Pub Date : 2022-12-23DOI: 10.1109/ICPES56491.2022.10073355
Xudong Li, Hua Li, Yichen Yan, Peng Kou
When converter blocking occurs on the high voltage direct current (HVDC) transmission systems, the resulting excess active power and reactive power lead to the rise in grid frequency and bus voltage, which seriously endangers the safe operation of the power system. The traditional control methods mainly focus on the separate control of frequency and voltage, which cannot regulate them cooperatively. To address this issue, this paper proposes a combined voltage and frequency optimal control method. For the prediction of frequency and voltage, the state space models are established based on the swing equation and the voltage sensitivity matrix. Using the linear quadratic regulator (LQR), the frequency control and voltage control are inherently integrated. When blocking occurs, the grid frequency and voltage increase, and the LQR controller adjusts the wind farm's active and reactive power output to achieve a cooperative control of grid frequency and bus voltage. Simulation results verify the effectiveness of this method.
{"title":"Combined Frequency and Voltage Support by Wind Farm with Linear Quadratic Regulator under Converter Blocking","authors":"Xudong Li, Hua Li, Yichen Yan, Peng Kou","doi":"10.1109/ICPES56491.2022.10073355","DOIUrl":"https://doi.org/10.1109/ICPES56491.2022.10073355","url":null,"abstract":"When converter blocking occurs on the high voltage direct current (HVDC) transmission systems, the resulting excess active power and reactive power lead to the rise in grid frequency and bus voltage, which seriously endangers the safe operation of the power system. The traditional control methods mainly focus on the separate control of frequency and voltage, which cannot regulate them cooperatively. To address this issue, this paper proposes a combined voltage and frequency optimal control method. For the prediction of frequency and voltage, the state space models are established based on the swing equation and the voltage sensitivity matrix. Using the linear quadratic regulator (LQR), the frequency control and voltage control are inherently integrated. When blocking occurs, the grid frequency and voltage increase, and the LQR controller adjusts the wind farm's active and reactive power output to achieve a cooperative control of grid frequency and bus voltage. Simulation results verify the effectiveness of this method.","PeriodicalId":425438,"journal":{"name":"2022 12th International Conference on Power and Energy Systems (ICPES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128357263","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 : 2022-12-23DOI: 10.1109/ICPES56491.2022.10073301
Bo Li, Weinian Ouyang, Tianlun Wang, Zhirui Tang, Tingwei Chen, Zefu Wang
Under the new power system, the traditional source-follow-load model has changed. With the access of high penetration of renewable energy, more flexible resources need to be explored from the source-side grid side and load side to increase the consumption of renewable energy. Therefore, the optimization of ‘source-grid-load-storage (SGLS)’ interaction is a hot topic of current research. Because of the different interests belonging to different parties and their willingness to participate, the adoption of a centralized algorithm cannot coordinate the interests of all parties well. The state based potential game (SPG) method can coordinate the consistency of individual interests and subject interests, and has higher solution accuracy and solution efficiency compared with the general potential game (PG). Therefore, this article designs the SGLS interaction optimization model as a SPG problem, solves it using a distributed algorithm, and verifies the effectiveness of the proposed method through simulation.
{"title":"Optimal Regulation of ‘Source-Grid-Load-Storage’ Interaction Based on State Based Potential Game","authors":"Bo Li, Weinian Ouyang, Tianlun Wang, Zhirui Tang, Tingwei Chen, Zefu Wang","doi":"10.1109/ICPES56491.2022.10073301","DOIUrl":"https://doi.org/10.1109/ICPES56491.2022.10073301","url":null,"abstract":"Under the new power system, the traditional source-follow-load model has changed. With the access of high penetration of renewable energy, more flexible resources need to be explored from the source-side grid side and load side to increase the consumption of renewable energy. Therefore, the optimization of ‘source-grid-load-storage (SGLS)’ interaction is a hot topic of current research. Because of the different interests belonging to different parties and their willingness to participate, the adoption of a centralized algorithm cannot coordinate the interests of all parties well. The state based potential game (SPG) method can coordinate the consistency of individual interests and subject interests, and has higher solution accuracy and solution efficiency compared with the general potential game (PG). Therefore, this article designs the SGLS interaction optimization model as a SPG problem, solves it using a distributed algorithm, and verifies the effectiveness of the proposed method through simulation.","PeriodicalId":425438,"journal":{"name":"2022 12th International Conference on Power and Energy Systems (ICPES)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127053129","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 : 2022-12-23DOI: 10.1109/ICPES56491.2022.10073145
Wu Junling, Dai Hanyang, Su Lining
Energy storage is an effective means to ensure the consumption of renewable energy and the supply to power consumers in the new power system, which will be widely applied. As energy storage is also a kind of power electronic equipment, its low/high voltage ride through (LVRT/HVRT) transient characteristics will have positive or negative impacts on the safety of power grid, especially on the transient stability and temporary overvoltage (TOV) problems. In order to make full use of the flexible regulation ability of energy storage and make it play a positive role to the safety of power grid, this paper sorted out the typical power transmission mode of large scale renewable energy bases in China and constructed a typical model of wind-solar-thermal-storage combined system. On this basis, the principle of the influence of the LVRT/HVRT transient characteristics of the energy storage on the transient stability of the sending end system and the TOV of renewable energy generation unit is analyzed. Then, the optimization direction of the key control parameters for LVRT/HVRT of energy storage was studied through simulation by PSD-BPA. Finally, the differentiated technical requirements were proposed.
