Pub Date : 2021-11-13DOI: 10.1109/USSEC53120.2021.9655741
Yu. N. Bulatov, A. Kryukov, K. Suslov
The application of a large number of distributed generation plants, built on the basis of synchronous generators in electric energy system (EES), requires solving the problem of their centralized control, adjustment of local controllers and stabilization of alternating current frequency, which entails taking into account a large number of interrelated system parameters. For example, the use of several hydrogenerators in a small-scale HPP requires solving problems of distribution and optimization of their load, as well as group control. These problems can be solved using prognostic control algorithms. Below is a description of the method to control the frequency of a group of low power synchronous hydrogenerators, the description of computer models of DG plants and the proposed group power controller of prognostic type, as well as the simulation results in the modes of additional powerful load connection and disconnection from EES. The research was conducted in MATLAB environment. The aim was to determine the effectiveness of group control of prognostic speed controllers of several hydrogenerators of the same type in emergency and post-emergency modes. The results of computer simulation indicate that the use of prognostic controllers reduces overshoot, oscillability index and transient time for voltage, rotational frequency and frequency in the normal and emergency conditions. The proposed methods of formation and tunning the group prognostic speed controllers allow to improve quality indices of small-scale HPP voltage and frequency control, while retaining the former settings of the local controllers.
{"title":"Methods for Formation and Tunning of Group Prognostic Controller of Hydrogenerators Rotors' Rotational Frequency","authors":"Yu. N. Bulatov, A. Kryukov, K. Suslov","doi":"10.1109/USSEC53120.2021.9655741","DOIUrl":"https://doi.org/10.1109/USSEC53120.2021.9655741","url":null,"abstract":"The application of a large number of distributed generation plants, built on the basis of synchronous generators in electric energy system (EES), requires solving the problem of their centralized control, adjustment of local controllers and stabilization of alternating current frequency, which entails taking into account a large number of interrelated system parameters. For example, the use of several hydrogenerators in a small-scale HPP requires solving problems of distribution and optimization of their load, as well as group control. These problems can be solved using prognostic control algorithms. Below is a description of the method to control the frequency of a group of low power synchronous hydrogenerators, the description of computer models of DG plants and the proposed group power controller of prognostic type, as well as the simulation results in the modes of additional powerful load connection and disconnection from EES. The research was conducted in MATLAB environment. The aim was to determine the effectiveness of group control of prognostic speed controllers of several hydrogenerators of the same type in emergency and post-emergency modes. The results of computer simulation indicate that the use of prognostic controllers reduces overshoot, oscillability index and transient time for voltage, rotational frequency and frequency in the normal and emergency conditions. The proposed methods of formation and tunning the group prognostic speed controllers allow to improve quality indices of small-scale HPP voltage and frequency control, while retaining the former settings of the local controllers.","PeriodicalId":260032,"journal":{"name":"2021 Ural-Siberian Smart Energy Conference (USSEC)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121431967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-13DOI: 10.1109/USSEC53120.2021.9655736
Jabrane Slimani, Abdeslam Kadrani, I. El harraki, E. Ezzahid
Since 2010, Morocco has been pursuing an energy strategy focused mainly on increasing the share of renewable sources in the energy mix, promoting energy efficiency, and boosting regional trade. This energy strategy plans to increase the share of renewable electricity to 42 % of installed capacity in 2020 and more than 52% in 2030. In this study, it is assumed that Morocco will continue this development of the share of renewable energies, setting new targets for 2040 and 2050, respectively, of 62% and 72%. Thus, a bottom-up linear optimization model is proposed to study the demand, production, and installed capacity of electrical energy in 2050 in Morocco. The aim is to identify the optimal trajectory for the development of the installed capacity of wind energy and its share in the electricity mix at this horizon. For this purpose, three Scenarios of wind energy development are considered. For each of these Scenarios, the impact on the electricity mix is assessed in terms of discounted global costs and greenhouse gas emissions. The results show Morocco is able to reduce its greenhouse gas emissions from the electricity sector by more than 85% compared to their current projected levels. It can also be concluded that wind energy is a more mature technology than solar photovoltaic and that natural gas production capacity should be greatly increased.
