Real-time Load Prediction Model of Electric Vehicle Charging Station Considering Environmental Factors
CSTR:
Author:
Affiliation:

School of Automotive Studies, Tongji University, Shanghai 201804, China

Clc Number:

U469.72

  • Article
  • | |
  • Metrics
  • |
  • Reference [31]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    To mitigate the adverse effects of large-scale integration of electric vehicles into the grid, a method for the precise prediction of charging station load is proposed in this paper. The method employs a combination of LightGBM and XGBoost to construct offline-online ensemble models. Historical data including charging load, time, temperature, and weather are considered. Firstly, a charging load offline prediction model is established using LightGBM. Based on the XGBoost model, with the error between offline prediction model output load and actual load as the optimization target, and the real-time varying traffic flow as a covariate, an online prediction model is developed, and the error correction is performed on preliminary prediction results. Predictions from actual charging stations in a certain city indicate that compared to random forest (RF), LightGBM, XGBoost, multilayer perceptron (MLP), and LightGBM-RF ensemble models, the ensemble model demonstrates higher prediction accuracy while accurately forecasting real-time charging loads for different charging stations.

    Reference
    [1] 夏文芳. 电动汽车用电负荷预测及对城市电网的影响[J]. 农村电气化, 2018(11): 9.XIA Wenfang. Electric vehicle load predication and analysis of influence of electric vehicle load on urban power network [J]. Rural Electrification, 2018(11): 9.
    [2] MüLLER M, BLUME Y, REINHARD J. Impact of behind-the-meter optimised bidirectional electric vehicles on the distribution grid load[J]. Energy, 2022, 255: 124537.
    [3] ALLENSPACH C, HOGGER R, OBUSHEVS A, et al. Implementation of quasi-static time series simulations for analysis of the impact of electric vehicles on the grid[C]//2019 IEEE 60th International Scientific Conference on Power and Electrical Engineering of Riga Technical University (RTUCON). Piscataway: IEEE, 2019: 1-10.
    [4] ZWEISTRA M, JANSSEN S, GEERTS F. Large scale smart charging of electric vehicles in practice[J]. Energies, 2020,13(2):298.
    [5] 魏阳喆. 电动汽车充电对电网影响综述[J]. 时代汽车, 2022(2): 108.WEI Yangzhe. Overview of the impact of electric vehicle charging on the power grid [J]. Times Automotive, 2022(2): 108.
    [6] 金兆鹏. 电动汽车大规模接入对电网安全运行影响及管控措施分析[J]. 装备维修技术, 2019(4): 159.JIN Zhaopeng. Analysis of the impact of large-scale access of electric vehicles on the safe operation of power grid and control measures[J]. Equipment Technology, 2019(4): 159.
    [7] 陈男, 孙晓东, 马志鹏. 电动汽车接入电网对电网谐波的影响[J]. 电子测试, 2021(17): 122.CHEN Nan, SUN Xiaodong, MA Zhipeng. The impact of electric vehicles connected to the grid on grid harmonics [J]. Electronic Test, 2021(17): 122.
    [8] BUZNA L, DE FALCO P, FERRUZZI G, et al. An ensemble methodology for hierarchical probabilistic electric vehicle load forecasting at regular charging stations[J]. Applied Energy, 2021, 283: 116337.
    [9] DENG S, CHEN F, WU D, et al. Quantitative combination load forecasting model based on forecasting error optimization[J]. Computers and Electrical Engineering, 2022, 101: 108125.
    [10] 蔡黎, 葛棚丹, 代妮娜, 等. 电动汽车入网负荷预测及其与电网互动研究进展综述[J]. 智慧电力, 2022, 50(7): 96.CAI Li, GE Pengdan, DAI Nina, et al. Review of research progress on load prediction and grid interaction of electric vehicles [J]. Smart Power, 2022, 50(7): 96.
    [11] 王哲, 万宝, 凌天晗, 等. 基于谱聚类和LSTM神经网络的电动公交车充电负荷预测方法[J]. 电力建设, 2021, 42(6): 58.WANG Zhe, WAN Bao, LING Tianhan, et al. Electric bus charging load forecasting method based on spectral clustering and LSTM neural network [J]. Electric Power Construction, 2021, 42(6): 58.
    [12] 王琨, 高敬更, 张勇红, 等. 基于LSTM神经网络的复合变量电动汽车充电负荷预测方法技术研究[J]. 工业仪表与自动化装置, 2019(1): 27.WANG Kun, GAO Jinggeng, ZHANG Yonghong, et al. Study on forecasting method of charging load of hybrid variable electric vehicle based on LSTM neural network [J]. Industrial Instrumentation & Automation, 2019(1): 27.
    [13] ZHENG Y, SHAO Z, ZHANG Y, et al. A systematic methodology for mid-and-long term electric vehicle charging load forecasting: the case study of Shenzhen, China[J]. Sustainable Cities and Society, 2020, 56: 102084.
    [14] 陈丽丹, 张尧, FIGUEIREDO A. 电动汽车充放电负荷预测研究综述[J]. 电力系统自动化, 2019, 43(10): 177.CHEN Lidan, ZHANG Yao, FIGUEIREDO A. Overview of charging and discharging load forcasting for electric vehicles [J]. Power System Automation, 2019, 43(10): 177.