{"title":"Research on Influence and Parameter Optimization of Voltage Ride through Control Strategies of Energy Storage in Renewable Energy Power Sending System","authors":"Wu Junling, Dai Hanyang, Su Lining","doi":"10.1109/ICPES56491.2022.10073145","DOIUrl":"https://doi.org/10.1109/ICPES56491.2022.10073145","url":null,"abstract":"Energy storage is an effective means to ensure the consumption of renewable energy and the supply to power consumers in the new power system, which will be widely applied. As energy storage is also a kind of power electronic equipment, its low/high voltage ride through (LVRT/HVRT) transient characteristics will have positive or negative impacts on the safety of power grid, especially on the transient stability and temporary overvoltage (TOV) problems. In order to make full use of the flexible regulation ability of energy storage and make it play a positive role to the safety of power grid, this paper sorted out the typical power transmission mode of large scale renewable energy bases in China and constructed a typical model of wind-solar-thermal-storage combined system. On this basis, the principle of the influence of the LVRT/HVRT transient characteristics of the energy storage on the transient stability of the sending end system and the TOV of renewable energy generation unit is analyzed. Then, the optimization direction of the key control parameters for LVRT/HVRT of energy storage was studied through simulation by PSD-BPA. Finally, the differentiated technical requirements were proposed.","PeriodicalId":425438,"journal":{"name":"2022 12th International Conference on Power and Energy Systems (ICPES)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134223237","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 : 2022-12-23DOI: 10.1109/ICPES56491.2022.10072710
Yiqi Dang, Hua Wang, Lei Liu, Wenzhe Chen, Hongxiang Xu, Wei Han, W. Ma
In the process of stability controlling such as load shedding, if breaker failure occurred, current solutions cannot resection enough load to balance the generation and consumption to keep frequency and voltage stability. The same question also exists in other control processes such as out-step splitting, etc. In this paper, the authors analyzed the potential measures available in the field substation and discussed the feasibility of using breaker failure protection as the backup solution to handle the problems. Based on the analysis, the author put forward an optimized power system stability control structure and explained its availability, feasibility, and merits. Besides, the authors researched the logic of breaker failure protection, and come up with a method to prevent the breaker failure protection from malfunctioning. The simulation proved the correction of the authors' views.
{"title":"An Optimalized Power System Stability Control Structure Based on Breaker Failure Protection as Backup","authors":"Yiqi Dang, Hua Wang, Lei Liu, Wenzhe Chen, Hongxiang Xu, Wei Han, W. Ma","doi":"10.1109/ICPES56491.2022.10072710","DOIUrl":"https://doi.org/10.1109/ICPES56491.2022.10072710","url":null,"abstract":"In the process of stability controlling such as load shedding, if breaker failure occurred, current solutions cannot resection enough load to balance the generation and consumption to keep frequency and voltage stability. The same question also exists in other control processes such as out-step splitting, etc. In this paper, the authors analyzed the potential measures available in the field substation and discussed the feasibility of using breaker failure protection as the backup solution to handle the problems. Based on the analysis, the author put forward an optimized power system stability control structure and explained its availability, feasibility, and merits. Besides, the authors researched the logic of breaker failure protection, and come up with a method to prevent the breaker failure protection from malfunctioning. The simulation proved the correction of the authors' views.","PeriodicalId":425438,"journal":{"name":"2022 12th International Conference on Power and Energy Systems (ICPES)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134273313","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}
Photovoltaic (PV) systems used for the generation of power have been encouraged due to the availability and reliability of solar energy. A designed control system for the generation of power based on solar using a signal search artificial bee colony (SS-ABC) optimization algorithm as the maximum power point tracker (MPPT). The shorter and longer distances between the bees and their prey are signaled using the SS-ABC. The quick concurrence and high accuracy of the SS-ABC are established as it interactively integrates with the exploratory evolution with the essential distinctive signal search from the PV array during the maximum power point tracking process which increases the speed and tracks more power. The SS-ABC was compared with conventional ABC, particle swarm optimization (PSO), bat algorithm (BA), and perturb and observe (P&O) algorithms. The design was implemented and simulated in MATLAB Simulink and the efficiency of the proposed method has been achieved from the results.
