Pub Date : 2022-12-04DOI: 10.1109/iSPEC54162.2022.10032978
Wangjun Zhang, Chao Deng, Xiangjing Su, Liangzhao Nie, Yi Wu
False data injection attacks (FDIA) destroy the integrity of information transmission by evading the bad data detection mechanism, and thus affects the stability of power cyber-physical systems (PCPS). Existing studies simply introduce complex neural network models for FDIA detection, ignoring spatial-temporal correlation and interpretability of neural networks. As a result, the accuracy and reliability of false detection may be negatively affected. To address the challenges above, this paper proposes an interpretable deep learning framework based on the spatial-temporal attention mechanism. Firstly, based on the gated recurrent unit (GRU), a dual attention mechanism is designed by combining spatial and temporal features of deep neural network to dynamically mine the potential correlations between the FDIA detection and the input features. Besides, the quantification of attention weights is introduced to interpret the spatial-temporal correlations between normal and attack data, which can effectively enhance the interpretability and reliability of detection results. Finally, based on the IEEE 14-bus test system and real operation data, simulations are conducted and the results show that the proposed STAGN model can detect FDIA effectively, has higher accuracy and stability than the latest detection models, and also has reasonable interpretability.
{"title":"Spatial-Temporal Attention Based Interpretable Deep Framework for FDIA Detection in Smart Grid","authors":"Wangjun Zhang, Chao Deng, Xiangjing Su, Liangzhao Nie, Yi Wu","doi":"10.1109/iSPEC54162.2022.10032978","DOIUrl":"https://doi.org/10.1109/iSPEC54162.2022.10032978","url":null,"abstract":"False data injection attacks (FDIA) destroy the integrity of information transmission by evading the bad data detection mechanism, and thus affects the stability of power cyber-physical systems (PCPS). Existing studies simply introduce complex neural network models for FDIA detection, ignoring spatial-temporal correlation and interpretability of neural networks. As a result, the accuracy and reliability of false detection may be negatively affected. To address the challenges above, this paper proposes an interpretable deep learning framework based on the spatial-temporal attention mechanism. Firstly, based on the gated recurrent unit (GRU), a dual attention mechanism is designed by combining spatial and temporal features of deep neural network to dynamically mine the potential correlations between the FDIA detection and the input features. Besides, the quantification of attention weights is introduced to interpret the spatial-temporal correlations between normal and attack data, which can effectively enhance the interpretability and reliability of detection results. Finally, based on the IEEE 14-bus test system and real operation data, simulations are conducted and the results show that the proposed STAGN model can detect FDIA effectively, has higher accuracy and stability than the latest detection models, and also has reasonable interpretability.","PeriodicalId":129707,"journal":{"name":"2022 IEEE Sustainable Power and Energy Conference (iSPEC)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130586263","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 : 2022-12-04DOI: 10.1109/iSPEC54162.2022.10032979
Keguang Shen, Wentao Huang
The continuing COVID-19 pandemic around the world has raised concerns about public health security and posed a serious threat to the international shipping industry. Considering the fact that current epidemic may exist for a long time, it is necessary to set up independent epidemic prevention function zones on ships to deal with possible outbreaks. Due to the characteristics of high precision and low fault tolerance of medical devices and related equipment in epidemic prevention functional zones, they require more strict power supply quality and reliability, and may cause the deterioration of the power quality of the system. To solve this problem, the paper introduced a novel power management strategy for the shipboard medical system by power generation equipment switching process optimization, partitioning and grading of different types of loads to solve the power supply and distribution problems of the introduced ship epidemic prevention zone, and ensure a stable and reliable power supply of high-power medical equipment on the ship.
