Pub Date : 2022-12-09DOI: 10.1109/SPIES55999.2022.10082282
Zesen Wang, Qi Li, Kai Bai, Jinzhi Guo, Zhe Wang, Yinglin Liu
China's renewable energy development bases are mainly concentrated in the "Three North" areas. The phenomenon of renewable energy power abandonment is serious. As a flexible resource, energy storage can effectively shift electricity and improve the utilization of renewable energy. Firstly, the output model of electric energy storage equipment is established. Secondly, a time series production simulation optimization model considering the output characteristics of electric energy storage equipment is constructed. Finally, taking an actual large-scale renewable energy and thermal power transmission system in the north through UHV AC / DC lines as an example, the system operation, renewable energy consumption, economy and other issues after energy storage access are quantitatively analyzed. The results show that the reasonable allocation of energy storage is conducive to improving the consumption capacity of renewable energy, reducing the utilization hours of thermal power, and improving the economy of system operation. It is of great significance to the development of renewable energy power system and energy storage equipment.
{"title":"Renewable Energy Consumption and Economic Analysis of Renewable Energy and Thermal Power Combined Transmission System Considering Electric Energy Storage Configuration","authors":"Zesen Wang, Qi Li, Kai Bai, Jinzhi Guo, Zhe Wang, Yinglin Liu","doi":"10.1109/SPIES55999.2022.10082282","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082282","url":null,"abstract":"China's renewable energy development bases are mainly concentrated in the \"Three North\" areas. The phenomenon of renewable energy power abandonment is serious. As a flexible resource, energy storage can effectively shift electricity and improve the utilization of renewable energy. Firstly, the output model of electric energy storage equipment is established. Secondly, a time series production simulation optimization model considering the output characteristics of electric energy storage equipment is constructed. Finally, taking an actual large-scale renewable energy and thermal power transmission system in the north through UHV AC / DC lines as an example, the system operation, renewable energy consumption, economy and other issues after energy storage access are quantitatively analyzed. The results show that the reasonable allocation of energy storage is conducive to improving the consumption capacity of renewable energy, reducing the utilization hours of thermal power, and improving the economy of system operation. It is of great significance to the development of renewable energy power system and energy storage equipment.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132840442","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 : 2022-12-09DOI: 10.1109/SPIES55999.2022.10082249
Bozhen Jiang, Yi Liu, H. Geng, Huarong Zeng, Jiangqiao Ding
Short-term Load Forecasting (STLF) is important for the operational security and economics of power system. However, the existing Short-term Load Forecasting Models (SLFMs) generally consider the temporal dependency as static. Meanwhile, the load characteristics of periodic soft alignment and planed are ignored. Those neglect limits the STLF accuracy. In this paper, a Transformer based Short-term Load Forecasting Model (TSLFM) considering dynamic temporal dependency, periodic soft alignment and future information was proposed. Based on the encoder-decoder structure, TSLFM can be easily modified to satisfy different forecast ranges. Besides, the attention mechanism is employed in Transformer, TSLFM can capture the dynamic temporal dependency and realize periodic soft alignment. Additionally, TSLFM expands the attention range to combine historical and future information to infer the planed load. The results from two empirical studies in Switzerland and China suggest that: 1) TSLFM has good forecast performance (the maximum improvement of MAPE is 15.78% and 14.07%, and the minimum improvement is 8.49%, 8.99%, respectively) and can satisfy the high requirements for STLF, and 2) the attention maps further verify that TSLFM can consider dynamic temporal dependency, periodic soft alignment and future information.