{"title":"Solar Power Generation System Based on Signal Search Artificial Bee Colony Optimization Algorithm for Maximum Power Point Tracking","authors":"Akwasi Amoh Mensah, Haoyong Chen, Duku Otuo-Acheampong, Tumbiko Mbuzi","doi":"10.1109/ICPES56491.2022.10072495","DOIUrl":"https://doi.org/10.1109/ICPES56491.2022.10072495","url":null,"abstract":"Photovoltaic (PV) systems used for the generation of power have been encouraged due to the availability and reliability of solar energy. A designed control system for the generation of power based on solar using a signal search artificial bee colony (SS-ABC) optimization algorithm as the maximum power point tracker (MPPT). The shorter and longer distances between the bees and their prey are signaled using the SS-ABC. The quick concurrence and high accuracy of the SS-ABC are established as it interactively integrates with the exploratory evolution with the essential distinctive signal search from the PV array during the maximum power point tracking process which increases the speed and tracks more power. The SS-ABC was compared with conventional ABC, particle swarm optimization (PSO), bat algorithm (BA), and perturb and observe (P&O) algorithms. The design was implemented and simulated in MATLAB Simulink and the efficiency of the proposed method has been achieved from the results.","PeriodicalId":425438,"journal":{"name":"2022 12th International Conference on Power and Energy Systems (ICPES)","volume":"4638 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133231466","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 : 2022-12-23DOI: 10.1109/ICPES56491.2022.10073364
Zhichuan Li, Sheng Lan, Ke Wei
Aiming at the difficulty of locating single pole ground fault in LCC-MMC hybrid DC transmission lines, a single pole ground fault location method for transmission lines based on Variational model decomposition (VMD) - Decision Tree (DT) feature selection and Extremely randomized trees (Extra-Trees) is proposed. First, the collected two terminal fault waveforms are connected in series, sent to the VMD algorithm for decomposition, and then the decomposed modal components are connected in series with the original waveform. Then, the importance of features is calculated using the feature importance quantification method of DT algorithm, and the features with higher importance are constructed into a new feature set. Finally, the Extra-Trees model is built and trained with the new feature set to make it have the ability of fault prediction. A ±800kV LCC-MMC hybrid DC transmission system is built to verify the proposed method. The simulation results show that the proposed method can accurately locate the single pole ground fault location.
{"title":"Single Pole Ground Fault Location Method for LCC-MMC Hybrid DC Transmission Lines Based on Extremely Randomized Trees","authors":"Zhichuan Li, Sheng Lan, Ke Wei","doi":"10.1109/ICPES56491.2022.10073364","DOIUrl":"https://doi.org/10.1109/ICPES56491.2022.10073364","url":null,"abstract":"Aiming at the difficulty of locating single pole ground fault in LCC-MMC hybrid DC transmission lines, a single pole ground fault location method for transmission lines based on Variational model decomposition (VMD) - Decision Tree (DT) feature selection and Extremely randomized trees (Extra-Trees) is proposed. First, the collected two terminal fault waveforms are connected in series, sent to the VMD algorithm for decomposition, and then the decomposed modal components are connected in series with the original waveform. Then, the importance of features is calculated using the feature importance quantification method of DT algorithm, and the features with higher importance are constructed into a new feature set. Finally, the Extra-Trees model is built and trained with the new feature set to make it have the ability of fault prediction. A ±800kV LCC-MMC hybrid DC transmission system is built to verify the proposed method. The simulation results show that the proposed method can accurately locate the single pole ground fault location.","PeriodicalId":425438,"journal":{"name":"2022 12th International Conference on Power and Energy Systems (ICPES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130859658","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 : 2022-12-23DOI: 10.1109/ICPES56491.2022.10072484
Ma Yuan, Ding Ran, Yao Yiming, Geng Yan, Shao Yinchi, Wang Xiaoxiao
With the advancement of China's carbon peaking and carbon neutrality goals and the development of photovoltaic power generation technology, a large scale of distributed photovoltaics are connected to the rural distribution network in recent years. Photovoltaic power generation features high randomness and uncertainty, Accurate prediction of distributed PV power on ultra-short-term time scale (0-4h) is of great significance to the safe and stable operation of distribution network. This paper proposes a prediction algorithm based on satellite cloud images considering spatiotemporal correlation between solar stations nearby. Firstly, correlation between adjacent power plants are sorted, corresponding prediction models based on LSTM are built using historical power and NWP data, then satellite images are used to choose suitable prediction models for prediction when forecasting. With the actual dataset of photovoltaic power station in northeast China, The proposed algorithm is verified, the test results show that the proposed algorithm proposed in this paper is generally at a better accuracy level compared with other well-established benchmarks in terms of power curve and statistical error.
