Pub Date : 2022-12-01DOI: 10.1109/CEECT55960.2022.10030122
Chen Junsheng, Liu Lijun, Xu Hanwei, Huang Weidong, Lin Yufang
From the source-load perspective, considering the safety operation constraints of grid dispatching, a dispatching model that takes into account flexible load demand response and power system flexibility is established. Based on the price-based demand response and highly flexible load model, the flexible load demand response model is built to respond to the level of wind-photovoltaic output, guide load-side users to change their power consumption behavior, regulate the demand for power system flexibility and improve the consumption rate of new energy. Based on the supply-demand balance mechanism of power system flexibility and the uncertainty of wind-photovoltaic output and load, we construct power system flexibility indexes in different time scales, combine with the comprehensive economic cost index of grid operation, consider source-load coordination, design joint optimal dispatching strategy, and generate typical scenarios based on improved deep embedding clustering algorithm to establish optimal dispatching model, so as to reduce the influence of uncertainty of wind-photovoltaic output and load demand on the optimization results. The uncertainty of wind-photovoltaic output and load demand can reduce the impact on the optimization results. Finally, the feasibility and rationality of the proposed model are verified by an example analysis of a regional power grid.
{"title":"Joint Source-Load Optimal Scheduling Considering Demand Response and Flexible Supply-Demand Balance","authors":"Chen Junsheng, Liu Lijun, Xu Hanwei, Huang Weidong, Lin Yufang","doi":"10.1109/CEECT55960.2022.10030122","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030122","url":null,"abstract":"From the source-load perspective, considering the safety operation constraints of grid dispatching, a dispatching model that takes into account flexible load demand response and power system flexibility is established. Based on the price-based demand response and highly flexible load model, the flexible load demand response model is built to respond to the level of wind-photovoltaic output, guide load-side users to change their power consumption behavior, regulate the demand for power system flexibility and improve the consumption rate of new energy. Based on the supply-demand balance mechanism of power system flexibility and the uncertainty of wind-photovoltaic output and load, we construct power system flexibility indexes in different time scales, combine with the comprehensive economic cost index of grid operation, consider source-load coordination, design joint optimal dispatching strategy, and generate typical scenarios based on improved deep embedding clustering algorithm to establish optimal dispatching model, so as to reduce the influence of uncertainty of wind-photovoltaic output and load demand on the optimization results. The uncertainty of wind-photovoltaic output and load demand can reduce the impact on the optimization results. Finally, the feasibility and rationality of the proposed model are verified by an example analysis of a regional power grid.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128567979","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}
Aiming at the problem that most optimization methods can't give consideration to the economy and environmental protection of the “source-network-load-storage” (SNLS) system, a bilayer collaborative optimization method of SNLS based on multi-agent algorithm is proposed. Firstly, a multi-agent system model of SNLS is constructed based on the distributed characteristics of multi-agent algorithm and system photovoltaic power generation cluster. Then, the system objective function and constraint conditions are set, that is, the optimization objective is to minimize the system operation cost and the amount of light discarded. Finally, based on the double-layer nested optimization structure, the objective is solved, and the improved grey wolf optimization algorithm is used to solve the single objective, so as to obtain the best optimization scheme of the system. The experimental results based on the IEEE33 node system platform show that the system operation cost and light rejection of the proposed method are about 383600 yuan and 0.895MW, respectively, and the energy use effect in the network is ideal.