{"title":"A Transformer Based Method with Wide Attention Range for Enhanced Short-term Load Forecasting","authors":"Bozhen Jiang, Yi Liu, H. Geng, Huarong Zeng, Jiangqiao Ding","doi":"10.1109/SPIES55999.2022.10082249","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082249","url":null,"abstract":"Short-term Load Forecasting (STLF) is important for the operational security and economics of power system. However, the existing Short-term Load Forecasting Models (SLFMs) generally consider the temporal dependency as static. Meanwhile, the load characteristics of periodic soft alignment and planed are ignored. Those neglect limits the STLF accuracy. In this paper, a Transformer based Short-term Load Forecasting Model (TSLFM) considering dynamic temporal dependency, periodic soft alignment and future information was proposed. Based on the encoder-decoder structure, TSLFM can be easily modified to satisfy different forecast ranges. Besides, the attention mechanism is employed in Transformer, TSLFM can capture the dynamic temporal dependency and realize periodic soft alignment. Additionally, TSLFM expands the attention range to combine historical and future information to infer the planed load. The results from two empirical studies in Switzerland and China suggest that: 1) TSLFM has good forecast performance (the maximum improvement of MAPE is 15.78% and 14.07%, and the minimum improvement is 8.49%, 8.99%, respectively) and can satisfy the high requirements for STLF, and 2) the attention maps further verify that TSLFM can consider dynamic temporal dependency, periodic soft alignment and future information.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133758886","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 : 2022-12-09DOI: 10.1109/SPIES55999.2022.10082572
Yuanzhe Ren, Hua Lin, Shaojie Li, Xingwei Wang
In LCL-type grid-connected inverter system, the resonance frequency will shift down and cross 1/6 of the sampling frequency due to the variation of grid impedance in weak grid, which will lead to instability. To enhance the robustness, an improved stability region based LCL filter design which adds a restriction on the lowest resonance frequency can be introduced. In this paper the influence of this restriction on the filter parameters have been studied and the results shows that the influence is greater under higher switching frequency. However, it is proved that the restriction will only lead to a limited total inductance increment. Therefore, the robustness enhanced filter design is proved to be of great practical value. At last, the analytical results are verified through experiments and simulations.
{"title":"Analysis of Robustness Enhanced LCL Filter Design Based on Stability Region","authors":"Yuanzhe Ren, Hua Lin, Shaojie Li, Xingwei Wang","doi":"10.1109/SPIES55999.2022.10082572","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082572","url":null,"abstract":"In LCL-type grid-connected inverter system, the resonance frequency will shift down and cross 1/6 of the sampling frequency due to the variation of grid impedance in weak grid, which will lead to instability. To enhance the robustness, an improved stability region based LCL filter design which adds a restriction on the lowest resonance frequency can be introduced. In this paper the influence of this restriction on the filter parameters have been studied and the results shows that the influence is greater under higher switching frequency. However, it is proved that the restriction will only lead to a limited total inductance increment. Therefore, the robustness enhanced filter design is proved to be of great practical value. At last, the analytical results are verified through experiments and simulations.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132234215","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 : 2022-12-09DOI: 10.1109/SPIES55999.2022.10082185
Ruijin Liang, M. Dong, Li Wang, Chenyao Xu, Wenrui Yan
This paper proposes a general learning framework to derive topology of power electronics converters. To increase flexibility, a circuit is represented by a graph. A Graph Neural Network extract features of the circuit graph, which is further used in the RL framework. The topology derivation process is regarded as a Markov Decision Process. In each step, the RL agent selects and connects a new block to the initial block until a complete topology is made. To ensure that the derived circuits are feasible, basic circuit constraints are taken into consideration in the reward function. By using this framework, many new six-port, eight-port and ten-port converters are derived. Simulation results show that the derived circuits satisfy given constraints well.
