breaking before creating a prototype. The latter task is reduced to the problem of simulating the processes of interaction between the switching arc and the SF6 gas flow. This paper deals with the solution of the problem both analytically by a special method and numerically by a numerical software package through the creation of a mathematical model of the interaction process. The switching arc is taken into account as a form of a temperature source, based on experimental data on measuring the temperature of the arc column. The key feature of the research is to use the finite element method based on a moving mesh—the Arbitrary Lagrangian Eulerian (ALE) method. Such a problem statement allows us to take the contact separation curve of the circuit breaker into account as the input data of the model. The calculations were carried out during fault-current breaking by a 110 kV SF6 dead-tank circuit breaker. The calculations of pressure and mass flow in the under-piston volume change, gas flow speed, and temperature depending on the contact separation are given. The proposed model of the switching arc was used to simulate the process of 25 kA symmetrical fault–current breaking and was compared with an experiment.
8. Численное моделирование взаимодействия дуги отключения с потоком элегаза в автокомпрессионном дугогасительном устройстве элегазового
выключателя 110 кВ
https://www.powervestniksusu.ru/index.php/PVS/article/view/577
Поповцев В.В., Хальясмаа А.И., Патраков Ю.В.
Требования к повышению коммутационной способности элегазовых выключателей, диктуемые электросетевыми компаниями вследствие увеличения расчётных токов короткого замыкания в сетях 110 кВ и выше в настоящее время является сложной технико-экономической задачей. Очевидно, что материальные затраты на такое мероприятие высоки и перед созданием прототипа нового оборудования или модернизации существующего необходимо произвести расчёт сложнейших комплексных физических процессов гашения дуги, происходящих в дугогасительном устройстве элегазового выключателя высокого напряжения при отключении токов короткого замыкания. Последнее сводится к задаче моделирования процессов взаимодействия дуги отключения с неизотермическим потоком элегаза. В статье исследуется возможность решения вышеописанной задачи в численном программном комплексе при учёте дуги в форме источника температурного нагрева на основе экспериментальных данных измерения температуры ствола дуги при отключении симметричного тока короткого замыкания 10 кА. Расчёты проводились при коммутации автокомпрессионного дугогасительного устройства элегазового выключателя 110 кВ. Приведены результаты изменения давления и массового расхода в подпоршневой области, скорости, температуры в зависимости от хода контактов. Разработанная модель взаимодействия дуги отключения с потоком элегаза также использована для моделирования процесса отключения симметричного тока короткого замыкания 25 кА в реальном автокомпрессионном дугогасительном устройстве.
выключателя 110 кВ
https://www.powervestniksusu.ru/index.php/PVS/article/view/577
Поповцев В.В., Хальясмаа А.И., Патраков Ю.В.
Требования к повышению коммутационной способности элегазовых выключателей, диктуемые электросетевыми компаниями вследствие увеличения расчётных токов короткого замыкания в сетях 110 кВ и выше в настоящее время является сложной технико-экономической задачей. Очевидно, что материальные затраты на такое мероприятие высоки и перед созданием прототипа нового оборудования или модернизации существующего необходимо произвести расчёт сложнейших комплексных физических процессов гашения дуги, происходящих в дугогасительном устройстве элегазового выключателя высокого напряжения при отключении токов короткого замыкания. Последнее сводится к задаче моделирования процессов взаимодействия дуги отключения с неизотермическим потоком элегаза. В статье исследуется возможность решения вышеописанной задачи в численном программном комплексе при учёте дуги в форме источника температурного нагрева на основе экспериментальных данных измерения температуры ствола дуги при отключении симметричного тока короткого замыкания 10 кА. Расчёты проводились при коммутации автокомпрессионного дугогасительного устройства элегазового выключателя 110 кВ. Приведены результаты изменения давления и массового расхода в подпоршневой области, скорости, температуры в зависимости от хода контактов. Разработанная модель взаимодействия дуги отключения с потоком элегаза также использована для моделирования процесса отключения симметричного тока короткого замыкания 25 кА в реальном автокомпрессионном дугогасительном устройстве.
9. Maintenance Optimization within the Lifecycle Management of the Gas Compressor’s Electric Motors
https://ieeexplore.ieee.org/document/10225198
Mironenko Y.V., Khalyasmaa A.I.
As a part of the paper, the issue of optimizing repairs and maintenance of electrically driven gas pumping units are considered. The existing approach to the operation and maintenance of electric gas pumping units, both in the Russian Federation and abroad was described. Also, the statistics of their failures, the possibility of using a life cycle management system to assess the current state of electrical facilities and manage production assets was analyzed. In order to optimize and improve the reliability of the results of assessing the current state of this equipment, the main existing classical methods are considered, as well as the possibilities of using artificial intelligence methods. In the course of the study, models were prepared to assess the current state of electrical facilities, based on monitoring the main diagnostic (temperature, vibration) and operational (load, pressure) parameters. These models use machine learning algorithms, common in technical diagnostics: bagging and gradient boosting. The achieved accuracy in assessing the current state of electrically driven gas pumping units allows using these models as the basis for a life cycle management system. The main reason is reducing the costs and increasing the service life of electrically driven gas pumping units.
https://ieeexplore.ieee.org/document/10225198
Mironenko Y.V., Khalyasmaa A.I.
As a part of the paper, the issue of optimizing repairs and maintenance of electrically driven gas pumping units are considered. The existing approach to the operation and maintenance of electric gas pumping units, both in the Russian Federation and abroad was described. Also, the statistics of their failures, the possibility of using a life cycle management system to assess the current state of electrical facilities and manage production assets was analyzed. In order to optimize and improve the reliability of the results of assessing the current state of this equipment, the main existing classical methods are considered, as well as the possibilities of using artificial intelligence methods. In the course of the study, models were prepared to assess the current state of electrical facilities, based on monitoring the main diagnostic (temperature, vibration) and operational (load, pressure) parameters. These models use machine learning algorithms, common in technical diagnostics: bagging and gradient boosting. The achieved accuracy in assessing the current state of electrically driven gas pumping units allows using these models as the basis for a life cycle management system. The main reason is reducing the costs and increasing the service life of electrically driven gas pumping units.