{"title":"Bilayer Collaborative Optimization Method of “Source-network-load-storage” Based on Multi Agent Algorithm","authors":"Junhua Wu, Jian Chen, Jiayong Zhong, Yigang Zhao, Peng Gao","doi":"10.1109/CEECT55960.2022.10030158","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030158","url":null,"abstract":"Aiming at the problem that most optimization methods can't give consideration to the economy and environmental protection of the “source-network-load-storage” (SNLS) system, a bilayer collaborative optimization method of SNLS based on multi-agent algorithm is proposed. Firstly, a multi-agent system model of SNLS is constructed based on the distributed characteristics of multi-agent algorithm and system photovoltaic power generation cluster. Then, the system objective function and constraint conditions are set, that is, the optimization objective is to minimize the system operation cost and the amount of light discarded. Finally, based on the double-layer nested optimization structure, the objective is solved, and the improved grey wolf optimization algorithm is used to solve the single objective, so as to obtain the best optimization scheme of the system. The experimental results based on the IEEE33 node system platform show that the system operation cost and light rejection of the proposed method are about 383600 yuan and 0.895MW, respectively, and the energy use effect in the network is ideal.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128792634","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 : 2022-12-01DOI: 10.1109/CEECT55960.2022.10030669
P. Xu, Wei Zhao, Fuqiang Li
This paper proposed a method to analyze the transient synchronization stability of the grid-connected doubly-fed induction generator (DFIG) in case of power system failure. Firstly, analyze the voltage source converter (VSC) of the DFIG based on the phase-locked loop (PLL), and establish the grid-connected system model based on the PLL reference frame. Then, the swing equation of the system is deduced, and starting from the existence of equilibrium point, the stable area and the transient motion characteristics of the system, combined with the transient energy function method, the transient energy function of the DFIG that is weakly connected to the grid during the system failure is analyzed. State stability characteristics. Finally, a single-machine infinity simulation model of the grid-connected DFIG was built in MATLAB/SIMULINK. The simulation results verified the correctness of the theoretical analysis and the factors that affect the transient stability of the DFIG.
{"title":"Transient Stability Analysis Method of Grid-Connected DFIG Based on Direct Method","authors":"P. Xu, Wei Zhao, Fuqiang Li","doi":"10.1109/CEECT55960.2022.10030669","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030669","url":null,"abstract":"This paper proposed a method to analyze the transient synchronization stability of the grid-connected doubly-fed induction generator (DFIG) in case of power system failure. Firstly, analyze the voltage source converter (VSC) of the DFIG based on the phase-locked loop (PLL), and establish the grid-connected system model based on the PLL reference frame. Then, the swing equation of the system is deduced, and starting from the existence of equilibrium point, the stable area and the transient motion characteristics of the system, combined with the transient energy function method, the transient energy function of the DFIG that is weakly connected to the grid during the system failure is analyzed. State stability characteristics. Finally, a single-machine infinity simulation model of the grid-connected DFIG was built in MATLAB/SIMULINK. The simulation results verified the correctness of the theoretical analysis and the factors that affect the transient stability of the DFIG.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129346691","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 : 2022-12-01DOI: 10.1109/CEECT55960.2022.10030642
Zhifeng Qiu, Yanan Zhao, Wenbo Shi, Fengrui Su, Zhou Zhu
As the distributed energy mainly based on wind and solar energy continues to be incorporated into the power grid, its automatic control and management has become a very complicated task, and it needs to seek more intelligent control technology. In this paper, a deep reinforcement learning method SAC (Soft Actor-Critic) combined with attention mechanism is proposed to manage power grid. This method changes the line connection and bus distribution of the substation by adjusting the topology structure of the power grid, so that it can transmit power efficiently. And by assigning different feature weights, the attention mechanism enables the neural network to focus on the input that is more relevant to the current target task from a large number of grid input feature states, which enhances the robustness and computational efficiency of the model. And Experiments have proved that our algorithm can automatically manage three different size distribution networks IEEE-5, IEEE-14 and L2RPN WCCI 2020 for three days without experts' help and make sure them run properly and safely.
