Pub Date : 2023-03-23DOI: 10.1109/AEEES56888.2023.10114329
Zihan Chen, Han Lin, Wenxin Chen, Jinyu Chen, Han Chen, Wanqing Chen, Simin Chen, Jinchun Chen
The deep coupling of the power system network layer and the physical layer makes the risk of the power system being subjected to cyber attack constantly rise. Effective cyber attack detection plays an important role in the safe and stable operation of power system. However, due to the limited data available, the problem of cyber attack diagnosis in power system has a weak generalization. To this end, this paper proposes a model-agnostic meta-learning (MAML)-based false data injection attack (FDIA) diagnosis method with limited samples for power systems. More specifically, a basic-learner is first trained to learn the attributes of a series of related FDIA diagnostic tasks. In this training stage, the proposed model can obtain the meta-knowledge from the learning experience of these priori tasks. This technique makes the model have fast adaptation ability to unseen tasks by utilizing only limited data. Then, a meta-learner with fast learning ability is obtained. In addition, two learnable learning rates are applied in basic and meta-learner, which makes the model to converge faster compared with the fixed learning rate. The performance of the proposed FDIA detection model is evaluated on the New England 10-machine 39-bus test system. Experimental results show that the proposed can achieve promising performance with limited data under different scenarios, which can well prove the effectiveness of the proposed model.
{"title":"A Meta-Learning Enabled Method for False Data Injection Attack Detection in Smart Grid","authors":"Zihan Chen, Han Lin, Wenxin Chen, Jinyu Chen, Han Chen, Wanqing Chen, Simin Chen, Jinchun Chen","doi":"10.1109/AEEES56888.2023.10114329","DOIUrl":"https://doi.org/10.1109/AEEES56888.2023.10114329","url":null,"abstract":"The deep coupling of the power system network layer and the physical layer makes the risk of the power system being subjected to cyber attack constantly rise. Effective cyber attack detection plays an important role in the safe and stable operation of power system. However, due to the limited data available, the problem of cyber attack diagnosis in power system has a weak generalization. To this end, this paper proposes a model-agnostic meta-learning (MAML)-based false data injection attack (FDIA) diagnosis method with limited samples for power systems. More specifically, a basic-learner is first trained to learn the attributes of a series of related FDIA diagnostic tasks. In this training stage, the proposed model can obtain the meta-knowledge from the learning experience of these priori tasks. This technique makes the model have fast adaptation ability to unseen tasks by utilizing only limited data. Then, a meta-learner with fast learning ability is obtained. In addition, two learnable learning rates are applied in basic and meta-learner, which makes the model to converge faster compared with the fixed learning rate. The performance of the proposed FDIA detection model is evaluated on the New England 10-machine 39-bus test system. Experimental results show that the proposed can achieve promising performance with limited data under different scenarios, which can well prove the effectiveness of the proposed model.","PeriodicalId":272114,"journal":{"name":"2023 5th Asia Energy and Electrical Engineering Symposium (AEEES)","volume":"266 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115791678","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 : 2023-03-23DOI: 10.1109/AEEES56888.2023.10114074
Chunlong Li, Hui Huang, Dengfeng Ju, Junjie Xiong, Shi Zuo, Fuchao Li, Weiqiang Liu
In multiple-relay wireless power transfer system, the system is usually in a state of detuning caused by the variation of resonance parameter with various factors. In order to solve this phenomenon, a dynamic tuning control method based on variable inductor is proposed in this paper. The variable inductance is connected in series at the transmitting coil end to adjust the system impedance so that achieves the purpose of reducing the loss and improving the output voltage gain of the system. Through simulation experiments, the effectiveness of the proposed variable inductor structure to improve the performance of the multiple-relay coil wireless power transmission system is verified.