10. Assessment of the Hydroelectric Power Plant Cascade Economic Efficiency
https://ieeexplore.ieee.org/document/10296263/
Sidorova A.V., Haljasmaa K.I.
This article deals with the problem of assessing the economic efficiency of the operation of a cascade of hydroelectric power plants in the conditions of the wholesale electricity market. The definition of economic efficiency is based on the choice of the optimal plan for the available capacity of the hydropower plants, depending on the type of distribution of available capacity, as well as the size of the penalty for the difference between the actual available capacity and the planned one. The calculation was made in the MathCad computer algebra system for two hydropower plant cascades (the Pamir hydropower plant cascade and the Bureyskie hydropower plant cascade). The obtained results have shown that the influence of the selected distribution function of the available power has a stronger effect on more powerful stations. The cascade connection of hydropower plants allows increasing the value of the minimum capacity, thereby reducing the range of uncertainty and possible penalties for the declared capacity, thereby ensuring the most cost-effective financial result for generating companies.
https://ieeexplore.ieee.org/document/10296263/
Sidorova A.V., Haljasmaa K.I.
This article deals with the problem of assessing the economic efficiency of the operation of a cascade of hydroelectric power plants in the conditions of the wholesale electricity market. The definition of economic efficiency is based on the choice of the optimal plan for the available capacity of the hydropower plants, depending on the type of distribution of available capacity, as well as the size of the penalty for the difference between the actual available capacity and the planned one. The calculation was made in the MathCad computer algebra system for two hydropower plant cascades (the Pamir hydropower plant cascade and the Bureyskie hydropower plant cascade). The obtained results have shown that the influence of the selected distribution function of the available power has a stronger effect on more powerful stations. The cascade connection of hydropower plants allows increasing the value of the minimum capacity, thereby reducing the range of uncertainty and possible penalties for the declared capacity, thereby ensuring the most cost-effective financial result for generating companies.
11. Influence of Machine Learning Method Choice on the Accuracy of Power Load Forecast Models and HPP Cascade Mode
https://ieeexplore.ieee.org/document/10296424
Sidorova A.V., Haljasmaa K.I.
This article proposes a new approach to operational forecasting of power load schedules with the use of machine learning methods. In order to increase the accuracy of models and algorithms for operational forecasting of power load schedules, testing of several machine learning methods was implemented. The developed models were tested in the Python programming language using the sktime and scikit-learn libraries. A calculation of power modes was carried out, which showed high comparability of the results with the actual values of the mode. The residual values of the controlled parameters based on the results of using the calculated and predicted value of the power load with the use of machine learning methods showed a higher comparability of the results with the real power mode. This allows us to talk about obtaining a more accurate result when using the forecast of the power load in nodes with the use of machine learning methods and their possible use in dispatch centers as a basis for planning long-term conditions and coordinating repair schedules for the power grid equipment.
https://ieeexplore.ieee.org/document/10296424
Sidorova A.V., Haljasmaa K.I.
This article proposes a new approach to operational forecasting of power load schedules with the use of machine learning methods. In order to increase the accuracy of models and algorithms for operational forecasting of power load schedules, testing of several machine learning methods was implemented. The developed models were tested in the Python programming language using the sktime and scikit-learn libraries. A calculation of power modes was carried out, which showed high comparability of the results with the actual values of the mode. The residual values of the controlled parameters based on the results of using the calculated and predicted value of the power load with the use of machine learning methods showed a higher comparability of the results with the real power mode. This allows us to talk about obtaining a more accurate result when using the forecast of the power load in nodes with the use of machine learning methods and their possible use in dispatch centers as a basis for planning long-term conditions and coordinating repair schedules for the power grid equipment.
12. Algorithm for Calculating the Water and Energy Mode of the Cascade of Hydroelectric Power Plants on the Basis of the Integrated Mathematical Model
https://ieeexplore.ieee.org/document/10296379
Sidorova A.V., Haljasmaa K.I.
The article discusses the compilation of an algorithm for calculating the water-energy mode of a hydroelectric power plant cascade from particular mathematical models, integrated into a single mathematical model to take into account the variability of external and internal factors, electrical and hydrological relations, and technological restrictions, imposed on the process of its functioning. Drawing up a capacious algorithm for an interconnected process between two cascade hydroelectric power plants is based on Boolean algebra and includes two main modules of particular mathematical models “Electricity” and “Water” in the calculation. Verification of the algorithm was carried out in Eurostag. The obtained results showed that the developed algorithm for calculating the water-energy mode of the HPP cascade has a negligible calculation error, relative to the mathematical calculation and allows to determine with high accuracy the main parameters of the hydro power plant cascade operation mode. It is necessary to provide the power system with the required power, taking into account not only the magnitude of the water flow through the reservoir, but also the mode of its operation over long periods of time. The algorithm takes into account the possibility of idle discharges, monitors and identifies the reference points of unacceptable deviations, correcting the calculation error at each step, necessary for it. This ensures an increase in the mode controllability of the process of generating electricity through the hydro power plant cascade.
https://ieeexplore.ieee.org/document/10296379
Sidorova A.V., Haljasmaa K.I.
The article discusses the compilation of an algorithm for calculating the water-energy mode of a hydroelectric power plant cascade from particular mathematical models, integrated into a single mathematical model to take into account the variability of external and internal factors, electrical and hydrological relations, and technological restrictions, imposed on the process of its functioning. Drawing up a capacious algorithm for an interconnected process between two cascade hydroelectric power plants is based on Boolean algebra and includes two main modules of particular mathematical models “Electricity” and “Water” in the calculation. Verification of the algorithm was carried out in Eurostag. The obtained results showed that the developed algorithm for calculating the water-energy mode of the HPP cascade has a negligible calculation error, relative to the mathematical calculation and allows to determine with high accuracy the main parameters of the hydro power plant cascade operation mode. It is necessary to provide the power system with the required power, taking into account not only the magnitude of the water flow through the reservoir, but also the mode of its operation over long periods of time. The algorithm takes into account the possibility of idle discharges, monitors and identifies the reference points of unacceptable deviations, correcting the calculation error at each step, necessary for it. This ensures an increase in the mode controllability of the process of generating electricity through the hydro power plant cascade.