{"title":"A Power Supply Reliability Optimization Strategy of Shipboard Integrated Power System Equipped with Medical Load and Energy Storage System","authors":"Keguang Shen, Wentao Huang","doi":"10.1109/iSPEC54162.2022.10032979","DOIUrl":"https://doi.org/10.1109/iSPEC54162.2022.10032979","url":null,"abstract":"The continuing COVID-19 pandemic around the world has raised concerns about public health security and posed a serious threat to the international shipping industry. Considering the fact that current epidemic may exist for a long time, it is necessary to set up independent epidemic prevention function zones on ships to deal with possible outbreaks. Due to the characteristics of high precision and low fault tolerance of medical devices and related equipment in epidemic prevention functional zones, they require more strict power supply quality and reliability, and may cause the deterioration of the power quality of the system. To solve this problem, the paper introduced a novel power management strategy for the shipboard medical system by power generation equipment switching process optimization, partitioning and grading of different types of loads to solve the power supply and distribution problems of the introduced ship epidemic prevention zone, and ensure a stable and reliable power supply of high-power medical equipment on the ship.","PeriodicalId":129707,"journal":{"name":"2022 IEEE Sustainable Power and Energy Conference (iSPEC)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123547472","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 : 2022-12-04DOI: 10.1109/iSPEC54162.2022.10033031
Merid Aboye
Electrification of end-use services in the industrial sector is viewed as one of the key components for lowering hydrocarbon consumption and achieving a low-carbon future in Saudi Arabia. This paper describes a screening analysis that examines the economic viability and environmental benefits of replacing existing gas turbine-based mechanical pump drives with variable speed drive electric motors. The analysis is based on projected long-term duties of a seawater pumping network and expected prevailing energy prices in the country. Equipment sizing and off-design performance calculations for proposed gas turbine mechanical drive and electric motor options are accomplished using thermal-hydraulic simulation software. Economic and environmental viability of the electrification proposal is demonstrated by comparing its net life-cycle cost with that of mechanical drive options. The results of the analysis indicate an incremental twenty-year net present value of cash flow of over USD 530 million, in favor of the electrification option. In addition, its estimated that CO2 emissions can be reduced by approximately 900,000 metric tons per year.
{"title":"Feasibility Assessment of Power Supply Options for Seawater Pumping Stations","authors":"Merid Aboye","doi":"10.1109/iSPEC54162.2022.10033031","DOIUrl":"https://doi.org/10.1109/iSPEC54162.2022.10033031","url":null,"abstract":"Electrification of end-use services in the industrial sector is viewed as one of the key components for lowering hydrocarbon consumption and achieving a low-carbon future in Saudi Arabia. This paper describes a screening analysis that examines the economic viability and environmental benefits of replacing existing gas turbine-based mechanical pump drives with variable speed drive electric motors. The analysis is based on projected long-term duties of a seawater pumping network and expected prevailing energy prices in the country. Equipment sizing and off-design performance calculations for proposed gas turbine mechanical drive and electric motor options are accomplished using thermal-hydraulic simulation software. Economic and environmental viability of the electrification proposal is demonstrated by comparing its net life-cycle cost with that of mechanical drive options. The results of the analysis indicate an incremental twenty-year net present value of cash flow of over USD 530 million, in favor of the electrification option. In addition, its estimated that CO2 emissions can be reduced by approximately 900,000 metric tons per year.","PeriodicalId":129707,"journal":{"name":"2022 IEEE Sustainable Power and Energy Conference (iSPEC)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127719192","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}
Renewable energy microgrids provide an economical and environmentally friendly solution to the difficulty of powering islands. However, due to the changing load, complex environment, intermittency of energy sources, and the immaturity of microgrid technology, island microgrids face many risks. In this study, a risk management system for island microgrids is established, the fuzzy analytic hierarchy process is used for risk assessment. Measures are proposed to mitigate risks, and their effect is quantified to make sure whether they are worthwhile. Finally, this method is applied to the Dongfushan Island Microgrid Demonstration Project. The result shows that the risk level of this microgrid project is relatively low risk. Among the many methods proposed, it is the most effective to reduce the risk of personnel accidents through measures such as publicity and education, which can make the microgrid the lowest risk level.