{"title":"Variable-Inductor Based Tuning Method for Multiple-Relay Wireless Power Transfer System in Composite Insulator","authors":"Chunlong Li, Hui Huang, Dengfeng Ju, Junjie Xiong, Shi Zuo, Fuchao Li, Weiqiang Liu","doi":"10.1109/AEEES56888.2023.10114074","DOIUrl":"https://doi.org/10.1109/AEEES56888.2023.10114074","url":null,"abstract":"In multiple-relay wireless power transfer system, the system is usually in a state of detuning caused by the variation of resonance parameter with various factors. In order to solve this phenomenon, a dynamic tuning control method based on variable inductor is proposed in this paper. The variable inductance is connected in series at the transmitting coil end to adjust the system impedance so that achieves the purpose of reducing the loss and improving the output voltage gain of the system. Through simulation experiments, the effectiveness of the proposed variable inductor structure to improve the performance of the multiple-relay coil wireless power transmission system is verified.","PeriodicalId":272114,"journal":{"name":"2023 5th Asia Energy and Electrical Engineering Symposium (AEEES)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124138369","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 : 2023-03-23DOI: 10.1109/AEEES56888.2023.10114321
An Xing, Yang Shunfu, Sun Bo, Zhang Xiaohua, Sun Meng, Guangxin Zhang, Cheng Li
Substation is a place for voltage and current conversion, electric energy receiving and distribution in the power system. Compared with other power facilities, it has the characteristics of a small maintenance work range, short maintenance work cycle, and high voltage of live equipment around the maintenance site, to meet the requirements of substation maintenance operation safety management and portable mobile auxiliary equipment system is not mature. At the same time, the daily maintenance, expansion, transformation and other tasks of substations often have problems such as tight schedules, heavy tasks, and many cross operations. Therefore, it is very necessary to monitor the personnel and equipment on the site of substation maintenance and operation. In this paper, a dynamic multi-objective intelligent detection and tracking model was build under complex background is established to comprehensively analyze the potential transgression behaviors in the substation safety area, and realize the over-limit early warning of personnel and equipment in the substation maintenance and operation site.
{"title":"An Early Warning Model of Substation Over-Limit Based on Dynamic Multi-objective Intelligent Detection and Tracking Technology","authors":"An Xing, Yang Shunfu, Sun Bo, Zhang Xiaohua, Sun Meng, Guangxin Zhang, Cheng Li","doi":"10.1109/AEEES56888.2023.10114321","DOIUrl":"https://doi.org/10.1109/AEEES56888.2023.10114321","url":null,"abstract":"Substation is a place for voltage and current conversion, electric energy receiving and distribution in the power system. Compared with other power facilities, it has the characteristics of a small maintenance work range, short maintenance work cycle, and high voltage of live equipment around the maintenance site, to meet the requirements of substation maintenance operation safety management and portable mobile auxiliary equipment system is not mature. At the same time, the daily maintenance, expansion, transformation and other tasks of substations often have problems such as tight schedules, heavy tasks, and many cross operations. Therefore, it is very necessary to monitor the personnel and equipment on the site of substation maintenance and operation. In this paper, a dynamic multi-objective intelligent detection and tracking model was build under complex background is established to comprehensively analyze the potential transgression behaviors in the substation safety area, and realize the over-limit early warning of personnel and equipment in the substation maintenance and operation site.","PeriodicalId":272114,"journal":{"name":"2023 5th Asia Energy and Electrical Engineering Symposium (AEEES)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114354705","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 : 2023-03-23DOI: 10.1109/AEEES56888.2023.10114307
W. Liu, Dongsheng Cai, Joseph Nkou Nkou, Wei Liu, Qing-Wei Huang
The emission of a large amount of carbon dioxide has led to the greenhouse effect. With further research into the hazards of the greenhouse effect, the world’s major economies have started implementing energy-saving and emission-reduction plans. Predicting carbon emissions is important for the formulation of effective energy-saving and emission-reduction policies. This paper mainly introduces methods for predicting carbon emissions by using BP neural networks, recurrent neural networks, and a combination of traditional forecasting models with neural networks. Firstly, the characteristics of different neural networks are compared for carbon emission prediction. Secondly, the LSTM network is used for carbon emission prediction, and the evaluation results show the effect of the LSTM network. Finally, conclusion is drawn that BP and recurrent neural network are not ideal for long sequences. Joseph Junior NKOU NKOU