13. Development of Automated Life Cycle Management System for Electrically Driven Compressor Units in the Oil and Gas Industry
https://ieeexplore.ieee.org/document/10296464
Mironenko Y.V., Khalyasmaa A.I.
Electrically driven compressor units are one of the key elements in the processing equipment of oil and gas fabrication facilities. Today, due to the increasing share of exhausted complexes and the lack of a domestic market for competitive products, the focus of operation is on maintaining a minimum sufficient level of performance using tools such as a life cycle management system. The life cycle management system is an information and analytical expert system for managing the facility at all stages of the cycle. Its bases are data on current and predicted technical state within the framework of the organization's business model. This study examines the sources of data for the operation of the system and the mechanisms for implementing key modules: classification and prediction of the values of diagnostic parameters. The accuracy of classification and forecasting obtained during testing is sufficient for the use of the system by organizations operating compressor units.
https://ieeexplore.ieee.org/document/10296464
Mironenko Y.V., Khalyasmaa A.I.
Electrically driven compressor units are one of the key elements in the processing equipment of oil and gas fabrication facilities. Today, due to the increasing share of exhausted complexes and the lack of a domestic market for competitive products, the focus of operation is on maintaining a minimum sufficient level of performance using tools such as a life cycle management system. The life cycle management system is an information and analytical expert system for managing the facility at all stages of the cycle. Its bases are data on current and predicted technical state within the framework of the organization's business model. This study examines the sources of data for the operation of the system and the mechanisms for implementing key modules: classification and prediction of the values of diagnostic parameters. The accuracy of classification and forecasting obtained during testing is sufficient for the use of the system by organizations operating compressor units.
14. Study of Power Transformers Made of Various Electrical Steels
https://ieeexplore.ieee.org/document/10272739
Shmakov E.A, Smolyanov I.A., Sokolov I.V.
In this paper an influence of electrical steel features on the transformer specifications is studied. The application of non-grain oriented, grain oriented and double oriented electrical steel to be increased performance of the transformer is considered. Numerical experiments were carried out by solving the A-formulation of Maxwell’s equations system with the help of finite element method. As a result, the dependences of efficiency and power factor on value of the transformer relative magnetic permeability and relative mass, as well as the distribution of magnetic flux density in the transformer core, were obtained. Ultimately, conclusions are drawn about the advisability of using double oriented electrical steel in manufacture of transformers.
https://ieeexplore.ieee.org/document/10272739
Shmakov E.A, Smolyanov I.A., Sokolov I.V.
In this paper an influence of electrical steel features on the transformer specifications is studied. The application of non-grain oriented, grain oriented and double oriented electrical steel to be increased performance of the transformer is considered. Numerical experiments were carried out by solving the A-formulation of Maxwell’s equations system with the help of finite element method. As a result, the dependences of efficiency and power factor on value of the transformer relative magnetic permeability and relative mass, as well as the distribution of magnetic flux density in the transformer core, were obtained. Ultimately, conclusions are drawn about the advisability of using double oriented electrical steel in manufacture of transformers.
15. Numerical Simulation of Natural Convection in the Power Transformer
https://ieeexplore.ieee.org/document/10272835
Shmakov E.A, Smolyanov I.A., Lapin A.D.
Numerical analysis of natural convection in a three-phase power transformer filled with industrial oil is considered. The paper presents a comparative analysis of the temperature and hydrodynamic fields when reducing a load factor by three different approaches to the simulation of the transformer tank area. The initial conditions of the velocity, pressure, and temperature fields are the results of calculating a stationary study of the convection in a power transformer. It is shown that considering the computational domain as a one-phase case significantly distorts the results. The appropriate way to simulate a cooling system is to use the inlet-outlet boundary conditions calibrated by physical experiments or numerical simulations. All the calculations were performed using the k – ϵ turbulence model implemented in Comsol Multiphysics. The presented results are of particular interest for the power transformer oil condition forecasting by numerical simulation tools.
https://ieeexplore.ieee.org/document/10272835
Shmakov E.A, Smolyanov I.A., Lapin A.D.
Numerical analysis of natural convection in a three-phase power transformer filled with industrial oil is considered. The paper presents a comparative analysis of the temperature and hydrodynamic fields when reducing a load factor by three different approaches to the simulation of the transformer tank area. The initial conditions of the velocity, pressure, and temperature fields are the results of calculating a stationary study of the convection in a power transformer. It is shown that considering the computational domain as a one-phase case significantly distorts the results. The appropriate way to simulate a cooling system is to use the inlet-outlet boundary conditions calibrated by physical experiments or numerical simulations. All the calculations were performed using the k – ϵ turbulence model implemented in Comsol Multiphysics. The presented results are of particular interest for the power transformer oil condition forecasting by numerical simulation tools.
16. New Load Forecasting Ensemble Model based on LightGBM for Gas Industry Enterprises
https://ieeexplore.ieee.org/document/10583981
Stepanova A.I, Matrenin P.V.