{"title":"Risk management for electrifying off-grid island using renewable energy microgrid","authors":"Mengting Chen, Peiqiang Song, Guipeng Chen, Fengyan Zhang, X. Qing","doi":"10.1109/iSPEC54162.2022.10033013","DOIUrl":"https://doi.org/10.1109/iSPEC54162.2022.10033013","url":null,"abstract":"Renewable energy microgrids provide an economical and environmentally friendly solution to the difficulty of powering islands. However, due to the changing load, complex environment, intermittency of energy sources, and the immaturity of microgrid technology, island microgrids face many risks. In this study, a risk management system for island microgrids is established, the fuzzy analytic hierarchy process is used for risk assessment. Measures are proposed to mitigate risks, and their effect is quantified to make sure whether they are worthwhile. Finally, this method is applied to the Dongfushan Island Microgrid Demonstration Project. The result shows that the risk level of this microgrid project is relatively low risk. Among the many methods proposed, it is the most effective to reduce the risk of personnel accidents through measures such as publicity and education, which can make the microgrid the lowest risk level.","PeriodicalId":129707,"journal":{"name":"2022 IEEE Sustainable Power and Energy Conference (iSPEC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127973921","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 : 2022-12-04DOI: 10.1109/iSPEC54162.2022.10033055
Haojun Wang, Wenqian Jiang, Chenye Wu
The integration of large-scale renewable energy poses significant challenge to the real-time supply-demand balancing in the power grid, which reshapes the landscape of electricity pricing. To handle the uncertainty in the renewable generation outputs, system operators need to start up and shut down conventional generators more frequently, whereas the widely adopted locational marginal price (LMP) scheme fails to recover these frequent start-up costs, which causes inadequate incentive issues in the markets. To this end, extended LMP (eLMP) was proposed, which employs the uplift payment to compensate for the start-up costs. As eLMP is more complicated than LMP, it is commonly believed that the eLMP prediction will be much harder than the LMP prediction. However, in this paper, we submit that this common belief is unfounded through comparative study. We compare the prediction performances for the two pricing schemes measured by various evaluation metrics, including MAE, RMSE, and MAPE. The results highlight that eLMP scheme is in fact easier to predict than the LMP scheme in terms of prediction accuracy, and the prediction models trained by LMP can be directly used to predict eLMP with remarkable performance. However, through the robustness test, we find that the robustness of eLMP prediction is not as good as that of LMP prediction, which implies the complexity of eLMP scheme.
{"title":"Is eLMP Harder to Predict than LMP?","authors":"Haojun Wang, Wenqian Jiang, Chenye Wu","doi":"10.1109/iSPEC54162.2022.10033055","DOIUrl":"https://doi.org/10.1109/iSPEC54162.2022.10033055","url":null,"abstract":"The integration of large-scale renewable energy poses significant challenge to the real-time supply-demand balancing in the power grid, which reshapes the landscape of electricity pricing. To handle the uncertainty in the renewable generation outputs, system operators need to start up and shut down conventional generators more frequently, whereas the widely adopted locational marginal price (LMP) scheme fails to recover these frequent start-up costs, which causes inadequate incentive issues in the markets. To this end, extended LMP (eLMP) was proposed, which employs the uplift payment to compensate for the start-up costs. As eLMP is more complicated than LMP, it is commonly believed that the eLMP prediction will be much harder than the LMP prediction. However, in this paper, we submit that this common belief is unfounded through comparative study. We compare the prediction performances for the two pricing schemes measured by various evaluation metrics, including MAE, RMSE, and MAPE. The results highlight that eLMP scheme is in fact easier to predict than the LMP scheme in terms of prediction accuracy, and the prediction models trained by LMP can be directly used to predict eLMP with remarkable performance. However, through the robustness test, we find that the robustness of eLMP prediction is not as good as that of LMP prediction, which implies the complexity of eLMP scheme.","PeriodicalId":129707,"journal":{"name":"2022 IEEE Sustainable Power and Energy Conference (iSPEC)","volume":"175 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129504584","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 : 2022-12-04DOI: 10.1109/iSPEC54162.2022.10033072
Dowon Kim
Wireless power transfer (WPT) systems are commonly used in electric vehicles and various mobile applications. In order to transmit power wirelessly in a weak magnetic coupling between transmitting and receiving ends, it is required to compensate for the leakage inductance by the capacitors and conFigure an electrical resonance circuit. This study analyses a series-series (SS) capacitor compensation application in various compensating topologies. This paper introduces ABCD parameters in the SS WPT system based on the middle-length transmission line analysis in power system engineering. The SS WPT system can be represented as T-shape lumped model, and the ABCD parameters can be obtained by analysing the correlation of sending and receiving voltage and current. With the found parameters, the voltage and current between the ends can be estimated accurately for the design of the SS WPT system like traditional power transmission lines. Also, this paper verifies the effectiveness of the proposed ABCD parameters in the SS WPT application through the electromagnetic field solver simulation.