{"title":"Long-term Wind Power Development in Morocco: Optimality Assessment using Bottom-up Modeling","authors":"Jabrane Slimani, Abdeslam Kadrani, I. El harraki, E. Ezzahid","doi":"10.1109/USSEC53120.2021.9655736","DOIUrl":"https://doi.org/10.1109/USSEC53120.2021.9655736","url":null,"abstract":"Since 2010, Morocco has been pursuing an energy strategy focused mainly on increasing the share of renewable sources in the energy mix, promoting energy efficiency, and boosting regional trade. This energy strategy plans to increase the share of renewable electricity to 42 % of installed capacity in 2020 and more than 52% in 2030. In this study, it is assumed that Morocco will continue this development of the share of renewable energies, setting new targets for 2040 and 2050, respectively, of 62% and 72%. Thus, a bottom-up linear optimization model is proposed to study the demand, production, and installed capacity of electrical energy in 2050 in Morocco. The aim is to identify the optimal trajectory for the development of the installed capacity of wind energy and its share in the electricity mix at this horizon. For this purpose, three Scenarios of wind energy development are considered. For each of these Scenarios, the impact on the electricity mix is assessed in terms of discounted global costs and greenhouse gas emissions. The results show Morocco is able to reduce its greenhouse gas emissions from the electricity sector by more than 85% compared to their current projected levels. It can also be concluded that wind energy is a more mature technology than solar photovoltaic and that natural gas production capacity should be greatly increased.","PeriodicalId":260032,"journal":{"name":"2021 Ural-Siberian Smart Energy Conference (USSEC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123311532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-13DOI: 10.1109/USSEC53120.2021.9655762
E. Vorobyev, V. Antonov, N. Ivanov, V. Naumov, A. Soldatov
The existing structural uncertainty of the alarm process signal, which consists in the unknown dimension of the model and the uncertainty of the type of the process terms, requires the use of special methods and models of signal recognition that can work under conditions of a priori uncertainty. The resolution of the structural model is affected by the sampling frequency of the input signal, the competition of the components of the effective core filter, the intermodel decimation of the signal samples, the decimation of the residual samples, and the order of the initial filter. As the filter order increases, the signal processing window increases, so an unjustified increase in the order of the adaptive filter is undesirable. This report discusses a new approach to adaptive structural analysis based on a multi-channel adaptive filter. The advantages of multi-channel structures are the possibility of a different step within the model decimation in the filters.
{"title":"Fundamentals of Multichannelstructural Analysis of Electrical Signals","authors":"E. Vorobyev, V. Antonov, N. Ivanov, V. Naumov, A. Soldatov","doi":"10.1109/USSEC53120.2021.9655762","DOIUrl":"https://doi.org/10.1109/USSEC53120.2021.9655762","url":null,"abstract":"The existing structural uncertainty of the alarm process signal, which consists in the unknown dimension of the model and the uncertainty of the type of the process terms, requires the use of special methods and models of signal recognition that can work under conditions of a priori uncertainty. The resolution of the structural model is affected by the sampling frequency of the input signal, the competition of the components of the effective core filter, the intermodel decimation of the signal samples, the decimation of the residual samples, and the order of the initial filter. As the filter order increases, the signal processing window increases, so an unjustified increase in the order of the adaptive filter is undesirable. This report discusses a new approach to adaptive structural analysis based on a multi-channel adaptive filter. The advantages of multi-channel structures are the possibility of a different step within the model decimation in the filters.","PeriodicalId":260032,"journal":{"name":"2021 Ural-Siberian Smart Energy Conference (USSEC)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122487976","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-13DOI: 10.1109/USSEC53120.2021.9655759
D. Ignatiev, V. Popovtsev
The problem of the optimal placement of static var compensator is studied in this paper. Since there is a multitude of parameters that are influenced by static var compensator operation, in addition to various goals of static var compensator installation, the multi-objective optimization problem is being solved. The optimization methods in use are the genetic algorithm and the particle swarm, with the full enumeration method being applied for the purpose of obtaining “benchmark” results to compare with. The variable shunt capacitance is used as static var compensator model in N -1 based power flow calculations. N-l contingencies are proven to be taken into account because their integration into algorithms of static var compensator placement optimization radically changes the results, as it was proven by authors in their previous study. The current research has demonstrated the need to carry out detailed analysis, adjustment and improvement of existing optimization algorithms in order to obtain solutions in the most efficient way. Also sets of objective functions should be carefully selected in accordance with the purpose of device installation, its type and power system operation.