The forecasting of the power consumption leads the main role in the process of planning of operation modes of industrial enterprises. The issue of forecasting the power consumption of the industrial enterprise is more complicated than forecasting the load curve of large system due to the less periodicity of the consumption, its greater variance, and the need to consider technological factors. The object of this article is enterprises of the gas industry. Because of their remoteness from centralized power system and great seasonal impact on gas recovery process the forecasting of power consumption of such enterprises affects not only the cost of consumption, but also the usage of own generation. This article introduces the novel usage of the LightGBM algorithm for the forecasting of the power consumption of the enterprise of the gas industry. In the article four experiments with various feature combinations were conducted. The need for consideration of technological and meteorological factors was discussed. Comparison of the models based on LightGBM, XGBoost, AdaBoost, Random Forest was presented. Model using LightGBM have the highest MAPE of 9.641 % compared to others. This result was achieved with the regard of the retrospective of power consumption and technological process data. Furthermore, the topics of dataset creation and data preprocessing were established.
https://ieeexplore.ieee.org/document/10583981
Stepanova A.I, Matrenin P.V.
The forecasting of the power consumption leads the main role in the process of planning of operation modes of industrial enterprises. The issue of forecasting the power consumption of the industrial enterprise is more complicated than forecasting the load curve of large system due to the less periodicity of the consumption, its greater variance, and the need to consider technological factors. The object of this article is enterprises of the gas industry. Because of their remoteness from centralized power system and great seasonal impact on gas recovery process the forecasting of power consumption of such enterprises affects not only the cost of consumption, but also the usage of own generation. This article introduces the novel usage of the LightGBM algorithm for the forecasting of the power consumption of the enterprise of the gas industry. In the article four experiments with various feature combinations were conducted. The need for consideration of technological and meteorological factors was discussed. Comparison of the models based on LightGBM, XGBoost, AdaBoost, Random Forest was presented. Model using LightGBM have the highest MAPE of 9.641 % compared to others. This result was achieved with the regard of the retrospective of power consumption and technological process data. Furthermore, the topics of dataset creation and data preprocessing were established.
17. Multiobjective Optimization in the Problem of SVC Placement Using N-1 Approach and Population-Based Algorithms
https://ieeexplore.ieee.org/document/10615078
Popovtsev V.V., Ignatiev D.A., Haljasmaa K.I.
The comprehensive integration of key components within power systems and the interconnectedness of stakeholders involved in electricity generation, transmission, distribution, and consumption necessitates consideration at both macro and micro levels. Reactive power compensation devices play a crucial role in managing reactive power and have a substantial impact on various operational parameters of power systems. Consequently, it is essential to establish a set of optimization criteria for determining the optimal placement and parameters of these devices. This optimization problem is inherently multiobjective in nature and requires a systematic approach for resolution. This study focuses on the optimization of static var compensator placement using elitist genetic algorithms, particle swarm optimization, and full enumeration methods. The selection of optimal location and parameters for a static var compensator is based on power flow analysis of entire power systems within test schemes. The consideration of N−1 contingencies in the optimization algorithms has been shown to significantly influence the results, as demonstrated in previous research by the authors. Optimization criteria include the expected value and standard deviation of power excess, current capacity excess, and absolute voltage deviation. The results of the tests indicate that the formulation and number of objective functions play a critical role in determining the effectiveness of the solution to the optimization problem.
https://ieeexplore.ieee.org/document/10615078
Popovtsev V.V., Ignatiev D.A., Haljasmaa K.I.
The comprehensive integration of key components within power systems and the interconnectedness of stakeholders involved in electricity generation, transmission, distribution, and consumption necessitates consideration at both macro and micro levels. Reactive power compensation devices play a crucial role in managing reactive power and have a substantial impact on various operational parameters of power systems. Consequently, it is essential to establish a set of optimization criteria for determining the optimal placement and parameters of these devices. This optimization problem is inherently multiobjective in nature and requires a systematic approach for resolution. This study focuses on the optimization of static var compensator placement using elitist genetic algorithms, particle swarm optimization, and full enumeration methods. The selection of optimal location and parameters for a static var compensator is based on power flow analysis of entire power systems within test schemes. The consideration of N−1 contingencies in the optimization algorithms has been shown to significantly influence the results, as demonstrated in previous research by the authors. Optimization criteria include the expected value and standard deviation of power excess, current capacity excess, and absolute voltage deviation. The results of the tests indicate that the formulation and number of objective functions play a critical role in determining the effectiveness of the solution to the optimization problem.
18. Review of Modeling Approaches for Conjugate Heat Transfer Processes in Oil-Immersed Transformers
https://www.mdpi.com/2079-3197/12/5/97
Smolyanov I.A., Shmakov E.I., Butusov D.N., Khalyasmaa A.I.,
This review addresses the modeling approaches for heat transfer processes in oil-immersed transformer. Electromagnetic, thermal, and hydrodynamic thermal fields are identified as the most critical aspects in describing the state of the transformer. The paper compares the implementation complexity, calculation time, and details of the results for different approaches to creating a mathematical model, such as circuit-based models and finite element and finite volume methods. Examples of successful model implementation are provided, along with the features of oil-immersed transformer modeling. In addition, the review considers the strengths and limitations of the considered models in relation to creating a digital twin of a transformer. The review concludes that it is not feasible to create a universal model that accounts for all the features of physical processes in an oil-immersed transformer, operates in real time for a digital twin, and provides the required accuracy at the same time. The conducted research shows that joint modeling of electromagnetic and thermal processes, reducing the dimensionality of models, provides the most comprehensive solution to the problem.
https://www.mdpi.com/2079-3197/12/5/97
Smolyanov I.A., Shmakov E.I., Butusov D.N., Khalyasmaa A.I.,
This review addresses the modeling approaches for heat transfer processes in oil-immersed transformer. Electromagnetic, thermal, and hydrodynamic thermal fields are identified as the most critical aspects in describing the state of the transformer. The paper compares the implementation complexity, calculation time, and details of the results for different approaches to creating a mathematical model, such as circuit-based models and finite element and finite volume methods. Examples of successful model implementation are provided, along with the features of oil-immersed transformer modeling. In addition, the review considers the strengths and limitations of the considered models in relation to creating a digital twin of a transformer. The review concludes that it is not feasible to create a universal model that accounts for all the features of physical processes in an oil-immersed transformer, operates in real time for a digital twin, and provides the required accuracy at the same time. The conducted research shows that joint modeling of electromagnetic and thermal processes, reducing the dimensionality of models, provides the most comprehensive solution to the problem.