{"title":"Learning to Topology Derivation of Power Electronics Converters with Graph Neural Network","authors":"Ruijin Liang, M. Dong, Li Wang, Chenyao Xu, Wenrui Yan","doi":"10.1109/SPIES55999.2022.10082185","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082185","url":null,"abstract":"This paper proposes a general learning framework to derive topology of power electronics converters. To increase flexibility, a circuit is represented by a graph. A Graph Neural Network extract features of the circuit graph, which is further used in the RL framework. The topology derivation process is regarded as a Markov Decision Process. In each step, the RL agent selects and connects a new block to the initial block until a complete topology is made. To ensure that the derived circuits are feasible, basic circuit constraints are taken into consideration in the reward function. By using this framework, many new six-port, eight-port and ten-port converters are derived. Simulation results show that the derived circuits satisfy given constraints well.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134378605","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 : 2022-12-09DOI: 10.1109/SPIES55999.2022.10082593
Nan Wang, Hao Bai, Ruiqing Ma, Gang Huang
Real-time simulation technology plays an important role in the development cycle of a permanent magnet synchronous motor (PMSM) control system. In this paper, an FPGA-based real-time simulation method is proposed for a five-phase permanent magnet synchronous motor (FPMSM). The mathematical model and its FPGA implementation are presented in detail. Moreover, to verify the accuracy of the model, the FPGA-based simulation results are compared with that of the FPMSM model in the Simulink Simscape Power System (SPS) library, and very good consistency is obtained. Finally, the dual-loop controller is implemented on FPGA and the real-time experiments of FPMSM control under various conditions are conducted to validate the effectiveness of the proposed FPGA real-time simulation method.
实时仿真技术在永磁同步电机控制系统的开发周期中起着重要的作用。本文提出了一种基于fpga的五相永磁同步电动机实时仿真方法。详细介绍了该系统的数学模型及其FPGA实现。此外，为了验证模型的准确性，将基于fpga的仿真结果与Simulink Simscape Power System (SPS)库中的FPMSM模型进行了比较，得到了很好的一致性。最后，在FPGA上实现了双环控制器，并在各种条件下对FPMSM进行了实时控制实验，验证了所提出的FPGA实时仿真方法的有效性。
{"title":"FPGA-based Real-Time Simulation of Five-Phase PMSM for the HIL Applications","authors":"Nan Wang, Hao Bai, Ruiqing Ma, Gang Huang","doi":"10.1109/SPIES55999.2022.10082593","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082593","url":null,"abstract":"Real-time simulation technology plays an important role in the development cycle of a permanent magnet synchronous motor (PMSM) control system. In this paper, an FPGA-based real-time simulation method is proposed for a five-phase permanent magnet synchronous motor (FPMSM). The mathematical model and its FPGA implementation are presented in detail. Moreover, to verify the accuracy of the model, the FPGA-based simulation results are compared with that of the FPMSM model in the Simulink Simscape Power System (SPS) library, and very good consistency is obtained. Finally, the dual-loop controller is implemented on FPGA and the real-time experiments of FPMSM control under various conditions are conducted to validate the effectiveness of the proposed FPGA real-time simulation method.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133050438","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}
The virtual impedance in droop control for adjusting the reactive power distribution between parallel distributed generators is used to regulate the microgrid power flow in this paper. Both considering reactive sharing and microgrid stability, the value range of virtual impedance is analyzed. Since the operating characteristic of the distributed generators with droop control are different from the traditional generators, the traditional power flow calculation is not suitable for this island microgrid. Then the microgrid power model with distributed generator adopted droop control is established to calculate the power flow. In order to optimize the power flow, the objective function with minimum network loss is established, and the Particle Swarm Optimization is used for the optimal virtual impedance.