{"title":"N-1 Based Multi-Objective Optimization of Static Var Compensator Placement Using Heuristic Methods","authors":"D. Ignatiev, V. Popovtsev","doi":"10.1109/USSEC53120.2021.9655759","DOIUrl":"https://doi.org/10.1109/USSEC53120.2021.9655759","url":null,"abstract":"The problem of the optimal placement of static var compensator is studied in this paper. Since there is a multitude of parameters that are influenced by static var compensator operation, in addition to various goals of static var compensator installation, the multi-objective optimization problem is being solved. The optimization methods in use are the genetic algorithm and the particle swarm, with the full enumeration method being applied for the purpose of obtaining “benchmark” results to compare with. The variable shunt capacitance is used as static var compensator model in N -1 based power flow calculations. N-l contingencies are proven to be taken into account because their integration into algorithms of static var compensator placement optimization radically changes the results, as it was proven by authors in their previous study. The current research has demonstrated the need to carry out detailed analysis, adjustment and improvement of existing optimization algorithms in order to obtain solutions in the most efficient way. Also sets of objective functions should be carefully selected in accordance with the purpose of device installation, its type and power system operation.","PeriodicalId":260032,"journal":{"name":"2021 Ural-Siberian Smart Energy Conference (USSEC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126042620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-13DOI: 10.1109/USSEC53120.2021.9655719
F. Tarasov, E. Shmakov
The paper is concerned with numerical study of parameters of the magnetic system for induction heating of the large-size installations. The paper is included in a papers series concerning development of the installation for maintaining the specified pressing tool temperature for a long time period, more than 24 hours. Induction heating is the basic heating mechanism. Studies of the energy parameters depending on the power frequency are presented in this section of the paper. Determination of the basic frequency dependencies of efficiency and heat release is the objective of the paper. The studies were performed using numerical modeling in a three-dimensional formulation by the finite element method. A parametric study was carried out in which the frequency of the supply current was changed from 50 Hz to 60 kHz. During the study, the dependences of total electromagnetic power, volumetric loss density and efficiency on frequency were obtained. It was found that the optimal frequency for the most efficient induction heating process is 10 kHz.
{"title":"Induction Heating of the Large-Size Installations. Part 1. Study on the Power Frequency Dependence of the Heating Efficiency","authors":"F. Tarasov, E. Shmakov","doi":"10.1109/USSEC53120.2021.9655719","DOIUrl":"https://doi.org/10.1109/USSEC53120.2021.9655719","url":null,"abstract":"The paper is concerned with numerical study of parameters of the magnetic system for induction heating of the large-size installations. The paper is included in a papers series concerning development of the installation for maintaining the specified pressing tool temperature for a long time period, more than 24 hours. Induction heating is the basic heating mechanism. Studies of the energy parameters depending on the power frequency are presented in this section of the paper. Determination of the basic frequency dependencies of efficiency and heat release is the objective of the paper. The studies were performed using numerical modeling in a three-dimensional formulation by the finite element method. A parametric study was carried out in which the frequency of the supply current was changed from 50 Hz to 60 kHz. During the study, the dependences of total electromagnetic power, volumetric loss density and efficiency on frequency were obtained. It was found that the optimal frequency for the most efficient induction heating process is 10 kHz.","PeriodicalId":260032,"journal":{"name":"2021 Ural-Siberian Smart Energy Conference (USSEC)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126865251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-13DOI: 10.1109/USSEC53120.2021.9655721
A. Serov
The complex spectrum is used as a basic parameter for calculating spectrum and power parameters of the signals of real electrical power grids. For measuring the complex spectrum, the most popular is the discrete Fourier transform technique. Analog-to-digital converters are used to convert voltage and current samples to the digital form. The conversion function of analog-to-digital converters is not ideal. The largest contribution to the spectrum measurement error is due to the influence of quantization error and nonlinearity, since these components almost impossible to reduce by offset-adjustment and calibration. The “worst case” method can be applied to estimate the measurement error of the spectrum, electric power and other parameters. This method makes it possible to estimate “from above” the measurement error of considerate parameters, which makes it in demand in applications where the error estimate must necessarily exceed its real value. The analytical relationships are obtained for calculation of the error estimation of spectrum and power parameters caused by quantization error and nonlinearity. The influence of parameters of input signals and analog-to-digital converter on the error of the measured parameters is investigated. The influence of the nonlinearity form on the measurement error of considered parameters is estimated by simulation modeling in Matlab environment. It is shown that for all the considered nonlinearity forms, the error estimation result does not exceed the “worst case” method estimation.