19. Анализ возможности применения мультиагентных систем в задаче краткосрочного прогнозирования электрической энергии электротехнического комплекса предприятия нефтегазовой промышленности
https://www.powervestniksusu.ru/index.php/PVS/article/view/825
Степанова А.И., Хальясмаа А.И., Матренин П.В.
Электротехнические установки и комплексы в нефтегазовой промышленности относятся к объектам критической инфраструктуры. Одно из требований к электротехническому комплексу заключается в соответствии требованиям по обеспечению энергосбережения и энергетической эффективности. Ввиду сложности учета технологических процессов на предприятиях нефтегазовой промышленности, в основном, применяются технические меры, требующие значительных капиталовложений. В данной статье рассматривается возможность внедрения организационной меры, которая заключается в прогнозировании электропотребления предприятия нефтегазовой промышленности. Для демонстрации проблемы прогнозирования, которая заключаются в высокой доле апериодических составляющих графика потребления и его высокой дисперсии, в статье представлен пример на реальных данных. Для решения указанной проблемы в статье анализируется возможность применения мультиагентных систем при реализации организационной меры по повышению энергетической эффективности за счет краткосрочного прогнозирования потребления электрической энергии предприятиями. В статье предложена мультиагентная система, включающая агентов-потребителей (с учетом потребителей-регуляторов), агентов-генераторов и агентов-накопителей. При построении слабосвязанной сети агенты стремятся к решению не только собственной, но и общей целевой функции системы, которая состоит в обеспечении баланса мощности и уменьшении расходов на электрическую энергию. Показано, что возможно снизить расходы предприятия за счет прогнозирования потребления агентами-потребителями, нахождения оптимального графика собственной генерации, накопления электрической энергии и включенности потребителей-регуляторов. В рамках данного исследования для каждого агента определены целевая функция, входные и выходные потоки данных.
https://www.powervestniksusu.ru/index.php/PVS/article/view/825
Степанова А.И., Хальясмаа А.И., Матренин П.В.
Электротехнические установки и комплексы в нефтегазовой промышленности относятся к объектам критической инфраструктуры. Одно из требований к электротехническому комплексу заключается в соответствии требованиям по обеспечению энергосбережения и энергетической эффективности. Ввиду сложности учета технологических процессов на предприятиях нефтегазовой промышленности, в основном, применяются технические меры, требующие значительных капиталовложений. В данной статье рассматривается возможность внедрения организационной меры, которая заключается в прогнозировании электропотребления предприятия нефтегазовой промышленности. Для демонстрации проблемы прогнозирования, которая заключаются в высокой доле апериодических составляющих графика потребления и его высокой дисперсии, в статье представлен пример на реальных данных. Для решения указанной проблемы в статье анализируется возможность применения мультиагентных систем при реализации организационной меры по повышению энергетической эффективности за счет краткосрочного прогнозирования потребления электрической энергии предприятиями. В статье предложена мультиагентная система, включающая агентов-потребителей (с учетом потребителей-регуляторов), агентов-генераторов и агентов-накопителей. При построении слабосвязанной сети агенты стремятся к решению не только собственной, но и общей целевой функции системы, которая состоит в обеспечении баланса мощности и уменьшении расходов на электрическую энергию. Показано, что возможно снизить расходы предприятия за счет прогнозирования потребления агентами-потребителями, нахождения оптимального графика собственной генерации, накопления электрической энергии и включенности потребителей-регуляторов. В рамках данного исследования для каждого агента определены целевая функция, входные и выходные потоки данных.
20. Solar Irradiance Forecasting with Natural Language Processing of Cloud Observations and Interpretation of Results with Modified Shapley Additive Explanations
https://www.mdpi.com/1999-4893/17/4/150
Matrenin P.V., Gamaley V.V., Khalyasmaa A.I., Stepanova A.I.
Forecasting the generation of solar power plants (SPPs) requires taking into account meteorological parameters that influence the difference between the solar irradiance at the top of the atmosphere calculated with high accuracy and the solar irradiance at the tilted plane of the solar panel on the Earth’s surface. One of the key factors is cloudiness, which can be presented not only as a percentage of the sky area covered by clouds but also many additional parameters, such as the type of clouds, the distribution of clouds across atmospheric layers, and their height. The use of machine learning algorithms to forecast the generation of solar power plants requires retrospective data over a long period and formalising the features; however, retrospective data with detailed information about cloudiness are normally recorded in the natural language format. This paper proposes an algorithm for processing such records to convert them into a binary feature vector. Experiments conducted on data from a real solar power plant showed that this algorithm increases the accuracy of short-term solar irradiance forecasts by 5–15%, depending on the quality metric used. At the same time, adding features makes the model less transparent to the user, which is a significant drawback from the point of view of explainable artificial intelligence. Therefore, the paper uses an additive explanation algorithm based on the Shapley vector to interpret the model’s output. It is shown that this approach allows the machine learning model to explain why it generates a particular forecast, which will provide a greater level of trust in intelligent information systems in the power industry.
https://www.mdpi.com/1999-4893/17/4/150
Matrenin P.V., Gamaley V.V., Khalyasmaa A.I., Stepanova A.I.
Forecasting the generation of solar power plants (SPPs) requires taking into account meteorological parameters that influence the difference between the solar irradiance at the top of the atmosphere calculated with high accuracy and the solar irradiance at the tilted plane of the solar panel on the Earth’s surface. One of the key factors is cloudiness, which can be presented not only as a percentage of the sky area covered by clouds but also many additional parameters, such as the type of clouds, the distribution of clouds across atmospheric layers, and their height. The use of machine learning algorithms to forecast the generation of solar power plants requires retrospective data over a long period and formalising the features; however, retrospective data with detailed information about cloudiness are normally recorded in the natural language format. This paper proposes an algorithm for processing such records to convert them into a binary feature vector. Experiments conducted on data from a real solar power plant showed that this algorithm increases the accuracy of short-term solar irradiance forecasts by 5–15%, depending on the quality metric used. At the same time, adding features makes the model less transparent to the user, which is a significant drawback from the point of view of explainable artificial intelligence. Therefore, the paper uses an additive explanation algorithm based on the Shapley vector to interpret the model’s output. It is shown that this approach allows the machine learning model to explain why it generates a particular forecast, which will provide a greater level of trust in intelligent information systems in the power industry.
