|本期目录/Table of Contents|

[1]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,(01):27-31.[doi:1000-0682（2019）01-0000-00]
　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,(01):27-31.[doi:1000-0682（2019）01-0000-00]
点击复制

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

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2019年01期
页码:
27-31
栏目:
出版日期:
2019-02-15

文章信息/Info

Title:
Study on forecasting method of charging load of hybrid variable electric vehicle based on LSTM neural network
作者:
王 琨1; 高敬更1; 张勇红2; 魏立兵1; 李 鹏1; 杨春光1; 董智颖1
1. 国网甘肃省电力公司电力科学研究院；
2. 国网甘肃省电力公司，兰州 730070
Author(s):
WANG Kun1;  GAO Jinggeng1;  ZHANG Yonghong2;  WEI Libing1;  LI Peng1;  YANG Chunguang1;  DONG Zhiying1
1. State Grid Gansu Electric Power Research Institute;?
2.State Grid Gansu Power Company, Lanzhou 730070, China
关键词:
电动汽车; 负荷预测; LSTM
Keywords:
electric vehicle;  load forecasting;  LSTM
分类号:
U469.72;TM910.6
DOI:
1000-0682（2019）01-0000-00
文献标志码:
A
摘要:
随着电动汽车并网容量的不断增加，面向电动汽车充电负荷准确地开展功率预测对于并网电力系统的经济调度和优化运行意义重大。基于计算机交叉学科的深度学习领域算法不断进步，为准确构建电动汽车充电负荷模型提供高效工具。该文研究一种基于LSTM(long short-term memory)神经网络的复合变量电动汽车充电负荷预测方法，将电动汽车充电负荷历史数据进行预处理，采用LSTM网络对降维后的时间序列进行动态建模，完成电动汽车充电负荷预测。采用实际数据进行验证，结果证明所提方法的有效性。
Abstract:
With the growth of electric vehicle charging load integrated with power system, accurate load forecasting is essential to economic dispatching and optimal operation of PV system. The progress of algorithm from deep learning provides an effective method for refined analysis of electric vehicle charging load. A multivariate method for electric vehicle charging load forecasting based on LSTM(Long Short-term memory) was presented in this paper. It modeled the model from the viewpoint of time based on LSTM. The real data was applied to verify the accuracy of the proposed method.

参考文献/References:

[1] Electric Vehicles Initiative(EVI).Globe EV outlook: under- standding the electric vehicle landscape to 2020[R]. 2013.

[2] RAZEGHI G,ZHANG L,BROWN T,et al.Impacts of plug in hybrid electric vehicles on a residential transformer using stochastic and empirical analysis[J].Journal of Power Sources,2014,252: 277-285.
[3] 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):14-21.
[4] CLEMENT K, HAESEN E, DRIESEN J, et al. The impact of charging plug in hybrid electric vehicle on a residential distribution grid[J].IEEE Trans on Power System,2010, 25(1): 371-380.
[5] 袁正平,周伟,王文斌.电动汽车充电负荷预测方法研究[J].华东电力,2013,41(12):2657-2665.
[6] 刘青,戚中译.考虑空间运动特性的规模化电动汽车接入电网负荷预测模型[J].现代电力, 2015, 32(1): 76-87.
[7] ASHTARI A, BIBEAU E, SHAHIDINEJAD S, et al. PEV charging profile prediction and analysis based on vehicle usage data[J].IEEE Trans on Smart Grid,2012,3(1):341-350.
[8] 常德政,任杰,赵建伟,等.基于RBF-NN的电动汽车充电站短期负荷预测研究[J].青岛大学学报(工程技术版), 2014, 29(4): 45-51.
[9] 刘文霞,徐晓波,周樨.基于支持向量机的纯电动公交车充/换电站日负荷预测[J].电力系统自动化设备,2014, 34(11): 41-48.
[10] TASCIKARAOGLU A, UZUNOGLU M. A review of combined approaches for prediction of short-term wind speed and power[J].Renewable and Sustainable Energy Reviews,2014(34): 243-254.
[11] ZHANG W Y,HONG W C,DONG Y C,et al.Application of SVR with chaotic GASA algorithm in cyclic electric load forecasting[J]. Energy, 2012, 45(1): 850-858.
[12] 周湶,孙威,任海军,等.基于最小二乘支持向量机和负荷密度指标法的配电网空间负荷预测[J].电网技术,2011, 35(1): 66-70.[13] 肖白,聂鹏,穆钢,等.基于多级聚类分析和支持向量机的空间负荷预测方法[J].电力系统自动化,2015,39(12): 56-61.[14] 伦淑娴,林健,姚显双.基于小世界回声状态网的时间序列预测[J].自动化学报,2015,34(7): 90-94.
[15] 朱乔木,党杰,陈金富,等.基于深度置信网络的电力系统暂态稳定评估方法[J].中国电机工程学报, 2018,38(03): 735-743.
[16] JORDAN M I.Serial order:a parallel distributed processing approach[J].Advanced in Psychology,1997,121(4):471-495.
[17] HOCHREITER S,BENGIO Y,FRASCONI P,et al. Gradient flow in recurrent nets: the difficulty of learning long-term dependencies[C]//A field Guide to Dynamical Recurrent Networks, Wiley-IEEE Press, 2001: 237-243.
[18] GRAVES A.Supervised sequence labeling with recurrent neural networks[D].Ph.D Dissertation.Manno. Switzerland: Technical University of Munich, 2008.
[19] Bengio Y,Simard P,Frasconi P.Learning long-term dependencies with gradient descent is difficult[J].IEEE Trans on Neural Networks,1994,5(2):157-166.
[20] Chang F, Chang C, Huang H, et al. Real-time recurrent learning network for stream-flow forecasting[J]. Hydrological Processes,2002,16(13):2577-2588.
[21] 杜明建.大数据技术在负荷预测与负荷特性分析中的应用[D].南京:东南大学, 2015.
[22] 万志宏.基于时间序列的电力系统短期负荷预测研究[D].广州:华南理工大学, 2012.

