基于深度循环神经网络的地铁供电系统负荷预测*

doi:10.11985/2022.04.033

摘要/Abstract

摘要：

随着国民经济持续发展、城市化进程加快，地铁建设也随之快速发展，地铁供电系统也相应地日益庞大，地铁供电系统负荷已然成为城市电力系统负荷的重要组成部分。由于地铁供电系统负荷所呈现的移动性、时变性、非线性等特点，对地铁供电系统负荷预测技术的研究越来越重要。首先对于地铁供电系统负荷预测开展研究，考虑了地铁历史负荷、地铁换乘站、地铁地上/地下形式、客流量、天气、温度等多维度因素，再基于堆叠式降噪自动编码器对多维度因素进行特征学习，基于适用于处理序列性质非线性问题的深度循环神经网络，提出了一种地铁供电系统负荷预测方法。最后通过南京地铁的实际运行数据验证了所提预测方法的有效性和优越性，该方法对于地铁供电系统短期和中长期负荷预测均有较好的预测效果。针对南京地铁待建的地铁站，进行中长期负荷预测，为其主站定容提供参考依据。

关键词: 地铁供电系统, 负荷预测, 深度学习, 多维度因素, 深度循环神经网络

Abstract:

With the continuous development of China’s national economy and the acceleration of urbanization, the construction of subway is developing rapidly, and the power supply system of subway is also growing correspondingly. The load of the power supply system of subway has become an important part of the load of the urban power system. Due to the characteristics of mobility, time-varying and non-linearity of the load of the metro power supply system, the research on the load prediction technology of the metro power supply system is becoming more and more important. Firstly, the load prediction of the subway power supply system is studied, and the multi-dimensional factors such as subway historical load, subway transfer station, subway over-ground/underground form, passenger flow, weather, temperature are considered. Then, the feature learning of the multi-dimensional factors is carried out based on the stacked denoising autoencoders. Based on the deep recurrent neural network which is suitable for dealing with nonlinear problems of sequence properties, a load prediction method of the subway power supply system is proposed. Finally, the actual operation data of Nanjing metro proves the effectiveness and superiority of the prediction method is proposed, and the method has good effect on short term and medium-long term load forecast of metro power supply system. The medium and long term load prediction is carried out for the subway station to be built in Nanjing, which provides reference for the capacity regulation of the main station.

Key words: Subway power supply system, load forecasting, deep learning, multidimensional factor, deep recurrent neural network

中图分类号:

TM744

刘江涛, 延巧娜, 周涛, 邵雷, 陈中. 基于深度循环神经网络的地铁供电系统负荷预测^*[J]. 电气工程学报, 2022, 17(4): 309-317.

LIU Jiangtao, YAN Qiaona, ZHOU Tao, SHAO Lei, CHEN Zhong. Load Forecasting of Metro Power Supply System Based on Deep Recurrent Neural Network[J]. Journal of Electrical Engineering, 2022, 17(4): 309-317.