{"title":"Application of the “Worst Case” Method to Estimate the Spectrum and Power Measurement Error Caused by ADC Imperfection","authors":"A. Serov","doi":"10.1109/USSEC53120.2021.9655721","DOIUrl":"https://doi.org/10.1109/USSEC53120.2021.9655721","url":null,"abstract":"The complex spectrum is used as a basic parameter for calculating spectrum and power parameters of the signals of real electrical power grids. For measuring the complex spectrum, the most popular is the discrete Fourier transform technique. Analog-to-digital converters are used to convert voltage and current samples to the digital form. The conversion function of analog-to-digital converters is not ideal. The largest contribution to the spectrum measurement error is due to the influence of quantization error and nonlinearity, since these components almost impossible to reduce by offset-adjustment and calibration. The “worst case” method can be applied to estimate the measurement error of the spectrum, electric power and other parameters. This method makes it possible to estimate “from above” the measurement error of considerate parameters, which makes it in demand in applications where the error estimate must necessarily exceed its real value. The analytical relationships are obtained for calculation of the error estimation of spectrum and power parameters caused by quantization error and nonlinearity. The influence of parameters of input signals and analog-to-digital converter on the error of the measured parameters is investigated. The influence of the nonlinearity form on the measurement error of considered parameters is estimated by simulation modeling in Matlab environment. It is shown that for all the considered nonlinearity forms, the error estimation result does not exceed the “worst case” method estimation.","PeriodicalId":260032,"journal":{"name":"2021 Ural-Siberian Smart Energy Conference (USSEC)","volume":"44 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127990836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-13DOI: 10.1109/USSEC53120.2021.9655740
Alexandra Sidorova, I. Litvinov, D. Kornilovich, V. Fedorova, Oleg Tanfilev, Vasily Titov
The aim of the work is to develop a method and means for diagnostics of instrument transformers, allowing high accuracy to identify damage to the winding or core of a transformer. It implies definition of a clear diagnostic criterion that allows assessing the transformer under test conditions. The suggested method for detecting damage is based on mathematical processing of transformer magnetizing current, which involves analyzing its harmonic composition and determining amplitudes and initial phases ratio of magnetizing current fundamental and higher harmonics. The applied digital signal processing includes digital filtering and Fourier series decomposition of the signal. The magnetizing current signals are used as initial data for analysis by the proposed method and can be obtained during routine work on taking current-voltage characteristic of the transformer using the RETOM-51 (61) test device. Based on analysis results of experimental data obtained from the various types tests of instrument transformers, recommendations were formed for application of the proposed method: it is recommended to record the instantaneous values of current simultaneously with taking the current-versus-voltage characteristic for its linear and nonlinear parts. In this case, to confirm presence of damage, it is sufficient to fix phase or amplitude deviation of calculated phasor, determined by harmonic components ratio of magnetizing current, at least by 10% at one or more points. Application of described method will make it possible to reliably identify internal faults of current transformers without significantly complicating the diagnostic and test equipment.