{"title":"A Survey of Carbon Emission Forecasting Methods Based on Neural Networks","authors":"W. Liu, Dongsheng Cai, Joseph Nkou Nkou, Wei Liu, Qing-Wei Huang","doi":"10.1109/AEEES56888.2023.10114307","DOIUrl":"https://doi.org/10.1109/AEEES56888.2023.10114307","url":null,"abstract":"The emission of a large amount of carbon dioxide has led to the greenhouse effect. With further research into the hazards of the greenhouse effect, the world’s major economies have started implementing energy-saving and emission-reduction plans. Predicting carbon emissions is important for the formulation of effective energy-saving and emission-reduction policies. This paper mainly introduces methods for predicting carbon emissions by using BP neural networks, recurrent neural networks, and a combination of traditional forecasting models with neural networks. Firstly, the characteristics of different neural networks are compared for carbon emission prediction. Secondly, the LSTM network is used for carbon emission prediction, and the evaluation results show the effect of the LSTM network. Finally, conclusion is drawn that BP and recurrent neural network are not ideal for long sequences. Joseph Junior NKOU NKOU","PeriodicalId":272114,"journal":{"name":"2023 5th Asia Energy and Electrical Engineering Symposium (AEEES)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123626495","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 : 2023-03-23DOI: 10.1109/AEEES56888.2023.10114356
Xun Li, Yantao Sun, Mengge Shi, Youwei Jia
With the rapid growth of the number of electric vehicles (EVs), how to manage the charging of various types of EVs in an orderly manner plays a crucial role in the stable operation of the power system. Therefore, this paper proposes a multi-stage charging planning strategy for charging stations (CSs) based on the various types of EV user’s charging behavior. First, formulate core user information labels for EV users of typical CSs, build EV users’ behavior data analysis models, and revise labels according to EV users’ responses. Secondly, to meet the day-ahead planned charging load curve as the goal, send the day-ahead invitation information to the core EV users. In addition, the charging load is adjusted in the intra-day recommendation stage to reduce the deviation from the day-ahead power purchase plan. Through a series of simulation experiments, the feasibility of the proposed framework of day-ahead invitation and intra-day recommendation of CSs is verified, and the operating costs of CSs can be effectively reduced.
{"title":"Multi-stage Charging Recommendation of Charging Station Considering User's Charging Behavior","authors":"Xun Li, Yantao Sun, Mengge Shi, Youwei Jia","doi":"10.1109/AEEES56888.2023.10114356","DOIUrl":"https://doi.org/10.1109/AEEES56888.2023.10114356","url":null,"abstract":"With the rapid growth of the number of electric vehicles (EVs), how to manage the charging of various types of EVs in an orderly manner plays a crucial role in the stable operation of the power system. Therefore, this paper proposes a multi-stage charging planning strategy for charging stations (CSs) based on the various types of EV user’s charging behavior. First, formulate core user information labels for EV users of typical CSs, build EV users’ behavior data analysis models, and revise labels according to EV users’ responses. Secondly, to meet the day-ahead planned charging load curve as the goal, send the day-ahead invitation information to the core EV users. In addition, the charging load is adjusted in the intra-day recommendation stage to reduce the deviation from the day-ahead power purchase plan. Through a series of simulation experiments, the feasibility of the proposed framework of day-ahead invitation and intra-day recommendation of CSs is verified, and the operating costs of CSs can be effectively reduced.","PeriodicalId":272114,"journal":{"name":"2023 5th Asia Energy and Electrical Engineering Symposium (AEEES)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122251837","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 : 2023-03-23DOI: 10.1109/AEEES56888.2023.10114098
Shiyu Sun, Mingming Shi, Yao Qu, Bin Li, Juntao Fei, Xiong Yang
A voltage coordination control strategy based on adjustable resources in power distribution grid is presented for improving the precision of voltage deviation control in power distribution grid. Firstly, the mechanism of voltage change in distribution grid is analyzed, and the relation between reactive power and PCC voltage change is quantified. Then, the characteristics of photovoltaic(PV) output and user load are analyzed, and the line voltage deviation curve is obtained, which can be used to determine the installation location and capacity of the var compensation equipment. On this basis, the PV output is predicted according to different time scales, and the reactive power of the adjustable resources in the station is allocated to ensure the voltage deviation requirements of the bus and nodal points in the station area with the objective of voltage deviation and user economy. An example shows that the strategy used in this paper has higher precision than traditional voltage regulation. By introducing traditional reactive power compensation devices into the station and invoking the PV reactive power balance, this strategy reduces the installation amount of the station reactive power compensation devices, and improves the precision of voltage deviation correction according to the relation between reactive power and PCC voltage variation.