图/表 13

图1

图2

图3

图4

图5

图6

图7

图8

图9

表1

图10

表2

图11

参考文献 28

[1]	龚孟荣. 地铁供电系统设计及仿真研究[D]. 成都: 西南交通大学, 2013.
	GONG Mengrong. Design and simulation of metro power supply system[D]. Chengdu: Southwest Jiaotong University, 2013.
[2]	李家旭. 地铁车站负荷计算方法的探讨[J]. 科技创新与应用, 2017(20):77-78.
	LI Jiaxu. Discussion on the load calculation method of metro station[J]. Science and Technology Innovation and Application, 2017(20):77-78.
[3]	崔洪敏, 刘炜, 李鲲鹏, 等. 城市轨道交通牵引变电所负荷过程及概率特性研究[J]. 城市轨道交通研究, 2019, 22(7):33-37.
	CUI Hongmin, LIU Wei, LI Kunpeng, et al. Study on load process and probability characteristics of traction substation of urban rail transit[J]. Urban Rail Transit Research, 2019, 22(7):33-37.
[4]	徐舒. 南京地铁牵引供电系统负荷建模与仿真及其对电网影响分析[D]. 南京: 东南大学, 2006.
	XU Shu. Load modeling and simulation of traction power supply system in Nanjing metro and analysis of its influence on power grid[D]. Nanjing: Southeast University, 2006.
[5]	FAN G F, PENG L L, HONG W C. Short term load forecasting based on phase space reconstruction algorithm and bi-square kernel regression model[J]. Applied Energy, 2018(34):224-232.
[6]	ZHANG J L, WEI Y M, LI D Z, et al. Short term electricity load forecasting using a hybrid model[J]. Energy, 2018(46):158-167.
[7]	彭鹏, 彭佳红. 基于多元线性回归模型的电力负荷预测研究[J]. 中国安全生产科学技术, 2011, 7(9):158-161.
	PENG Peng, PENG Jiahong. Research on the prediction of power load based on multiple linear regression model[J]. Journal of Safety Science and Technology, 2011, 7(9):158-161.
[8]	张俊芳, 吴伊昂, 吴军基. 基于灰色理论负荷预测的应用研究[J]. 电力自动化设备, 2004(5):24-27.
	ZHANG Junfang, WU Yiang, WU Junji. Application of gray system theory in load forecasting[J]. Electric Power Automation Equipment, 2004(5):24-27.
[9]	黄伟, 费维刚, 王炳革, 等. 模糊理论在中长期负荷预测中的应用[J]. 电力系统及其自动化学报, 1999(4):25-29.
	HUANG Wei, FEI Weigang, WANG Bingge, et al. The application and medium of fuzzy theory in the long term load forecasting[J]. Proceedings of the CSU-EPSA, 1999(4):25-29.
[10]	王新, 孟玲玲. 基于EEMD-LSSVM的超短期负荷预测[J]. 电力系统保护与控制, 2015, 43(1):61-66.
	WANG Xin, MENG Lingling. Super-short-term load prediction based on EEMD-LSSVM[J]. Power System Protection and Control, 2015, 43(1):61-66.
[11]	张刚, 刘福潮, 王维洲, 等. 电网短期负荷预测的BP-ANN方法及应用[J]. 电力建设, 2014, 35(3):54-58. doi: 10.3969/j.issn.1000－7229.2014.03.010
	ZHANG Gang, LIU Fuchao, WANG Weizhou, et al. BP-ANN method and its application for short-term load prediction of power grid[J]. Electric Power Construction, 2014, 35(3):54-58. doi: 10.3969/j.issn.1000－7229.2014.03.010
[12]	吴元香. 基于遗传算法的电力负荷预测[J]. 科技信息, 2013(6):472.
	WU Yuanxiang. Power load prediction based on genetic algorithm[J]. Science and Technology Information, 2013(6):472.
[13]	BASHIR Z A, EL-HAWARY M E. Applying wavelets to short-term load forecasting using PSO-based neural networks[J]. IEEE Transactions on Power Systems, 2009, 24(1):20-27. doi: 10.1109/TPWRS.2008.2008606
[14]	宋晓辉, 白晓民, 易俗. 一种考虑负荷特性变化的改进线性回归负荷预测法[J]. 供用电, 2006(1):23-26.
	SONG Xiaohui, BAI Xiaomin, YI Su. An improved linear regression load prediction method considering the variation of load characteristics[J]. Power Supply and Consumption, 2006(1):23-26.