{"title":"Distribution Network Topology Control Using Attention Mechanism-Based Deep Reinforcement Learning","authors":"Zhifeng Qiu, Yanan Zhao, Wenbo Shi, Fengrui Su, Zhou Zhu","doi":"10.1109/CEECT55960.2022.10030642","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030642","url":null,"abstract":"As the distributed energy mainly based on wind and solar energy continues to be incorporated into the power grid, its automatic control and management has become a very complicated task, and it needs to seek more intelligent control technology. In this paper, a deep reinforcement learning method SAC (Soft Actor-Critic) combined with attention mechanism is proposed to manage power grid. This method changes the line connection and bus distribution of the substation by adjusting the topology structure of the power grid, so that it can transmit power efficiently. And by assigning different feature weights, the attention mechanism enables the neural network to focus on the input that is more relevant to the current target task from a large number of grid input feature states, which enhances the robustness and computational efficiency of the model. And Experiments have proved that our algorithm can automatically manage three different size distribution networks IEEE-5, IEEE-14 and L2RPN WCCI 2020 for three days without experts' help and make sure them run properly and safely.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"153 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127269012","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 : 2022-12-01DOI: 10.1109/CEECT55960.2022.10030204
H. Yin, D. Yin, Fei Mei, Jianyong Zheng
Aiming at low efficiency and high cost of scheduling schemes in distributed photovoltaic operation and maintenance, a distributed photovoltaic(PV) operation and maintenance scheduling based on improved particle swarm optimization-progress rate genetic algorithm (PSO-PRGA) is proposed. Firstly, establish a distributed PV scheduling model according to the cost which are selected to construct the objective function. Then, proposed an improved PSO-PRGA algorithm to solve the operation and maintenance scheduling optimization model. Finally, according to the operation and maintenance data of distributed photovoltaic power stations in Suqian City, Jiangsu Province, a distributed PV scenario is constructed for calculation example analysis, and it is verified that the scheduling model proposed in this paper conforms to the characteristics of distributed photovoltaic operation and maintenance, and the proposed algorithm can improve the distribution of photovoltaic power. It is feasible and efficient in practical applications to improve the efficiency of photovoltaic scheduling and reduce costs.
{"title":"Distributed PV Operation and Maintenance Scheduling Method Based on Improved PSO-PRGA Algorithm","authors":"H. Yin, D. Yin, Fei Mei, Jianyong Zheng","doi":"10.1109/CEECT55960.2022.10030204","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030204","url":null,"abstract":"Aiming at low efficiency and high cost of scheduling schemes in distributed photovoltaic operation and maintenance, a distributed photovoltaic(PV) operation and maintenance scheduling based on improved particle swarm optimization-progress rate genetic algorithm (PSO-PRGA) is proposed. Firstly, establish a distributed PV scheduling model according to the cost which are selected to construct the objective function. Then, proposed an improved PSO-PRGA algorithm to solve the operation and maintenance scheduling optimization model. Finally, according to the operation and maintenance data of distributed photovoltaic power stations in Suqian City, Jiangsu Province, a distributed PV scenario is constructed for calculation example analysis, and it is verified that the scheduling model proposed in this paper conforms to the characteristics of distributed photovoltaic operation and maintenance, and the proposed algorithm can improve the distribution of photovoltaic power. It is feasible and efficient in practical applications to improve the efficiency of photovoltaic scheduling and reduce costs.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127311391","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 : 2022-12-01DOI: 10.1109/CEECT55960.2022.10030401
Dong Qiu, Shaohua Han, Zhaojie Tang, Tengfei Hou
With a large scale of renewable energy connected to the distribution system, the problem of uncertainty will become more obvious due to the huge fluctuation and intermittent characteristics. To ease the effects of uncertainty, static var generator (SVG) is often used to track reactive power fluctuations in the distribution system and compensate. Based on this background, an interval power flow method based on an optimization model is presented in this paper. The tracking characteristic of SVG is involved in this method. The presented method is more efficient and accurate than the existing methods due to its linearized features and considering the tracking characteristic of SVG. Finally, a modified 33-bus distribution system is used to demonstrate the effectiveness of the proposed algorithm.