{"title":"Ultra Short Term Distributed Photovoltaic Power Prediction Based on Satellite Cloud Images Considering Spatiotemporal Correlation","authors":"Ma Yuan, Ding Ran, Yao Yiming, Geng Yan, Shao Yinchi, Wang Xiaoxiao","doi":"10.1109/ICPES56491.2022.10072484","DOIUrl":"https://doi.org/10.1109/ICPES56491.2022.10072484","url":null,"abstract":"With the advancement of China's carbon peaking and carbon neutrality goals and the development of photovoltaic power generation technology, a large scale of distributed photovoltaics are connected to the rural distribution network in recent years. Photovoltaic power generation features high randomness and uncertainty, Accurate prediction of distributed PV power on ultra-short-term time scale (0-4h) is of great significance to the safe and stable operation of distribution network. This paper proposes a prediction algorithm based on satellite cloud images considering spatiotemporal correlation between solar stations nearby. Firstly, correlation between adjacent power plants are sorted, corresponding prediction models based on LSTM are built using historical power and NWP data, then satellite images are used to choose suitable prediction models for prediction when forecasting. With the actual dataset of photovoltaic power station in northeast China, The proposed algorithm is verified, the test results show that the proposed algorithm proposed in this paper is generally at a better accuracy level compared with other well-established benchmarks in terms of power curve and statistical error.","PeriodicalId":425438,"journal":{"name":"2022 12th International Conference on Power and Energy Systems (ICPES)","volume":"387 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131986929","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 poloidal field AC/DC converter system, the one of the core system of the ITER fusion device, has many abnormal situations during its operation. A stable and reliable local interlock system is an essential facility for its safe operation. In this paper, the fail-safe PLC is used as the core controller, fail-safe module as I/O interface, and the CODAC core system based on EPICS provided by ITER organization as the development platform to realize the development of the local interlock control system. The system collects the status of the transformers, converters, and water cooling system, etc. of the poloidal field converter system in real time. When the core controller of the interlock system detects a fault or abnormality, the fail-safe PLC will respond in time to ensure that the converter system enters a safe state. The system designed by this paper has been successfully tested on ITER PF test platform and supplied to IO.
{"title":"Local Interlock Control System with Fail-Safe PLC for PF Converter System Based on CODAC Core System","authors":"Shiying He, Liansheng Huang, Xiaojiang Chen, Xiuqing Zhang, Zejing Wang, Lingpeng Li, Ying Zuo","doi":"10.1109/ICPES56491.2022.10072659","DOIUrl":"https://doi.org/10.1109/ICPES56491.2022.10072659","url":null,"abstract":"The poloidal field AC/DC converter system, the one of the core system of the ITER fusion device, has many abnormal situations during its operation. A stable and reliable local interlock system is an essential facility for its safe operation. In this paper, the fail-safe PLC is used as the core controller, fail-safe module as I/O interface, and the CODAC core system based on EPICS provided by ITER organization as the development platform to realize the development of the local interlock control system. The system collects the status of the transformers, converters, and water cooling system, etc. of the poloidal field converter system in real time. When the core controller of the interlock system detects a fault or abnormality, the fail-safe PLC will respond in time to ensure that the converter system enters a safe state. The system designed by this paper has been successfully tested on ITER PF test platform and supplied to IO.","PeriodicalId":425438,"journal":{"name":"2022 12th International Conference on Power and Energy Systems (ICPES)","volume":"37 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133585242","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 : 2022-12-23DOI: 10.1109/ICPES56491.2022.10072847
W. Ma, Houlei Gao, Haoran Song, Yunchi Zhang
When the grid voltage contains high harmonics, decouple double synchronous reference frame phase lock loop (DDSRF-PLL) will not extract the synchronizing information accurately. And conventional grid-connected control strategy makes insufficient use of photovoltaic (PV) inverter's reactive power output capacity when grid is faulty. For above problem, this paper proposes a low voltage riding through control strategy based on improved DDSRF-PLL and reactive current control. After analyzing the structure of DDSRF-PLL module, high-order harmonic filters are introduced before decoupling calculation, so that the module can extract grid synchronizing information and positive/negative sequence value more accurately. Furthermore, by establishing relationship between voltage drop and output reactive current, PV inverter can provide reactive power support required from grid during LVRT, and provide active power as much as possible. When bus capacitor voltage rises due to power imbalance between front and rear stage of system, the crowbar circuit is used to ensure DC voltage stability. Finally, A simulation model is build in MATLAB/simulink to verify the effectiveness of this LVRT strategy.