21. Weather Condition Clustering for Improvement of Photovoltaic Power Plant Generation Forecasting Accuracy
https://www.mdpi.com/1999-4893/17/9/419
Haljasmaa K.I., Bramm A.M., Matrenin P.V., Eroshenko S.A.
Together with the growing interest towards renewable energy sources within the framework of different strategies of various countries, the number of solar power plants keeps growing. However, managing optimal power generation for solar power plants has its own challenges. First comes the problem of work interruption and reduction in power generation. As the system must be tolerant to the faults, the relevance and significance of short-term forecasting of solar power generation becomes crucial. Within the framework of this research, the applicability of different forecasting methods for short-time forecasting is explained. The main goal of the research is to show an approach regarding how to make the forecast more accurate and overcome the above-mentioned challenges using opensource data as features. The data clustering algorithm based on KMeans is proposed to train unique models for specific groups of data samples to improve the generation forecast accuracy. Based on practical calculations, machine learning models based on Random Forest algorithm are selected which have been proven to have higher efficiency in predicting the generation of solar power plants. The proposed algorithm was successfully tested in practice, with an achieved accuracy near to 90%.
https://www.mdpi.com/1999-4893/17/9/419
Haljasmaa K.I., Bramm A.M., Matrenin P.V., Eroshenko S.A.
Together with the growing interest towards renewable energy sources within the framework of different strategies of various countries, the number of solar power plants keeps growing. However, managing optimal power generation for solar power plants has its own challenges. First comes the problem of work interruption and reduction in power generation. As the system must be tolerant to the faults, the relevance and significance of short-term forecasting of solar power generation becomes crucial. Within the framework of this research, the applicability of different forecasting methods for short-time forecasting is explained. The main goal of the research is to show an approach regarding how to make the forecast more accurate and overcome the above-mentioned challenges using opensource data as features. The data clustering algorithm based on KMeans is proposed to train unique models for specific groups of data samples to improve the generation forecast accuracy. Based on practical calculations, machine learning models based on Random Forest algorithm are selected which have been proven to have higher efficiency in predicting the generation of solar power plants. The proposed algorithm was successfully tested in practice, with an achieved accuracy near to 90%.
22. Review of Existing Tools for Software Implementation of Digital Twins in the Power Industry
https://www.mdpi.com/2411-5134/9/5/101
Iumanova I.F., Matrenin P.V., Khalyasmaa A.I.
Digital twin technology is an important tool for the digitalization of the power industry. A digital twin is a concept that allows for the creation of virtual copies of real objects that can be used for technical state analysis, predictive analysis, and optimization of the operation of power systems and their components. Digital twins are used to address different issues, including the management of equipment reliability and efficiency, integration of renewable energy sources, and increased flexibility and adaptability of power grids. Digital twins can be developed with the use of specialized software solutions for designing, prototyping, developing, deploying, and supporting. The existing diversity of software requires systematization for a well-informed choice of digital twin’s development tool. It is necessary to take into account the technical characteristics of power systems and their elements (equipment of power plants, substations and power grids of power systems, mini- and microgrids). The reviews are dedicated to tools for creating digital twins in the power industry. The usage of Digital Twin Definition Language for the description data of electromagnetic, thermal, and hydrodynamic models of a power transformer is presented.
https://www.mdpi.com/2411-5134/9/5/101
Iumanova I.F., Matrenin P.V., Khalyasmaa A.I.
Digital twin technology is an important tool for the digitalization of the power industry. A digital twin is a concept that allows for the creation of virtual copies of real objects that can be used for technical state analysis, predictive analysis, and optimization of the operation of power systems and their components. Digital twins are used to address different issues, including the management of equipment reliability and efficiency, integration of renewable energy sources, and increased flexibility and adaptability of power grids. Digital twins can be developed with the use of specialized software solutions for designing, prototyping, developing, deploying, and supporting. The existing diversity of software requires systematization for a well-informed choice of digital twin’s development tool. It is necessary to take into account the technical characteristics of power systems and their elements (equipment of power plants, substations and power grids of power systems, mini- and microgrids). The reviews are dedicated to tools for creating digital twins in the power industry. The usage of Digital Twin Definition Language for the description data of electromagnetic, thermal, and hydrodynamic models of a power transformer is presented.
23. Optimized Wavelet Transform for the Development of an Algorithm Designed for the Analysis of Digital Substation Electrical Equipment Parameters
https://www.mdpi.com/2411-5134/9/5/108
Efimov A.S., Eroshenko S.A., Matrenin P.V., Popovtsev V.V.
This study emphasizes the urgent need for systems that monitor the operational states of primary electrical equipment, particularly power transformers. The rapid digitalization of and increasing data volumes from substations, coupled with the inability to retrofit outdated equipment with modern sensors, underscore the necessity for algorithms that analyze the operational parameters of digital substations based on key power system metrics such as current and voltage. This research focuses on digital substations with Architecture III and aims to develop an algorithm for processing digital substation data through an appropriate mathematical tool for time-series analysis. For this purpose, the fast discrete wavelet transform was chosen as the most suitable method. Within the framework of the research, possible transformer faults were divided into two categories by the nature of their manifestation. A mathematical model for two internal transformer fault categories was built. The most effective parameters from the point of view of the possibility of identifying an internal fault were selected. The proposed algorithm shows its effectiveness in the compact representation of the signal and compression of the time series of the parameter to be monitored.
https://www.mdpi.com/2411-5134/9/5/108
Efimov A.S., Eroshenko S.A., Matrenin P.V., Popovtsev V.V.