{"title":"ABCD Parameters in Series-Series Compensation Wireless Power Transfer System","authors":"Dowon Kim","doi":"10.1109/iSPEC54162.2022.10033072","DOIUrl":"https://doi.org/10.1109/iSPEC54162.2022.10033072","url":null,"abstract":"Wireless power transfer (WPT) systems are commonly used in electric vehicles and various mobile applications. In order to transmit power wirelessly in a weak magnetic coupling between transmitting and receiving ends, it is required to compensate for the leakage inductance by the capacitors and conFigure an electrical resonance circuit. This study analyses a series-series (SS) capacitor compensation application in various compensating topologies. This paper introduces ABCD parameters in the SS WPT system based on the middle-length transmission line analysis in power system engineering. The SS WPT system can be represented as T-shape lumped model, and the ABCD parameters can be obtained by analysing the correlation of sending and receiving voltage and current. With the found parameters, the voltage and current between the ends can be estimated accurately for the design of the SS WPT system like traditional power transmission lines. Also, this paper verifies the effectiveness of the proposed ABCD parameters in the SS WPT application through the electromagnetic field solver simulation.","PeriodicalId":129707,"journal":{"name":"2022 IEEE Sustainable Power and Energy Conference (iSPEC)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115540410","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 : 2022-12-04DOI: 10.1109/iSPEC54162.2022.10032999
Boming Zhang, Tat Kei Chau, H. Iu, Paul McCormick
To maintain the stability of the power system, the load frequency controller design is one critical task. In this paper, an adaptive disturbance observer-based sliding mode control (ADOB-SMC) is constructed, which relaxes the requirement for having prior knowledge of the disturbance by introducing a disturbance observer. To achieve better control performance, the adaptive constant reaching law is integrated into the proposed ADOB-SMC. The proposed controller can effectively regulate the frequency deviation to zero, and produce less overshoots compared with the conventional proportional-integral (PI) controller-based methods. In addition, the proposed ADOB-SMC controller has less dependence on prior knowledge on the system disturbance than the traditional sliding mode control (SMC). Considering the real situation in Western Australia (WA), two cases are constructed to test the performance of the proposed methods. The performance of the proposed controller is verified by simulation studies using MATLAB/Simulink.