{"title":"Power Flow Optimization for Island Microgrid Minimal Loss Based on Virtual Impedance","authors":"Xiaobin Zhang, Yifan Wen, Chenxi Huang, Yue Li, Xiao Sige, Chengkai Li","doi":"10.1109/SPIES55999.2022.10082442","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082442","url":null,"abstract":"The virtual impedance in droop control for adjusting the reactive power distribution between parallel distributed generators is used to regulate the microgrid power flow in this paper. Both considering reactive sharing and microgrid stability, the value range of virtual impedance is analyzed. Since the operating characteristic of the distributed generators with droop control are different from the traditional generators, the traditional power flow calculation is not suitable for this island microgrid. Then the microgrid power model with distributed generator adopted droop control is established to calculate the power flow. In order to optimize the power flow, the objective function with minimum network loss is established, and the Particle Swarm Optimization is used for the optimal virtual impedance.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125666271","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 : 2022-12-09DOI: 10.1109/SPIES55999.2022.10082694
Hao Jiao, Jinming Chen, Xindong Zhao, Yajuan Guo, Yezhou Yang
With the access of distributed new energy sources and loads, the coupling relationship between the transmission and the distribution network is greatly enhanced. In order to adapt to the increasing coupling relationship between transmission and distribution, this paper proposes a generalized global optimization model for transmission and distribution. Considering the carbon reduction requirements of the power industry in the context of carbon peak and carbon neutral, the coordinated transmission and distribution optimal power flow (TDOPF) model with carbon emission constraints is proposed. Based on the different characteristics of the transmission and distribution network, the heterogeneous decomposition algorithm is used to solve the optimization model. The transmission and distribution network is alternately optimized. The auxiliary function is constructed by parameters such as boundary node voltage and injection power to ensure that the optimal conditions of the global network are satisfied. The numerical example test shows the proposed algorithm has great accuracy and convergence.
{"title":"Coordinated Transmission and Distribution Optimal Power Flow with Carbon Constraints","authors":"Hao Jiao, Jinming Chen, Xindong Zhao, Yajuan Guo, Yezhou Yang","doi":"10.1109/SPIES55999.2022.10082694","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082694","url":null,"abstract":"With the access of distributed new energy sources and loads, the coupling relationship between the transmission and the distribution network is greatly enhanced. In order to adapt to the increasing coupling relationship between transmission and distribution, this paper proposes a generalized global optimization model for transmission and distribution. Considering the carbon reduction requirements of the power industry in the context of carbon peak and carbon neutral, the coordinated transmission and distribution optimal power flow (TDOPF) model with carbon emission constraints is proposed. Based on the different characteristics of the transmission and distribution network, the heterogeneous decomposition algorithm is used to solve the optimization model. The transmission and distribution network is alternately optimized. The auxiliary function is constructed by parameters such as boundary node voltage and injection power to ensure that the optimal conditions of the global network are satisfied. The numerical example test shows the proposed algorithm has great accuracy and convergence.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115822463","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 : 2022-12-09DOI: 10.1109/SPIES55999.2022.10082695
Zhihui Liu, Yuchen Zhao, Boyu Zhou, Kai Yuan, Ye Tian, Liang Wang
In winter in China, thermal power units bear both the power supply load and the heat supply load. The coupling of the two greatly reduces the output adjustment range of the thermal power unit. Affected by holidays, etc., the load may suddenly decrease, but the thermal power unit may be forced to start up, and even if it is calculated by the lower output limit, the power load balance cannot be achieved. The production simulation program cannot find any feasible solution and will stop, requiring people to manually modify the working state of the thermal power unit. This paper proposes an algorithm to demarcate the priority of each thermal power unit when inputting data. Among the equal priorities, they are sorted according to the capacity from low to high. When the solution fails, a thermal power unit will be automatically selected for downgrading. The algorithm in this paper replaces manual operation steps in production simulation, and expands the solution space at the expense of part of the heating load.