{"title":"Coordination Control Strategy of Distribution Grid Voltage Based on Adjustable Resources in Substation Area","authors":"Shiyu Sun, Mingming Shi, Yao Qu, Bin Li, Juntao Fei, Xiong Yang","doi":"10.1109/AEEES56888.2023.10114098","DOIUrl":"https://doi.org/10.1109/AEEES56888.2023.10114098","url":null,"abstract":"A voltage coordination control strategy based on adjustable resources in power distribution grid is presented for improving the precision of voltage deviation control in power distribution grid. Firstly, the mechanism of voltage change in distribution grid is analyzed, and the relation between reactive power and PCC voltage change is quantified. Then, the characteristics of photovoltaic(PV) output and user load are analyzed, and the line voltage deviation curve is obtained, which can be used to determine the installation location and capacity of the var compensation equipment. On this basis, the PV output is predicted according to different time scales, and the reactive power of the adjustable resources in the station is allocated to ensure the voltage deviation requirements of the bus and nodal points in the station area with the objective of voltage deviation and user economy. An example shows that the strategy used in this paper has higher precision than traditional voltage regulation. By introducing traditional reactive power compensation devices into the station and invoking the PV reactive power balance, this strategy reduces the installation amount of the station reactive power compensation devices, and improves the precision of voltage deviation correction according to the relation between reactive power and PCC voltage variation.","PeriodicalId":272114,"journal":{"name":"2023 5th Asia Energy and Electrical Engineering Symposium (AEEES)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124044333","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 : 2023-03-23DOI: 10.1109/AEEES56888.2023.10114322
Dajun Si, Yuanyuan Zhao, Lingfang Li, Yixuan Chen, Peng Sun
The annual power generation scenario sequence of new energy is the basis of system operation simulation. A new energy probabilistic annual output scenario generation method based on electricity characteristic matching is proposed in this paper. Firstly, the power balance characteristics of historical new energy scenarios are described based on the characteristic index, and then the probabilistic annual generation utilization hour scenario is constructed based on k-means clustering algorithm. Finally, the multi-time-scale electricity distribution curve is matched based on the feature index extraction, and the probabilistic new energy annual output scenarios under different power generation levels are generated. The example is tested based on the historical new energy data of a provincial power grid in China, and the generated new energy sequence scenario is used to calculate the power balance capacity of the system. the results verify the effectiveness and practicability of the proposed method.