[15]	马婉贞, 杜斌. 基于改进灰色理论的中长期负荷预测方法研究[J]. 智能城市, 2019, 5(23):20-21.
	MA Wanzhen, DU Bin. Research on medium and long term load forecasting method based on improved grey theory[J]. Smart City, 2019, 5(23):20-21.
[16]	陈志巧. 基于模糊理论的电力负荷预测研究[J]. 山东科技大学学报, 2006(2):81-83.
	CHEN Zhiqiao. Research on power load prediction based on fuzzy theory[J]. Journal of Shandong University of Science and Technology, 2006(2):81-83.
[17]	杨治中. 地铁供电系统安装工程的施工管理[J]. 集成电路应用, 2020, 37(11):176-177.
	YANG Zhizhong. Construction management of subway power supply system installation project[J]. Integrated Circuit Application, 2020, 37(11):176-177.
[18]	孟新心. 轨道交通供电系统智能运维平台研究与应用[J]. 电气化铁道, 2020, 31(S1):94-96.
	MENG Xinxin. Research and application of intelligent operation and maintenance platform for rail transit power supply system[J]. Electric Railway, 2020, 31(S1):94-96.
[19]	于松伟, 杨兴山. 城市轨道交通供电系统设计原理与应用[M]. 成都: 西南交通大学出版社, 2008.
	YU Songwei, YANG Xingshan. Design principle and application of urban rail transportation power supply system[M]. Chengdu: Southwest Jiaotong University Press, 2008.
[20]	欧阳慧林. 城市轨道交通供电方案研究[J]. 广东输电与变电技术, 2009, 11(5):64-67.
	OUYANG Huilin. Study on power supply scheme of urban rail transit[J]. Guangdong Power Transmission and Transformation Technology, 2009, 11(5):64-67.
[21]	杨亚兵. 地铁供电系统中的并行送电技术探讨[J]. 智能城市, 2020, 6(13):73-74.
	YANG Yabing. Discussion on parallel power transmission technology in metro power supply system[J]. Smart City, 2020, 6(13):73-74.
[22]	谭丽娜, 白冰. 城市轨道交通供电系统浅析[J]. 教育教学论坛, 2012(36):190-191.
	TAN Lina, BAI Bing. Analysis of power supply system of urban rail transit[J]. Education and Teaching Forum, 2012(36):190-191.
[23]	黄胜德, 张巍. 地下铁道供电[M]. 北京: 中国电力出版社, 2009.
	HUANG Shengde, ZHANG Wei. Underground railway power supply[M]. Beijing: China Electric Power Press, 2009.
[24]	李光蕊. 北京地铁负荷建模及其对城市配电网影响的分析[D]. 北京: 北京交通大学, 2015.
	LI Guangrui. Modeling of metro load in Beijing and its impact on urban distribution network[D]. Beijing: Beijing Jiaotong University, 2015.
[25]	张惠茹, 贾利民, 王莉, 等. 面向列车节能控制的时刻表优化[J]. 铁道学报, 2019, 41(2):8-15.
	ZHANG Huiru, JIA Limin, WANG Li, et al. Study of timetable optimization based on train enemy saving control[J]. Journal of the China Railway Society, 2019, 41(2):8-15.
[26]	胡海涛, 郑政, 何正友, 等. 交通能源互联网体系架构及关键技术[J]. 中国电机工程学报, 2018, 38(1):12-24,339.
	HU Haitao, ZHENG Zheng, HE Zhengyou, et al. Transportation and energy Internet architecture and key technologies[J]. Proceedings of the CSEE, 2018, 38(1):12-24,339.
[27]	常金蓉. 轨道交通供电系统牵引负荷建模及其电能质量评估方法[D]. 兰州: 兰州理工大学, 2020.
	CHANG Jinrong. Traction load modeling and power quality evaluation method of rail transit power supply system[D]. Lanzhou: Lanzhou University of Technology, 2020.
[28]	ZHANG Zehan, JIANG Teng, LI Shuanghong, et al. Automated feature learning for nonlinear process monitoring:An approach using stacked denoising autoencoder and k-nearest neighbor rule[J]. Journal of Process Control, 2018, 64:49-61. doi: 10.1016/j.jprocont.2018.02.004