相似文献/References:

[1]贺 剑.基于改进的灰色理论在中长期电力负荷预测中的应用[J].工业仪表与自动化装置,2014,(05):100.
　HE Jian.Prediction model for medium and long term electric load based on improved grey theory[J].Industrial Instrumentation & Automation,2014,(01):100.
[2]张明光,周　君.含电动汽车及光伏发电的微电网控制策略研究[J].工业仪表与自动化装置,2015,(06):113.
　ZHANG Mingguang,ZHOU Jun.A control strategy study for electric vehicles and PV in microgrid[J].Industrial Instrumentation & Automation,2015,(01):113.
[3]朱春颖,沈海军,吴晓飞,等.电动汽车智能有序充电模式[J].工业仪表与自动化装置,2016,(04):75.
　ZHU Chunying,SHEN Haijun,WU Xiaofei,et al.The electric car orderly intelligent charging mode[J].Industrial Instrumentation & Automation,2016,(01):75.
[4]郭松林,水泉龙,顾翔瑜.灰色系统理论在负荷预测中运用综述[J].工业仪表与自动化装置,2017,(03):24.
　GUO Songlin,SHUI Quanlong,GU Xiangyu.Summary of application of gray system theory in load forecasting[J].Industrial Instrumentation & Automation,2017,(01):24.
[5]李伟生,张继龙,漆建平.基于动态分时电价的电动汽车有序充放电研究[J].工业仪表与自动化装置,2017,(04):46.
　LI Weisheng,ZHANG Jilong,QI Jianping.A dynamic time-of-use price based order for charging and discharging of electric vehicles[J].Industrial Instrumentation & Automation,2017,(01):46.
[6]李万敏,李新勇,王 彦,等.电动汽车永磁同步电机控制策略研究[J].工业仪表与自动化装置,2018,(03):30.[doi:1000-0682（2018）03-0000-00]
　LI Wanmin,LI Xinyong,WANG Yan,et al.Research on control strategy on permanent magnet synchronous motor for electric vehicle[J].Industrial Instrumentation & Automation,2018,(01):30.[doi:1000-0682（2018）03-0000-00]
[7]邓孝祥,王鑫鑫,李 鹏,等.超级电容器储能在电动汽车中的应用研究[J].工业仪表与自动化装置,2018,(06):48.[doi:1000-0682（2018）06-0000-00]
　DENG Xiaoxiang,WANG Xinxin,LI Peng,et al.Research on the application of super capacitor energy storage in electric vehicle[J].Industrial Instrumentation & Automation,2018,(01):48.[doi:1000-0682（2018）06-0000-00]
[8]高敬更,李 项,张勇红,等.基于PSO算法的电动汽车电能计量优化[J].工业仪表与自动化装置,2019,(02):49.[doi:1000-0682(2019)02-0000-00]
　GAO Jinggeng,LI Xiang,ZHANG Yonghong,et al.An electric vehicle energy metering optimization based on particle swarm optimization[J].Industrial Instrumentation & Automation,2019,(01):49.[doi:1000-0682(2019)02-0000-00]
[9]高敬更,王 琨,王兴贵,等.一种电动汽车充电站三相电压自动平衡充电系统[J].工业仪表与自动化装置,2019,(04):27.[doi:1000-0682(2019)04-0000-00]
　GAO Jinggeng,WANG Kun,WANG Xinggui,et al.Three-phase voltage automatic balance charging system for electric vehicle charging station[J].Industrial Instrumentation & Automation,2019,(01):27.[doi:1000-0682(2019)04-0000-00]

备注/Memo

备注/Memo:
收稿日期：2018-05-31
基金项目：国网甘肃省电力公司科技项目资助（522722160030）
作者简介：王琨(1988)，男，江苏徐州人，硕士，电力工程师，研究方向为电力系统及其自动化。
更新日期/Last Update: 2019-01-15