Suzhou Electric Appliance Research Institute
期刊號: CN32-1800/TM| ISSN1007-3175

Article retrieval

文章檢索

首頁 >> 文章檢索 >> 往年索引

基于電動汽車充電負荷變動速率與TCN-LSTM的負荷預測

來源:電工電氣發布時間:2025-06-27 13:27 瀏覽次數:5

基于電動汽車充電負荷變動速率與TCN-LSTM的負荷預測

汪楚皓1,2,郭航3
(1 長沙理工大學 電氣與信息工程學院,湖南 長沙 410114;
2 國網湖南省電力有限公司常德供電分公司,湖南 常德 415000;
3 國網湖南省電力有限公司株洲供電分公司,湖南 株洲 412000)
 
    摘 要:電動汽車充電負荷的隨機性波動對電力系統的安全穩定性帶來挑戰,提出了一種基于電動汽車充電負荷變動速率與人工智能算法結合的短期預測方法。分析了電動汽車充電負荷的歷史數據,提出了一種反映充電負荷速率變動特征的指標;結合時空卷積網絡(TCN)和長短期記憶網絡(LSTM)構建了預測模型,對充電負荷進行精準預測。實驗結果表明,該方法能夠有效研究區域內電動汽車用戶的充電規律,對充電負荷峰谷態勢的預測表現出較高的準確性,為深入分析用戶充電行為模式、準確預估短期充電負荷提供了重要技術支持,對提升電力系統運行效率與穩定性具有重要意義。
    關鍵詞: 電動汽車;充電負荷;時空卷積網絡;長短期記憶網絡;短期負荷預測
    中圖分類號:TM715 ;U469.72     文獻標識碼:A     文章編號:1007-3175(2025)06-0019-05
 
Load Forecasting Based on the Variation Rate of Electric
Vehicle Charging Load and TCN-LSTM
 
WANG Chu-hao1,2, GUO Hang3
(1 School of Electrical and Information Engineering, Changsha University of Science & Technology, Changsha 410114, China;
2 State Grid Hunan Electric Power Co., Ltd. Changde Power Supply Branch Company, Changde 415000, China;
3 State Grid Hunan Electric Power Co., Ltd. Zhuzhou Power Supply Branch Company, Zhuzhou 412000, China)
 
    Abstract: The stochastic fluctuations of electric vehicle charging loads pose challenges to the safety and stability of power systems. To address this issue, this paper proposes a short-term forecasting method based on the combination of the variation rate of electric vehicle charging load and artificial intelligence algorithms. Firstly, historical data of electric vehicle charging loads are analyzed, and an indicator reflecting the variation characteristics of the charging load rate is introduced. Subsequently, a predictive model combining temporal convolutional network(TCN) and long short-term memory network(LSTM) is constructed to achieve accurate load forecasting. Experimental results demonstrate that the proposed method effectively analyzes the charging patterns of electric vehicle users in the study area and achieves high accuracy in predicting the peak-valley trends of charging loads. This study provides critical technical support for analyzing user charging behavior patterns and accurately estimating short-term charging loads, offering significant contributions to enhancing the operational efficiency and stability of power systems.
    Key words: electric vehicle; charging load; temporal convolutional network; long short-term memory network; short-term load forecasting
 
參考文獻
[1] HU Xiaosong, YUAN Hao, ZOU Changfu, et al.Coestimation of state of charge and state of health for lithium-ion batteries based on fractionalorder calculus[J].IEEE Transactions on Vehicular Technology,2018,67(11) :10319-10329.
[2] LIU Senyi, LIU Chunhua.Generic predictive model calibration for PMSMs with different topologies[J].Green Energy and Intelligent Transportation,2022,1(1) :100015.
[3] DANESHZAND F, COKER P J, POTTER B, et al.EV smart charging: How tariff selection influences grid stress and carbon reduction[J].Applied Energy,2023,348 :121482.
[4] 王惠文,孟潔. 多元線性回歸的預測建模方法[J]. 北京航空航天大學學報,2007,33(4) :500-504.
[5] 彭丁聰. 卡爾曼濾波的基本原理及應用[J]. 軟件導刊,2009,8(11) :32-34.
[6] 包研科,陳然,鄭宏杰,等. 指數平滑與自回歸融合預測模型及實證[J] . 計算機工程與應用,2022,58(14) :269-281.
[7] SHI Jinkai, ZHANG Weige, BAO Yan, et al.Load forecasting of electric vehicle charging stations: Attention based spatiotemporal multigraph convolutional networks[J].IEEE Transactions on Smart Grid,2024,15(3) :3016-3027.
[8] 尤勇,孟云龍,吳景濤,等. 基于鯨魚優化算法-支持向量回歸的汽車運動狀態估計[J] . 中國機械工程,2024,35(6) :973-981.
[9] 周澤楷,侯宏娟,孫莉,等. 基于 CNN 和 BiLSTM 神經網絡模型的太陽能供暖負荷預測研究[J] . 太陽能學報,2024,45(10) :415-422.
[10] 王義國,林峰,李琦,等. 基于 TCN-LSTM 模型的電網電能質量擾動分類研究[J] . 電力系統保護與控制,2024,52(17) :161-167.
[11] 劉寧,謝越棟,胡彬,等. CNN-LSTM 車輛運動狀態識別的 AUKF 組合導航方法[J] . 中國慣性技術學報,2024,32(8) :803-811.
[12] WANG Ning, GUO Jiahui, LIU Xiang, et al.A service demand forecasting model for oneway electric car-sharing systems combining long short-term memory networks with Granger causality test[J].Journal of Cleaner Production,2020,244 :118812.
[13] ALI A, ZHU Y, ZAKARYA M.Exploiting dynamic spatiotemporal graph convolutional neural networks for citywide traffic flows prediction[J].Neural Networks, 2022,145 :233-247.
[14] TIAN Jiarui, LIU Hui, GAN Wei, et al.Shortterm electric vehicle charging load forecasting based on TCN-LSTM network with comprehensive similar day identification[J].Applied Energy,2025,381 :125174.

 

精品无码国产一区二区12p