{"title":"An optimization model based interval power flow analysis method considering the tracking characteristic of static voltage generator","authors":"Dong Qiu, Shaohua Han, Zhaojie Tang, Tengfei Hou","doi":"10.1109/CEECT55960.2022.10030401","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030401","url":null,"abstract":"With a large scale of renewable energy connected to the distribution system, the problem of uncertainty will become more obvious due to the huge fluctuation and intermittent characteristics. To ease the effects of uncertainty, static var generator (SVG) is often used to track reactive power fluctuations in the distribution system and compensate. Based on this background, an interval power flow method based on an optimization model is presented in this paper. The tracking characteristic of SVG is involved in this method. The presented method is more efficient and accurate than the existing methods due to its linearized features and considering the tracking characteristic of SVG. Finally, a modified 33-bus distribution system is used to demonstrate the effectiveness of the proposed algorithm.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"115 26","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113945874","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 : 2022-12-01DOI: 10.1109/CEECT55960.2022.10030592
Huang Wei, Zhang Guowei, Lu Qiuhong
At this stage, the detection method of UAV carrying tools has become an indispensable means of maintenance for wire identification. The results of traditional detection methods are not intuitive or the false detection rate is high. For the above problems, this paper proposes a wire identification method based on lightweight Yolov4. Firstly, MobileNetv2 is used as the lightweight backbone feature network, and Sandglass Block is used to reduce the loss of feature information. Then, the Convolutional Block Attention Module (CBAM) is added to improve the accuracy of small target recognition. Finally, the target of the overhead transmission line is identified by judging whether the insulator and the overhead transmission line exist together in the image. The experimental results show that the mAP of the improved method is 96.78%, the FPS is 87.74, and the model size is only 22.74MB. The proposed method can satisfy the small equipment's identification of overhead transmission lines, and the error detection rate is low.
{"title":"Wire recognition method based on image recognition","authors":"Huang Wei, Zhang Guowei, Lu Qiuhong","doi":"10.1109/CEECT55960.2022.10030592","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030592","url":null,"abstract":"At this stage, the detection method of UAV carrying tools has become an indispensable means of maintenance for wire identification. The results of traditional detection methods are not intuitive or the false detection rate is high. For the above problems, this paper proposes a wire identification method based on lightweight Yolov4. Firstly, MobileNetv2 is used as the lightweight backbone feature network, and Sandglass Block is used to reduce the loss of feature information. Then, the Convolutional Block Attention Module (CBAM) is added to improve the accuracy of small target recognition. Finally, the target of the overhead transmission line is identified by judging whether the insulator and the overhead transmission line exist together in the image. The experimental results show that the mAP of the improved method is 96.78%, the FPS is 87.74, and the model size is only 22.74MB. The proposed method can satisfy the small equipment's identification of overhead transmission lines, and the error detection rate is low.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127845678","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 : 2022-12-01DOI: 10.1109/CEECT55960.2022.10030457
C. Yuting, Hong-hui Qiu, Shen Ran, Mao Lei, L. Junhui, He Wei
Under the background of electric power system reform, the storage management of materials is related to the efficiency of the operation of electric power Supply Company. This article shows how to enhance the details of the acceptance, storage and delivery, and how to effectively manage the materials, and put forward a modern electric power storage management system, the actual operation proved its advanced nature and effectiveness.