{"title":"Grid-Connected Photovoltaic LVRT Strategy Based on Improved DDSRF-PLL and Reactive Power Control","authors":"W. Ma, Houlei Gao, Haoran Song, Yunchi Zhang","doi":"10.1109/ICPES56491.2022.10072847","DOIUrl":"https://doi.org/10.1109/ICPES56491.2022.10072847","url":null,"abstract":"When the grid voltage contains high harmonics, decouple double synchronous reference frame phase lock loop (DDSRF-PLL) will not extract the synchronizing information accurately. And conventional grid-connected control strategy makes insufficient use of photovoltaic (PV) inverter's reactive power output capacity when grid is faulty. For above problem, this paper proposes a low voltage riding through control strategy based on improved DDSRF-PLL and reactive current control. After analyzing the structure of DDSRF-PLL module, high-order harmonic filters are introduced before decoupling calculation, so that the module can extract grid synchronizing information and positive/negative sequence value more accurately. Furthermore, by establishing relationship between voltage drop and output reactive current, PV inverter can provide reactive power support required from grid during LVRT, and provide active power as much as possible. When bus capacitor voltage rises due to power imbalance between front and rear stage of system, the crowbar circuit is used to ensure DC voltage stability. Finally, A simulation model is build in MATLAB/simulink to verify the effectiveness of this LVRT strategy.","PeriodicalId":425438,"journal":{"name":"2022 12th International Conference on Power and Energy Systems (ICPES)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116427414","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 : 2022-12-23DOI: 10.1109/ICPES56491.2022.10072605
Qiyao He, Yongxin Su
Accurate residential load forecasting plays an important role to improve the economy and security of power system operation. However, as the unbalanced distribution of residential load and the intertwined effects of multiple factors, it is difficult for a single neural network to make accurate predictions and its ability to generalize is limited. In this regard, this paper proposes a CNN-LSTM and non-uniform quantization based method for one-hour ahead residential load forecasting. First, we solve the unbalanced distribution of residential load by non-uniform quantization, which converts the load to an approximately normal distribution and fits the learning of neural networks. Then, the equivalent load after non-uniform quantization and its influencing factors are interwoven to form intertwining diagrams to facilitate the extraction of nonlinear relationships. Next, considering the intertwined effects of multiple factors, we use CNN-LSTM to extract temporal and spatial characteristics between multiple factors and cope with complex load patterns. We train and validate the proposed method using a real-world dataset, and the experiment results show that the proposed method outperforms the existing load forecasting methods.
{"title":"Residential Load Forecasting Based on CNN-LSTM and Non-uniform Quantization","authors":"Qiyao He, Yongxin Su","doi":"10.1109/ICPES56491.2022.10072605","DOIUrl":"https://doi.org/10.1109/ICPES56491.2022.10072605","url":null,"abstract":"Accurate residential load forecasting plays an important role to improve the economy and security of power system operation. However, as the unbalanced distribution of residential load and the intertwined effects of multiple factors, it is difficult for a single neural network to make accurate predictions and its ability to generalize is limited. In this regard, this paper proposes a CNN-LSTM and non-uniform quantization based method for one-hour ahead residential load forecasting. First, we solve the unbalanced distribution of residential load by non-uniform quantization, which converts the load to an approximately normal distribution and fits the learning of neural networks. Then, the equivalent load after non-uniform quantization and its influencing factors are interwoven to form intertwining diagrams to facilitate the extraction of nonlinear relationships. Next, considering the intertwined effects of multiple factors, we use CNN-LSTM to extract temporal and spatial characteristics between multiple factors and cope with complex load patterns. We train and validate the proposed method using a real-world dataset, and the experiment results show that the proposed method outperforms the existing load forecasting methods.","PeriodicalId":425438,"journal":{"name":"2022 12th International Conference on Power and Energy Systems (ICPES)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114427326","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：