{"title":"A Degraded Scheduling Algorithm for Thermal Power Units Based on Multiple Priority Queues","authors":"Zhihui Liu, Yuchen Zhao, Boyu Zhou, Kai Yuan, Ye Tian, Liang Wang","doi":"10.1109/SPIES55999.2022.10082695","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082695","url":null,"abstract":"In winter in China, thermal power units bear both the power supply load and the heat supply load. The coupling of the two greatly reduces the output adjustment range of the thermal power unit. Affected by holidays, etc., the load may suddenly decrease, but the thermal power unit may be forced to start up, and even if it is calculated by the lower output limit, the power load balance cannot be achieved. The production simulation program cannot find any feasible solution and will stop, requiring people to manually modify the working state of the thermal power unit. This paper proposes an algorithm to demarcate the priority of each thermal power unit when inputting data. Among the equal priorities, they are sorted according to the capacity from low to high. When the solution fails, a thermal power unit will be automatically selected for downgrading. The algorithm in this paper replaces manual operation steps in production simulation, and expands the solution space at the expense of part of the heating load.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134382857","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 : 2022-12-09DOI: 10.1109/SPIES55999.2022.10082110
Hongbin Pan, Changmin Yuan, Kai Qin, Dong Chen, Siqi Peng
In order to effectively utilize the large amount of regenerative braking energy generated by railroad locomotives, merged the advantages of modular multilevel converter (MMC) in medium and high voltage applications, a railway braking energy feedback device and its control method based on MMC topology are proposed. The operation principle and topological structure of the braking energy feedback device are analyzed, the corresponding control methods are given for the rectifier and inverter links, it could save the cost of transformer, improve the quality of grid current effectively, and achieve the rational recycling of regenerative braking energy. Finally, a simulation model is established to verify the feasibility and effectiveness of the proposed braking energy feedback device and control method.
{"title":"Research on Railway Braking Energy Feedback Device and Control Method","authors":"Hongbin Pan, Changmin Yuan, Kai Qin, Dong Chen, Siqi Peng","doi":"10.1109/SPIES55999.2022.10082110","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082110","url":null,"abstract":"In order to effectively utilize the large amount of regenerative braking energy generated by railroad locomotives, merged the advantages of modular multilevel converter (MMC) in medium and high voltage applications, a railway braking energy feedback device and its control method based on MMC topology are proposed. The operation principle and topological structure of the braking energy feedback device are analyzed, the corresponding control methods are given for the rectifier and inverter links, it could save the cost of transformer, improve the quality of grid current effectively, and achieve the rational recycling of regenerative braking energy. Finally, a simulation model is established to verify the feasibility and effectiveness of the proposed braking energy feedback device and control method.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132373896","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 : 2022-12-09DOI: 10.1109/SPIES55999.2022.10082264
Hao Li, Bozhen Jiang, Zhengyang Ma, H. Geng, Yi Liu
Accurate wind power forecasting plays an increasingly important role in the field of wind power forecasting but still intractable in practice. In order to improve the accuracy of wind power forecasting, a novel model based on squeeze and excitation network (SENet) embedded in a dual-channel is proposed. The dual-channel mechanism integrates convolutional neural network and gated recurrent unit, both of which can be used without interfering with each other. SENet can increase the attention of each important features, thus improving the network efficiency. Compared with a single model, the proposed model has better feature extraction performance with the root mean square error of 29.9. The test results of wind power data based on Kaggle platform show that the proposed method outperforms several deep learning forecasting methods.
{"title":"Dual-Channel Wind Power Forecasting Model Using Squeeze and Excitation Network","authors":"Hao Li, Bozhen Jiang, Zhengyang Ma, H. Geng, Yi Liu","doi":"10.1109/SPIES55999.2022.10082264","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082264","url":null,"abstract":"Accurate wind power forecasting plays an increasingly important role in the field of wind power forecasting but still intractable in practice. In order to improve the accuracy of wind power forecasting, a novel model based on squeeze and excitation network (SENet) embedded in a dual-channel is proposed. The dual-channel mechanism integrates convolutional neural network and gated recurrent unit, both of which can be used without interfering with each other. SENet can increase the attention of each important features, thus improving the network efficiency. Compared with a single model, the proposed model has better feature extraction performance with the root mean square error of 29.9. The test results of wind power data based on Kaggle platform show that the proposed method outperforms several deep learning forecasting methods.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"79 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133522765","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：