{"title":"The Analysis and Optimization of the Storage Management in Power Supply Company","authors":"C. Yuting, Hong-hui Qiu, Shen Ran, Mao Lei, L. Junhui, He Wei","doi":"10.1109/CEECT55960.2022.10030457","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030457","url":null,"abstract":"Under the background of electric power system reform, the storage management of materials is related to the efficiency of the operation of electric power Supply Company. This article shows how to enhance the details of the acceptance, storage and delivery, and how to effectively manage the materials, and put forward a modern electric power storage management system, the actual operation proved its advanced nature and effectiveness.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122995086","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 : 2022-12-01DOI: 10.1109/CEECT55960.2022.10030548
Meiying Wu, Guan Wang, Hongshun Liu
The rapid development of artificial intelligence provides a new method with higher accuracy for transformer fault diagnosis, but the existing fault diagnosis models are not conducive to handling unbalanced data sets. In order to improve the accuracy of transformer fault diagnosis, a diagnosis method combining SMOTE and random forest is proposed. The SMOTE algorithm is used to expand the minority fault samples of transformer oil chromatography fault data set to balance the data quantity of each fault type. Then, the random forest classifier is used to identify the faults of the data that have not been expanded and the data that have been expanded by SMOTE respectively. The diagnosis results show that the accuracy of fault diagnosis can be significantly improved by using SMOTE to expand the unbalanced transformer oil chromatography fault data set before fault diagnosis. In addition, the results of several other fault diagnosis models are added to verify the above conclusion. At the same time, it is concluded that the random forest classifier is the model with the highest diagnostic accuracy among several fault diagnosis models, so it is an ideal choice for transformer fault diagnosis.
{"title":"Research on Transformer Fault Diagnosis Based on SMOTE and Random Forest","authors":"Meiying Wu, Guan Wang, Hongshun Liu","doi":"10.1109/CEECT55960.2022.10030548","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030548","url":null,"abstract":"The rapid development of artificial intelligence provides a new method with higher accuracy for transformer fault diagnosis, but the existing fault diagnosis models are not conducive to handling unbalanced data sets. In order to improve the accuracy of transformer fault diagnosis, a diagnosis method combining SMOTE and random forest is proposed. The SMOTE algorithm is used to expand the minority fault samples of transformer oil chromatography fault data set to balance the data quantity of each fault type. Then, the random forest classifier is used to identify the faults of the data that have not been expanded and the data that have been expanded by SMOTE respectively. The diagnosis results show that the accuracy of fault diagnosis can be significantly improved by using SMOTE to expand the unbalanced transformer oil chromatography fault data set before fault diagnosis. In addition, the results of several other fault diagnosis models are added to verify the above conclusion. At the same time, it is concluded that the random forest classifier is the model with the highest diagnostic accuracy among several fault diagnosis models, so it is an ideal choice for transformer fault diagnosis.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127866690","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 electric vehicle (EV) charging facilities continue to grow in size, the proper operation of EV charging posts is of particular importance. However, certain non-human factors can lead to data anomalies in charging posts, thus hindering the normal operation of EV charging posts, as well as the daily operation and profitability of charging stations. Therefore, this paper lectures on the features of generative adversarial networks (GAN) that can retain the original data features and random forests that can detect anomalous data, and performs anomaly detection on the anomalous data detected by the EV charging station management system. Finally, the experimental results show that the GAN used in this paper can generate more anomalous data to augment the original dataset and that the model trained from the data-augmented dataset has higher data anomaly detection capability than the model trained from the dataset with less anomalous data without data augmentation.
{"title":"Data Augmentation Based Anomaly Data Detection for Charging Piles","authors":"Wen Sun, Qingming Lin, Wenhui Zhang, Xiaocun Wang, Qi Feng, Yun Zhou","doi":"10.1109/CEECT55960.2022.10030664","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030664","url":null,"abstract":"As electric vehicle (EV) charging facilities continue to grow in size, the proper operation of EV charging posts is of particular importance. However, certain non-human factors can lead to data anomalies in charging posts, thus hindering the normal operation of EV charging posts, as well as the daily operation and profitability of charging stations. Therefore, this paper lectures on the features of generative adversarial networks (GAN) that can retain the original data features and random forests that can detect anomalous data, and performs anomaly detection on the anomalous data detected by the EV charging station management system. Finally, the experimental results show that the GAN used in this paper can generate more anomalous data to augment the original dataset and that the model trained from the data-augmented dataset has higher data anomaly detection capability than the model trained from the dataset with less anomalous data without data augmentation.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"318 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121075788","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：