{"title":"Development and Verification of an Advanced Method for Diagnosing Measuring Transformers","authors":"Alexandra Sidorova, I. Litvinov, D. Kornilovich, V. Fedorova, Oleg Tanfilev, Vasily Titov","doi":"10.1109/USSEC53120.2021.9655740","DOIUrl":"https://doi.org/10.1109/USSEC53120.2021.9655740","url":null,"abstract":"The aim of the work is to develop a method and means for diagnostics of instrument transformers, allowing high accuracy to identify damage to the winding or core of a transformer. It implies definition of a clear diagnostic criterion that allows assessing the transformer under test conditions. The suggested method for detecting damage is based on mathematical processing of transformer magnetizing current, which involves analyzing its harmonic composition and determining amplitudes and initial phases ratio of magnetizing current fundamental and higher harmonics. The applied digital signal processing includes digital filtering and Fourier series decomposition of the signal. The magnetizing current signals are used as initial data for analysis by the proposed method and can be obtained during routine work on taking current-voltage characteristic of the transformer using the RETOM-51 (61) test device. Based on analysis results of experimental data obtained from the various types tests of instrument transformers, recommendations were formed for application of the proposed method: it is recommended to record the instantaneous values of current simultaneously with taking the current-versus-voltage characteristic for its linear and nonlinear parts. In this case, to confirm presence of damage, it is sufficient to fix phase or amplitude deviation of calculated phasor, determined by harmonic components ratio of magnetizing current, at least by 10% at one or more points. Application of described method will make it possible to reliably identify internal faults of current transformers without significantly complicating the diagnostic and test equipment.","PeriodicalId":260032,"journal":{"name":"2021 Ural-Siberian Smart Energy Conference (USSEC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124921284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-13DOI: 10.1109/USSEC53120.2021.9655745
L. Osipov, L. Plotnikov
The efficient operation of power machines and installations is largely determined by the initially set value of flow turbulence in gas-air systems. Consequently, the level of flow turbulence affects the formation of the boundary layer and the quality of heat transfer in the channels. The main goal of this study was to examine the effect of the turbulence scale on the heat transfer intensity from stationary gas flows in channels of different cross-sections. The research was carried out using numerical modeling of gas dynamics and heat transfer of stationary flows based on the Computational Fluid Dynamics method. Data on the assessment of the effect of flow turbulence scale on heat transfer in channels of different profiles for different gas flow regimes are presented in the paper. It was found that the turbulence scale has an insignificant effect on the change in the heat transfer coefficient in profiled channels. It is shown that the use of a square-shaped channel leads to a decrease in the heat transfer coefficient by an average of 4% in comparison with a circular channel. Conversely, the use of a channel with a triangular cross section causes an increase in the heat transfer coefficient within 10%. The suppression of the heat transfer coefficient along the channel length (downstream) by an average of 26% for all the considered channel profiles is demonstrated. The obtained data are planned to be used to predict thermophysical processes in gas exchange systems of heat engines for various purposes.
{"title":"Influence of the Turbulence Scale of Gas Flows on the Heat Exchange Intensity in Channels with Different Cross Sections","authors":"L. Osipov, L. Plotnikov","doi":"10.1109/USSEC53120.2021.9655745","DOIUrl":"https://doi.org/10.1109/USSEC53120.2021.9655745","url":null,"abstract":"The efficient operation of power machines and installations is largely determined by the initially set value of flow turbulence in gas-air systems. Consequently, the level of flow turbulence affects the formation of the boundary layer and the quality of heat transfer in the channels. The main goal of this study was to examine the effect of the turbulence scale on the heat transfer intensity from stationary gas flows in channels of different cross-sections. The research was carried out using numerical modeling of gas dynamics and heat transfer of stationary flows based on the Computational Fluid Dynamics method. Data on the assessment of the effect of flow turbulence scale on heat transfer in channels of different profiles for different gas flow regimes are presented in the paper. It was found that the turbulence scale has an insignificant effect on the change in the heat transfer coefficient in profiled channels. It is shown that the use of a square-shaped channel leads to a decrease in the heat transfer coefficient by an average of 4% in comparison with a circular channel. Conversely, the use of a channel with a triangular cross section causes an increase in the heat transfer coefficient within 10%. The suppression of the heat transfer coefficient along the channel length (downstream) by an average of 26% for all the considered channel profiles is demonstrated. The obtained data are planned to be used to predict thermophysical processes in gas exchange systems of heat engines for various purposes.","PeriodicalId":260032,"journal":{"name":"2021 Ural-Siberian Smart Energy Conference (USSEC)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121039433","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-13DOI: 10.1109/USSEC53120.2021.9655732
P. Matrenin, D. Antonenkov, V. Manusov
For open cast mining enterprises, electricity costs significantly affect the self-cost of production. To reduce the electricity tariff, an enterprise should improve the accuracy of short-term power consumption forecasting (day-ahead). Forecasting the power consumption of a mining enterprise is a difficult task due to the influence of many factors: technological, geological, metrological, and administrative. Therefore, it is necessary to use artificial intelligence methods based on machine learning, such as artificial neural networks and ensemble models. They show high efficiency in forecasting the daily curve of electricity consumption of large power supply systems, households, and industrial enterprises. At the same time, at present, there are practically no studies of modern machine learning methods concerning the short-term power consumption forecasting of mining enterprises. It is largely due to the lack of open access data on mining enterprises' power consumption. Research and verification of the results require the data on various enterprises for several years. In this work, the authors' data on four enterprises in Yakutia operating in the open cast coal mining and processing for four years are used. A study of two different classes of machine learning methods has been carried out. The first one is processing retrospective power consumption data as a time series using recurrent neural networks. The second one is selecting the most significant features and applying ensemble models based on decision trees. The advantages and disadvantages of these approaches are shown; the obtained forecast accuracy for four enterprises that differ in their technological processes are given.