This study emphasizes the urgent need for systems that monitor the operational states of primary electrical equipment, particularly power transformers. The rapid digitalization of and increasing data volumes from substations, coupled with the inability to retrofit outdated equipment with modern sensors, underscore the necessity for algorithms that analyze the operational parameters of digital substations based on key power system metrics such as current and voltage. This research focuses on digital substations with Architecture III and aims to develop an algorithm for processing digital substation data through an appropriate mathematical tool for time-series analysis. For this purpose, the fast discrete wavelet transform was chosen as the most suitable method. Within the framework of the research, possible transformer faults were divided into two categories by the nature of their manifestation. A mathematical model for two internal transformer fault categories was built. The most effective parameters from the point of view of the possibility of identifying an internal fault were selected. The proposed algorithm shows its effectiveness in the compact representation of the signal and compression of the time series of the parameter to be monitored.
24. Spring Runoff Simulation of Snow-Dominant Catchment in Steppe Regions: A Comparison Study of Lumped Conceptual Models
https://www.mdpi.com/2411-5134/9/5/109
Eroshenko S.A., Shmakov E.I., Klimenko D.E., Iumanova I.F.
This paper explores the application of conceptual hydrological models in optimizing the operation of hydroelectric power plants (HPPs) in steppe regions, a crucial aspect of promoting low-carbon energy solutions. The study aims to identify the most suitable conceptual hydrological model for predicting reservoir inflows from multiple catchments in a steppe region, where spring runoff dominates the annual water volume and requires careful consideration of snowfall. Two well-known conceptual models, HBV and GR6J-CemaNeige, which incorporate snow-melting processes, were evaluated. The research also investigated the best approach to preprocessing historical data to enhance model accuracy. Furthermore, the study emphasizes the importance of accurately defining low-water periods to ensure reliable HPP operation through more accurate inflow forecasting. A hypothesis was proposed to explore the relationship between atmospheric circulation and the definition of low-water periods; however, the findings did not support this hypothesis. Overall, the results suggest that combining the conceptual models under consideration can lead to more accurate forecasts, underscoring the need for integrated approaches in managing HPP reservoirs and promoting sustainable energy production.
https://www.mdpi.com/2411-5134/9/5/109
Eroshenko S.A., Shmakov E.I., Klimenko D.E., Iumanova I.F.
This paper explores the application of conceptual hydrological models in optimizing the operation of hydroelectric power plants (HPPs) in steppe regions, a crucial aspect of promoting low-carbon energy solutions. The study aims to identify the most suitable conceptual hydrological model for predicting reservoir inflows from multiple catchments in a steppe region, where spring runoff dominates the annual water volume and requires careful consideration of snowfall. Two well-known conceptual models, HBV and GR6J-CemaNeige, which incorporate snow-melting processes, were evaluated. The research also investigated the best approach to preprocessing historical data to enhance model accuracy. Furthermore, the study emphasizes the importance of accurately defining low-water periods to ensure reliable HPP operation through more accurate inflow forecasting. A hypothesis was proposed to explore the relationship between atmospheric circulation and the definition of low-water periods; however, the findings did not support this hypothesis. Overall, the results suggest that combining the conceptual models under consideration can lead to more accurate forecasts, underscoring the need for integrated approaches in managing HPP reservoirs and promoting sustainable energy production.
25. Application of SHAP and Multi-Agent Approach for Short-Term Forecast of Power Consumption of Gas Industry Enterprises
https://www.mdpi.com/1999-4893/17/10/447
Stepanova A.I., Khalyasmaa A.I., Matrenin P.V., Eroshenko S.A.
Currently, machine learning methods are widely applied in the power industry to solve various tasks, including short-term power consumption forecasting. However, the lack of interpretability of machine learning methods can lead to their incorrect use, potentially resulting in electrical system instability or equipment failures. This article addresses the task of short-term power consumption forecasting, one of the tasks of enhancing the energy efficiency of gas industry enterprises. In order to reduce the risks of making incorrect decisions based on the results of short-term power consumption forecasts made by machine learning methods, the SHapley Additive exPlanations method was proposed. Additionally, the application of a multi-agent approach for the decomposition of production processes using self-generation agents, energy storage agents, and consumption agents was demonstrated. It can enable the safe operation of critical infrastructure, for instance, adjusting the operation modes of self-generation units and energy-storage systems, optimizing the power consumption schedule, and reducing electricity and power costs. A comparative analysis of various algorithms for constructing decision tree ensembles was conducted to forecast power consumption by gas industry enterprises with different numbers of categorical features. The experiments demonstrated that using the developed method and production process factors reduced the MAE from 105.00 kWh (MAPE of 16.81%), obtained through expert forecasting, to 15.52 kWh (3.44%). Examples were provided of how the use of SHapley Additive exPlanation can increase the safety of the electrical system management of gas industry enterprises by improving experts’ confidence in the results of the information system.
https://www.mdpi.com/1999-4893/17/10/447
Stepanova A.I., Khalyasmaa A.I., Matrenin P.V., Eroshenko S.A.
Currently, machine learning methods are widely applied in the power industry to solve various tasks, including short-term power consumption forecasting. However, the lack of interpretability of machine learning methods can lead to their incorrect use, potentially resulting in electrical system instability or equipment failures. This article addresses the task of short-term power consumption forecasting, one of the tasks of enhancing the energy efficiency of gas industry enterprises. In order to reduce the risks of making incorrect decisions based on the results of short-term power consumption forecasts made by machine learning methods, the SHapley Additive exPlanations method was proposed. Additionally, the application of a multi-agent approach for the decomposition of production processes using self-generation agents, energy storage agents, and consumption agents was demonstrated. It can enable the safe operation of critical infrastructure, for instance, adjusting the operation modes of self-generation units and energy-storage systems, optimizing the power consumption schedule, and reducing electricity and power costs. A comparative analysis of various algorithms for constructing decision tree ensembles was conducted to forecast power consumption by gas industry enterprises with different numbers of categorical features. The experiments demonstrated that using the developed method and production process factors reduced the MAE from 105.00 kWh (MAPE of 16.81%), obtained through expert forecasting, to 15.52 kWh (3.44%). Examples were provided of how the use of SHapley Additive exPlanation can increase the safety of the electrical system management of gas industry enterprises by improving experts’ confidence in the results of the information system.
