摘要
快速、准确地预测电动汽车充电负荷是实现电动汽车充放电行为控制的基础。该文围绕电动汽车充电负荷预测开展研究,基于电动汽车充电负荷分布特性分析,综合比较各类负荷预测方法的特点,提出了基于BP神经网络和指数平滑法进行电动汽车充电负荷的滚动预测,对选取的算法进行仿真分析,并结合充电负荷的日预测,比较两者的误差,滚动预测的精度要高于日预测的结论,验证了电动汽车充电负荷滚动预测的可行性与有效性。
The fast and accurate prediction of ev charging load is the basis of electric vehicle charging and discharging behavior control. Research,the paper around the electric car charging load forecasting based on electric vehicle charging load distribution characteristics analysis,comprehensive comparison of the characteristic of load forecasting method is proposed based on BP neural networks and exponential smoothing method for electric vehicle charging load rolling forecasts,simulation analysis was carried out on the selection algorithm,and combination of charging load forecast,compare the two error,the precision of the rolling forecast than day forecast conclusion,verify the feasibility of electric vehicle charging load rolling forecasts and effectiveness.
引文
[1]邵尹池,穆云飞,余晓丹,等.“车–路–网”模式下电动汽车充电负荷时空预测及其对配电网潮流的影响[J].中国电机工程学报,2017,37(18):5207-5219.
[2]黄小庆,陈颉,陈永新,等.大数据背景下的充电站负荷预测方法[J].电力系统自动化,2016,40(12):68-74.
[3]张洪财,胡泽春,宋永华,等.考虑时空分布的电动汽车充电负荷预测方法[J].电力系统自动化,2014,38(1):13-20.
[4]马玲玲,杨军,付聪,等.电动汽车充放电对电网影响研究综述[J].电力系统保护与控制,2013,41(3):140-148.
[5]高赐威,张亮.电动汽车充电对电网影响的综述[J].电网技术,2011,35(2):127-131.
[6]齐雪雯,徐玉韬.基于指数平滑方法的风速分布预测[J].贵州电力技术,2016,19(11):18-23.
[7]潘雪涛.基于改进BP神经网络算法的短期负荷预测[J].上海电力学院学报,2012,28(4):388-391.
[3]张振高,杨正瓴.短期负荷预测中的负荷求导法及天气因素的使用[J].电力系统及其自动化学报,2006,18(5):79-83.
[4]徐进东,丁晓群,邓勇.基于相似日的线性外推短期负荷预测[J].继电器,2005,33(7):37-39.
[5]杨争林,宋燕敏,曹荣章,等.超短期负荷预测在发电市场中的应用[J].电力系统白动化,2000,6(10):14-17.
[6] Al-Hamadi H M,Soliman S A.Short-term elec-tric load forecasting based on Kalman filtering algo-rithm with moving window weather and load model[J]. Electric Power Systems Research,2004,68(1):47-59.
[7] Amjady N. Short-term hourly load forecasting us-ing time-series modeling with peak load estimationcapability[J]. Power Systems,IEEE Transactionson,2001,16(3):498-505.
[8] Hippert H S,Pedreira C E,Souza R C.Neural net-works for short-term load forecasting:A review andevaluation[J]. Power Systems,IEEE Transactionson,2001,16(1):44-55.
[9]刘青,戚中译.基于蒙特卡洛法的电动汽车负荷预测建模[J].电力科学与工程,2014,30(10):14-19.
[10]刘校坤,车延博,刘国鉴,等.考虑出行规律的电动汽车规模化协调充电[J].电子设计工程,2017,25(13):28-31.
[12]陈达,张靖,杨艳.基于博弈论的入网电动汽车最优经济调度优化[J].贵州电力技术,2016,19(3):9-12.
[17]黄俊.电动汽车光伏电池充电系统的研究[J].电子设计工程,2017,25(18):94-96.
[18]李达,陈达,江新标,等.基于BP神经网络从活化数据中求解1MeV等效中子注量[J].现代应用物理,2015(4):248-253.
[19]蔚治国.基于改进BP神经网络的样本分类方法[J].自动化与仪器仪表,2016(6):237-239.