{"title":"Generation Method of Probabilistic Annual Output Scenario of New Energy Based on Electricity Characteristic Matching","authors":"Dajun Si, Yuanyuan Zhao, Lingfang Li, Yixuan Chen, Peng Sun","doi":"10.1109/AEEES56888.2023.10114322","DOIUrl":"https://doi.org/10.1109/AEEES56888.2023.10114322","url":null,"abstract":"The annual power generation scenario sequence of new energy is the basis of system operation simulation. A new energy probabilistic annual output scenario generation method based on electricity characteristic matching is proposed in this paper. Firstly, the power balance characteristics of historical new energy scenarios are described based on the characteristic index, and then the probabilistic annual generation utilization hour scenario is constructed based on k-means clustering algorithm. Finally, the multi-time-scale electricity distribution curve is matched based on the feature index extraction, and the probabilistic new energy annual output scenarios under different power generation levels are generated. The example is tested based on the historical new energy data of a provincial power grid in China, and the generated new energy sequence scenario is used to calculate the power balance capacity of the system. the results verify the effectiveness and practicability of the proposed method.","PeriodicalId":272114,"journal":{"name":"2023 5th Asia Energy and Electrical Engineering Symposium (AEEES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128311238","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 : 2023-03-23DOI: 10.1109/AEEES56888.2023.10114309
Chengxi Li, Jinfeng Huang, Renqiong Wei, Yangsen Zhang, Bo Li, Lixun He
Driven by the goal of carbon peaking and carbon neutrality, renewable energy access such as wind power and photovoltaic is putting higher demands on the peaking capacity of the existing power system. In this paper, a joint system optimal scheduling model considering peak regulation initiative and demand response is constructed. First, on the basis of analyzing the compensation and apportionment model of thermal power unit peaking, considering thermal power unit peaking initiative constraint, stimulating thermal power units to participate in peaking through peaking profit, and providing space for wind power and solar power to be connected to the grid. Secondly, price-based demand response is used on the load side to guide users to actively participate in load adjustment, reduce the load peak-to-valley difference, and optimize the load curve. Then, with the optimization objectives of minimizing system operation cost and minimizing wind and solar abandonment, a day-ahead optimal scheduling model for the wind-fire storage system is constructed considering the peak regulation initiative of thermal power and load-side demand response. Finally, the improved IEEE30 node system is used as an example for multi-scenario analysis, and the results show that the proposed model can effectively promote the capacity of renewable energy consumption as well as improve the economy of the system, which verifies the effectiveness of the model.
{"title":"Optimal Scheduling of Multi-Energy Complementary Systems Considering Peaking Initiative and Demand Response","authors":"Chengxi Li, Jinfeng Huang, Renqiong Wei, Yangsen Zhang, Bo Li, Lixun He","doi":"10.1109/AEEES56888.2023.10114309","DOIUrl":"https://doi.org/10.1109/AEEES56888.2023.10114309","url":null,"abstract":"Driven by the goal of carbon peaking and carbon neutrality, renewable energy access such as wind power and photovoltaic is putting higher demands on the peaking capacity of the existing power system. In this paper, a joint system optimal scheduling model considering peak regulation initiative and demand response is constructed. First, on the basis of analyzing the compensation and apportionment model of thermal power unit peaking, considering thermal power unit peaking initiative constraint, stimulating thermal power units to participate in peaking through peaking profit, and providing space for wind power and solar power to be connected to the grid. Secondly, price-based demand response is used on the load side to guide users to actively participate in load adjustment, reduce the load peak-to-valley difference, and optimize the load curve. Then, with the optimization objectives of minimizing system operation cost and minimizing wind and solar abandonment, a day-ahead optimal scheduling model for the wind-fire storage system is constructed considering the peak regulation initiative of thermal power and load-side demand response. Finally, the improved IEEE30 node system is used as an example for multi-scenario analysis, and the results show that the proposed model can effectively promote the capacity of renewable energy consumption as well as improve the economy of the system, which verifies the effectiveness of the model.","PeriodicalId":272114,"journal":{"name":"2023 5th Asia Energy and Electrical Engineering Symposium (AEEES)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128153293","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}
As the energy revolution proceeds, integrated energy systems (IESs) are becoming increasingly indispensable. However, the economic dispatch problem of IESs is generally formulated as a complex mixed-integer nonlinear programming problem (MINLP) with various nonlinear constraints, which is difficult to solve. In this paper, we propose a deep reinforcement learning (DRL) based acceleration approach to deal with these nonlinear constraints. Thus, the original MINLP could be transformed into a mixed-integer linear programming problem (MILP) which can be tractably handled by existing optimization techniques. Numerical results have verified the effectiveness of the proposed strategy.