Монографии
1. Интеллектуальные мультиагентные системы в электроэнергетике https://elibrary.ru/item.asp?id=57174215
Хальясмаа А.И., Ерошенко С.А., Юманова И.Ф., Степанова А.И., Матренин П.В.
В монографии рассматриваются подходы к созданию мультиагентных систем и их применению в электроэнергетике, описываются архитектуры и классификации таких систем, используемые онтологические модели и методы коммуникации агентов. Особое внимание уделено анализу современных методов обучения с подкреплением и их возможностей для создания многоуровневых мультиагентных систем в задачах моделирования и оптимизации сложных технических систем, в частности, в электроэнергетике. Монография может представлять интерес для широкого круга научных работников, аспирантов, магистрантов, занимающихся вопросами разработки, проектирования, реализации и эксплуатации интеллектуальных систем в электроэнергетике.
Интеллектуальная собственность
1. Программа для анализа графов электрических сетей «Graph_solver»
Брамм А.М., Ерошенко С.А.Свидетельство о государственной регистрации программы для ЭВМ 2022682436, 22.11.2022.
2. Подпрограмма синхронизации взаимодействующих потоков обработки данных в режиме реального времени на основе обмена сигналами и медиатора
Хальясмаа А.И., Матренин П.В., Ерошенко С.А.Свидетельство о государственной регистрации программы для ЭВМ 2023661767, 01.06.2023.
3. Библиотека алгоритмов оптимизации на основе роевого интеллекта
Хальясмаа А.И., Матренин П.В., Ерошенко С.А.Свидетельство о государственной регистрации программы для ЭВМ 2023660237, 25.05.2023.
4. Программа краткосрочного прогнозирования потребления электрической энергии предприятием на базе моделей машинного обучения с учетом метеорологических и производственных факторов
Матренин П.В., Степанова А.И.Свидетельство о государственной регистрации программы для ЭВМ 2024616513 , 05.04.2024.
Доклады на конференциях
1. Prospects for the Use of Intelligent Multi-agent Models for the Control of Objects of Deeply Integrated Power Systems — 2022 Symposium on Smart Energy (USSEC)
https://ussec.ieeesiberia.org/
Eroshenko S.A.
2. Development of Automatic Determination of Types of Damage System of the Main Equipment of HPP — 2022 IEEЕ Ural-Siberian Conference on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT)
https://usbereit.ieeesiberia.org/
Khalyasmaa A.I.
3. Maintenance Optimization within the Lifecycle Management of the Gas Compressor’s Electric Motors — 2023 IEEE 24th International Conference of Young Professionals in Electron Devices and Materials (EDM)
https://ieeexplore.ieee.org/document/10225198
Khalyasmaa A.I.
4. К вопросу разработки модели дуги отключения на основе расчета мультифизических процессов при коммутации элегазовых выключателей — 2023 VIII Международная научно-техническая конференция «Развитие и повышение надежности распределительных электрических сетей»
https://event.eepir.ru/programma/05.07.2023.html
Поповцев В.В.
5. Assessment of the Hydroelectric Power Plant Cascade Economic Efficiency — 2023 Belarusian-Ural-Siberian Smart Energy Conference (BUSSEC)
https://ieeexplore.ieee.org/document/10296263
Haljasmaa K.I.
6. Influence of Machine Learning Method Choice on the Accuracy of Power Load Forecast Models and HPP Cascade Mode — 2023 Belarusian-Ural-Siberian Smart Energy Conference (BUSSEC)
https://ieeexplore.ieee.org/document/10296424
Haljasmaa K.I.
7. Algorithm for Calculating the Water and Energy Mode of the Cascade of Hydroelectric Power Plants on the Basis of the Integrated Mathematical Model
— 2023 Belarusian-Ural-Siberian Smart Energy Conference (BUSSEC)
https://ieeexplore.ieee.org/document/10296379
Haljasmaa K.I.
8. Development of Automated Life Cycle Management System for Electrically Driven Compressor Units in the Oil and Gas Industry
— 2023 Belarusian-Ural-Siberian Smart Energy Conference (BUSSEC)
https://ieeexplore.ieee.org/document/10296464
Khalyasmaa A.I.
9. Study of Power Transformers Made of Various Electrical Steels — 2023 International Russian Automation Conference, (RusAutoCon)
https://rusautocon.org/programme2023-rus.html
Shmakov E.I.
10. Numerical Simulation of Natural Convection in the Power Transformer — 2023 International Russian Automation Conference, (RusAutoCon)
https://rusautocon.org/programme2023-rus.html
Smolyanov I.A.
11. New Load Forecasting Ensemble Model based on LightGBM for Gas Industry Enterprises — 2024 IEEE Ural-Siberian Conference on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT)
https://usbereit.ieeesiberia.org/schedule/
Stepanova A.I.
12. Multiobjective Optimization in the Problem of SVC Placement Using N-1 Approach and Population-Based Algorithms — 2024 IEEE 25th International Conference of Young Professionals in Electron Devices and Materials (EDM)
https://ieeexplore.ieee.org/document/10615078
Popovtsev V.V.
13. Применение киберфизических систем и алгоритмов искусственного интеллекта при создании цифровых двойников энергообъектов — 2024 IX Международной научно-технической конференции «Развитие и повышение надежности распределительных электрических сетей»
https://event.eepir.ru/programma.html
Хальясмаа А.И.