    [15] 梁宏涛, 刘红菊, 李静, 等. 基于机器学习的短期负荷预测算法综述[J]. 计算机系统应用, 2022, 31(10): 25.LIANG Hongtao, LIU Hongju, LI Jing, et al. Survey on short-term load forecasting algorithm based on machine learning [J]. Computer Systems & Applications, 2022, 31(10): 25.
    [16] 王华彪, 李小勇. 基于融合注意力机制改进双向长短时记忆网络在电动汽车充电负荷中的预测研究[J]. 电网与清洁能源, 2022, 38(6): 104.WANG Huabiao, LI Xiaoyong. Prediction of electric vehicle charging load based on integrating attention mechanism to improve BiLSTM [J]. Power System and Clean Energy, 2022, 38(6): 104.
    [17] FENG J, YANG J, LI Y, et al. Load forecasting of electric vehicle charging station based on grey theory and neural network[J]. Energy Reports, 2021, 7: 487.
    [18] SHEN X, ZHAO H, XIANG Y, et al. Short-term electric vehicles charging load forecasting based on deep learning in low-quality data environments[J]. Electric Power Systems Research, 2022, 212: 108247.
    [19] 李恒杰, 朱江皓, 傅晓飞, 等. 基于集成学习的电动汽车充电站超短期负荷预测[J]. 上海交通大学学报, 2022,56(8):1004.LI Hengjie, ZHU Jianghao, FU Xiaofei, et al. Ultra-short-term load forecasting of electric vehicle charging stations based on ensemble learning [J]. Journal of Shanghai Jiao Tong University, 2022,56(8):1004.
    [20] 吴丹, 雷珽, 李芝娟, 等. 基于XGBoost与LightGBM集成的电动汽车充电负荷预测模型[J]. 电子技术应用, 2022, 48(9): 44.WU Dan, LEI Ting, LI Zhijuan, et al. Electric vehicle charging load forecasting based on XGBoost and LightGBM integration model [J]. Application of Electronic Technique, 2022, 48(9): 44.
    [21] 邱瑞东, 何山, 董宁, 等. 基于LSTM-LGB模型的光伏电站辐照强度预测[J]. 安徽大学学报(自然科学版), 2021, 45(3): 66.QIU Ruidong, HE Shan, DONG Ning, et al. Irradiation intensity prediction of photovoltaic power station based on LSTM-LGB model[J]. Journal of Anhui University(Natural Sciences), 2021, 45(3): 66.
    [22] 肖迁,穆云飞,焦志鹏,等.基于改进LightGBM的电动汽车电池剩余使用寿命在线预测[J].电工技术学报,2022,37(17):4517.XIAO Qian, MU Yunfei, JIAO Zhipeng, et al. lmproved LightGBM based remaining useful life prediction of lithium-ion battery under driving conditions [J]. Transactions of China Electrotechnical Society,2022,37(17):4517.
    [23] 昌玲, 邓国安. 基于LightGBM及LSTM融合的科技园区短期负荷预测[J]. 湖南电力, 2021, 41(6): 31.CHANG Ling, DENG Guoan. Short term load forecasting of science and technology park based on integration of LightGBM and LSTM [J]. Hunan Electric Power, 2021, 41(6): 31
    [24] 蔡明, 孙杰, 李培德, 等. 三种机器学习算法在回归应用中的对比分析[J]. 智能计算机与应用, 2022, 12(8): 165.CAI Ming, SUN Jie, LI Peide, et al. Comparative analysis of three machine learning algorithms in regression application [J]. Intelligent Computers and Applications, 2022, 12(8): 165.
    [25] 卢锦玲, 郭鲁豫, 张梦雪, 等. 基于MGS?LGBM算法的电力系统暂态稳定评估[J]. 电力科学与工程, 2020, 36(3): 52.LU Jinling, GUO Luyu, ZHANG Mengxue, et al. Power system transient stability assessment based on MGS-LGBM [J]. Electric Power Science and Engineering, 2020, 36(3): 52.
    [26] 肖宇, 赵建有, 叱干都, 等. 基于XGBoost的短时出租车速度预测模型[J]. 交通信息与安全, 2022, 40(3): 163.XIAO Yu, ZHAO Jianyou, CHIGAN Du, et al. A short-term prediction model for taxi speed based on XGBoost [J]. Journal of Transport Information and Safety, 2022, 40(3): 163.
    [27] 杨洋, 谷震浩. 基于XGBoost?DNN的中期电力负荷预测[J]. 计算机系统应用, 2021, 30(9): 186.YANG Yang, GU Zhenhao. Mid-term power load forecasting based on XGBoost-DNN [J]. Computer System & Applications, 2021, 30(9): 186.
    [28] DONG J, CHEN Y, YAO B, et al. A neural network boosting regression model based on XGBoost[J]. Applied Soft Computing, 2022, 125: 109067.
    [29] 代业明, 周琼. 基于改进Bi?LSTM和XGBoost的电力负荷组合预测方法[J]. 上海理工大学学报, 2022, 44(2): 138.DAI Yeming, ZHOU Qiong. Power load combination forecasting method based on improved Bi-LSTM and XGBoost [J]. Journal of University of Shanghai for Science and Technology, 2022, 44(2): 138.
    [30] CHICCO D, WARRENS M J, JURMAN G.The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation[J].PeerJ Computer Science,2021,7: e623.
    [31] AMARA-OUALI Y, GOUDE Y, HAMROUCHE B, et al. A benchmark of electric vehicle load and occupancy models for day-ahead forecasting on open charging session data[C]//Proceedings of the Thirteenth ACM International Conference on Future Energy Systems. New York: ACM, 2022: 193-207.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

LI Bo, WANG Ning, Lü Yelin, CHEN Yu. Real-time Load Prediction Model of Electric Vehicle Charging Station Considering Environmental Factors[J].同济大学学报(自然科学版),2024,52(6):962~969

Copy
Share
Article Metrics
  • Abstract:207
  • PDF: 1066
  • HTML: 959
  • Cited by: 0
History
  • Received:August 21,2022
  • Online: June 28,2024
Article QR Code