{"title":"Deep Reinforcement Learning Based Acceleration Approach for Day-Ahead Optimal Dispatch of Integrated Energy Systems","authors":"Yudong Lu, Miao Yang, Wenhao Jia, Xinran He, Yunhui Fang, Tao Ding","doi":"10.1109/AEEES56888.2023.10114294","DOIUrl":"https://doi.org/10.1109/AEEES56888.2023.10114294","url":null,"abstract":"As the energy revolution proceeds, integrated energy systems (IESs) are becoming increasingly indispensable. However, the economic dispatch problem of IESs is generally formulated as a complex mixed-integer nonlinear programming problem (MINLP) with various nonlinear constraints, which is difficult to solve. In this paper, we propose a deep reinforcement learning (DRL) based acceleration approach to deal with these nonlinear constraints. Thus, the original MINLP could be transformed into a mixed-integer linear programming problem (MILP) which can be tractably handled by existing optimization techniques. Numerical results have verified the effectiveness of the proposed strategy.","PeriodicalId":272114,"journal":{"name":"2023 5th Asia Energy and Electrical Engineering Symposium (AEEES)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128666322","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 : 2023-03-23DOI: 10.1109/AEEES56888.2023.10114292
Xin Fang, Shaohua Han, Juan Li, Jiaming Wang, M. Shi, Yunlong Jiang, Chenyu Zhang, Jian Sun
Aiming at the problem of low photovoltaic prediction accuracy, a short-term photovoltaic power prediction method based on fuzzy C-Means(FCM)- extreme gradient boosting (XGBoost)- gate recurrent unit (GRU) based on weather classification is proposed. First select the key meteorological factors as the clustering features, then use the FCM clustering method for cluster analysis, divide the historical data into sunny, cloudy, rainy and extreme weather, and then construct XGBoost-GRU combined forecasts for the four weather types The model predicts photovoltaic output power. Finally, the model proposed in this paper is compared with the prediction results of traditional XGBoost and GRU models. The results show that the proposed FCM-XGBoost-GRU short-term photovoltaic power prediction method can significantly reduce the error of photovoltaic prediction and improve the accuracy of short-term photovoltaic prediction. It is effective and scientific in practical application scenarios.
{"title":"A FCM-XGBoost-GRU Model for Short-Term Photovoltaic Power Forecasting Based on Weather Classification","authors":"Xin Fang, Shaohua Han, Juan Li, Jiaming Wang, M. Shi, Yunlong Jiang, Chenyu Zhang, Jian Sun","doi":"10.1109/AEEES56888.2023.10114292","DOIUrl":"https://doi.org/10.1109/AEEES56888.2023.10114292","url":null,"abstract":"Aiming at the problem of low photovoltaic prediction accuracy, a short-term photovoltaic power prediction method based on fuzzy C-Means(FCM)- extreme gradient boosting (XGBoost)- gate recurrent unit (GRU) based on weather classification is proposed. First select the key meteorological factors as the clustering features, then use the FCM clustering method for cluster analysis, divide the historical data into sunny, cloudy, rainy and extreme weather, and then construct XGBoost-GRU combined forecasts for the four weather types The model predicts photovoltaic output power. Finally, the model proposed in this paper is compared with the prediction results of traditional XGBoost and GRU models. The results show that the proposed FCM-XGBoost-GRU short-term photovoltaic power prediction method can significantly reduce the error of photovoltaic prediction and improve the accuracy of short-term photovoltaic prediction. It is effective and scientific in practical application scenarios.","PeriodicalId":272114,"journal":{"name":"2023 5th Asia Energy and Electrical Engineering Symposium (AEEES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130019474","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：