{"title":"Recurrent and Ensemble Models for Short-Term Load Forecasting of Coal Mining Companies","authors":"P. Matrenin, D. Antonenkov, V. Manusov","doi":"10.1109/USSEC53120.2021.9655732","DOIUrl":"https://doi.org/10.1109/USSEC53120.2021.9655732","url":null,"abstract":"For open cast mining enterprises, electricity costs significantly affect the self-cost of production. To reduce the electricity tariff, an enterprise should improve the accuracy of short-term power consumption forecasting (day-ahead). Forecasting the power consumption of a mining enterprise is a difficult task due to the influence of many factors: technological, geological, metrological, and administrative. Therefore, it is necessary to use artificial intelligence methods based on machine learning, such as artificial neural networks and ensemble models. They show high efficiency in forecasting the daily curve of electricity consumption of large power supply systems, households, and industrial enterprises. At the same time, at present, there are practically no studies of modern machine learning methods concerning the short-term power consumption forecasting of mining enterprises. It is largely due to the lack of open access data on mining enterprises' power consumption. Research and verification of the results require the data on various enterprises for several years. In this work, the authors' data on four enterprises in Yakutia operating in the open cast coal mining and processing for four years are used. A study of two different classes of machine learning methods has been carried out. The first one is processing retrospective power consumption data as a time series using recurrent neural networks. The second one is selecting the most significant features and applying ensemble models based on decision trees. The advantages and disadvantages of these approaches are shown; the obtained forecast accuracy for four enterprises that differ in their technological processes are given.","PeriodicalId":260032,"journal":{"name":"2021 Ural-Siberian Smart Energy Conference (USSEC)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115294501","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-13DOI: 10.1109/USSEC53120.2021.9655718
A. Bramm, S. Eroshenko
The paper is concerned with the problem of determining the optimal reconfiguration of the power grid for each hour of the day. The optimization criterion is the value of the total power losses in the power grid. The considered network operates in parallel with a large power system and includes two solar power plants. Consumers in this network are represented by electricity load curve of three types. The technique for determining the optimal configuration is based on knowledge about the features of flow distribution in grids with renewable energy sources and the fundamental principles from the graph theory. Also, the method relies on the results of forecasting the generation of solar power plants connected to the considered power grid. Solar power plants’ forecasting is carried out by a decision tree model trained using machine learning methods. To train the predictive model, data on the generation of real solar power plants are used.
{"title":"Optimal Reconfiguration of Distribution Network with Solar Power Plants","authors":"A. Bramm, S. Eroshenko","doi":"10.1109/USSEC53120.2021.9655718","DOIUrl":"https://doi.org/10.1109/USSEC53120.2021.9655718","url":null,"abstract":"The paper is concerned with the problem of determining the optimal reconfiguration of the power grid for each hour of the day. The optimization criterion is the value of the total power losses in the power grid. The considered network operates in parallel with a large power system and includes two solar power plants. Consumers in this network are represented by electricity load curve of three types. The technique for determining the optimal configuration is based on knowledge about the features of flow distribution in grids with renewable energy sources and the fundamental principles from the graph theory. Also, the method relies on the results of forecasting the generation of solar power plants connected to the considered power grid. Solar power plants’ forecasting is carried out by a decision tree model trained using machine learning methods. To train the predictive model, data on the generation of real solar power plants are used.","PeriodicalId":260032,"journal":{"name":"2021 Ural-Siberian Smart Energy Conference (USSEC)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133320450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：