{"title":"An Adaptive Load Frequency Control Based on Sliding Mode Control and Disturbance Observer","authors":"Boming Zhang, Tat Kei Chau, H. Iu, Paul McCormick","doi":"10.1109/iSPEC54162.2022.10032999","DOIUrl":"https://doi.org/10.1109/iSPEC54162.2022.10032999","url":null,"abstract":"To maintain the stability of the power system, the load frequency controller design is one critical task. In this paper, an adaptive disturbance observer-based sliding mode control (ADOB-SMC) is constructed, which relaxes the requirement for having prior knowledge of the disturbance by introducing a disturbance observer. To achieve better control performance, the adaptive constant reaching law is integrated into the proposed ADOB-SMC. The proposed controller can effectively regulate the frequency deviation to zero, and produce less overshoots compared with the conventional proportional-integral (PI) controller-based methods. In addition, the proposed ADOB-SMC controller has less dependence on prior knowledge on the system disturbance than the traditional sliding mode control (SMC). Considering the real situation in Western Australia (WA), two cases are constructed to test the performance of the proposed methods. The performance of the proposed controller is verified by simulation studies using MATLAB/Simulink.","PeriodicalId":129707,"journal":{"name":"2022 IEEE Sustainable Power and Energy Conference (iSPEC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126711429","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 : 2022-12-04DOI: 10.1109/iSPEC54162.2022.10033064
A. Ward
The law of conservation of energy has yet to be disproven. However, an inability to disprove this law is no proof of its validity. Energy creation was modeled with a lagging current and a quasi-sinusoidal variance in capacitance. A quasi-sinusoidal variance here is a sinusoidal waveform whose mean is larger than its median. The stator’s quasi-sinusoidal variance in capacitance is formed by the rotors’ electrostatic induction within its conductive segments, which is induced by the stator’s charge. The stator, connected to a dc voltage source, an electrical load, and an oversized inductor, form an RLC circuit. In combination with the dc voltage source and oversized inductor, the stator’s quasi-sinusoidal variance in capacitance establishes a lagging-alternating current. The lagging charge’s corresponding peaks occur once while the stator’s capacitance is slowly decreasing and once while the stator’s capacitance is quickly increasing. This difference in the stator’s variance in capacitance enables energy to be created. Variations of this device were modeled within Ansys and Maplesoft. In one variation, 10.77 Watts of average electrical power, 6. 5S Watts of average mechanical power, and 1.11 Watts of average power within the dc voltage source were created. Therefore, this device was modeled as having over-unity energy conversion.
{"title":"Modeling Energy Creation with a Lagging Current and a Quasi-Sinusoidal Variance in Capacitance","authors":"A. Ward","doi":"10.1109/iSPEC54162.2022.10033064","DOIUrl":"https://doi.org/10.1109/iSPEC54162.2022.10033064","url":null,"abstract":"The law of conservation of energy has yet to be disproven. However, an inability to disprove this law is no proof of its validity. Energy creation was modeled with a lagging current and a quasi-sinusoidal variance in capacitance. A quasi-sinusoidal variance here is a sinusoidal waveform whose mean is larger than its median. The stator’s quasi-sinusoidal variance in capacitance is formed by the rotors’ electrostatic induction within its conductive segments, which is induced by the stator’s charge. The stator, connected to a dc voltage source, an electrical load, and an oversized inductor, form an RLC circuit. In combination with the dc voltage source and oversized inductor, the stator’s quasi-sinusoidal variance in capacitance establishes a lagging-alternating current. The lagging charge’s corresponding peaks occur once while the stator’s capacitance is slowly decreasing and once while the stator’s capacitance is quickly increasing. This difference in the stator’s variance in capacitance enables energy to be created. Variations of this device were modeled within Ansys and Maplesoft. In one variation, 10.77 Watts of average electrical power, 6. 5S Watts of average mechanical power, and 1.11 Watts of average power within the dc voltage source were created. Therefore, this device was modeled as having over-unity energy conversion.","PeriodicalId":129707,"journal":{"name":"2022 IEEE Sustainable Power and Energy Conference (iSPEC)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126622390","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 : 2022-12-04DOI: 10.1109/iSPEC54162.2022.10033077
Kaifeng Wang, Lin Ye, Busheng Zhang, Yifei Jin, Yongning Zhao, Wei Chen
Multi-area power balance affects the safe and stable operation of the power system. This paper presents an optimization strategy for multi-area DC dispatching control considering frequency constraints. Firstly, a multi-area joint dispatching model is constructed, which includes conventional unit constraints and power balance constraints. Secondly, in order to ensure the safety and stability of DC transmission, the minimum adjustment time and range of transmission line adjustment are set. Finally, a case study is carried out based on the load and power generation data of a two-area power system to verify the effectiveness and feasibility of the proposed strategy.
{"title":"Optimization strategy for multi-area DC dispatching control considering frequency constraints","authors":"Kaifeng Wang, Lin Ye, Busheng Zhang, Yifei Jin, Yongning Zhao, Wei Chen","doi":"10.1109/iSPEC54162.2022.10033077","DOIUrl":"https://doi.org/10.1109/iSPEC54162.2022.10033077","url":null,"abstract":"Multi-area power balance affects the safe and stable operation of the power system. This paper presents an optimization strategy for multi-area DC dispatching control considering frequency constraints. Firstly, a multi-area joint dispatching model is constructed, which includes conventional unit constraints and power balance constraints. Secondly, in order to ensure the safety and stability of DC transmission, the minimum adjustment time and range of transmission line adjustment are set. Finally, a case study is carried out based on the load and power generation data of a two-area power system to verify the effectiveness and feasibility of the proposed strategy.","PeriodicalId":129707,"journal":{"name":"2022 IEEE Sustainable Power and Energy Conference (iSPEC)","volume":" 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113949348","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 : 2022-12-04DOI: 10.1109/iSPEC54162.2022.10033001
Yu Zhao, J. Liu, Xiaoming Liu, Keyu Yuan, Kezheng Ren, Mengqin Yang
Increasing penetrations of renewable energy, flexible loads and distributed power supplies is prompting the mordern power system to be highly complex and uncertain. Besides, topology changes can greatly discount the effectiveness and real-time performance of traditional autonomous operation policies. Therefore, developing autonomous power dispatch methods is of great importance to the ensurance of modern power sytem economy and reliability. This paper proposes a novel graph-based deep reinforcement learning (DRL) framework for autonomous power dispatch considering topology changes. Based on the formulation of Markov decision process (MDP), a proximal policy optimization (PPO) algorithm with pre-training of imitation learning is adopted to obtain effective and timely power dispatch policies. Plus, to get the generalization ability to adopt to changing topologies caused by emergencies, maintenance plan and power grid construction, the GraphSAGE algorithm is embedded in the DRL agent to capture changing charcteristics of the power network. The case study is conducted on a modified IEEE 118-bus system and the results suggest good performance of the proposed framework.
{"title":"A Graph-based Deep Reinforcement Learning Framework for Autonomous Power Dispatch on Power Systems with Changing Topologies","authors":"Yu Zhao, J. Liu, Xiaoming Liu, Keyu Yuan, Kezheng Ren, Mengqin Yang","doi":"10.1109/iSPEC54162.2022.10033001","DOIUrl":"https://doi.org/10.1109/iSPEC54162.2022.10033001","url":null,"abstract":"Increasing penetrations of renewable energy, flexible loads and distributed power supplies is prompting the mordern power system to be highly complex and uncertain. Besides, topology changes can greatly discount the effectiveness and real-time performance of traditional autonomous operation policies. Therefore, developing autonomous power dispatch methods is of great importance to the ensurance of modern power sytem economy and reliability. This paper proposes a novel graph-based deep reinforcement learning (DRL) framework for autonomous power dispatch considering topology changes. Based on the formulation of Markov decision process (MDP), a proximal policy optimization (PPO) algorithm with pre-training of imitation learning is adopted to obtain effective and timely power dispatch policies. Plus, to get the generalization ability to adopt to changing topologies caused by emergencies, maintenance plan and power grid construction, the GraphSAGE algorithm is embedded in the DRL agent to capture changing charcteristics of the power network. The case study is conducted on a modified IEEE 118-bus system and the results suggest good performance of the proposed framework.","PeriodicalId":129707,"journal":{"name":"2022 IEEE Sustainable Power and Energy Conference (iSPEC)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121753534","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：