基于DE-GWO-SVR的中长期电力需求预测

doi:10.11930/j.issn.1004-9649.202105016

中国电力 ›› 2021, Vol. 54 ›› Issue (9): 83-88.DOI: 10.11930/j.issn.1004-9649.202105016

基于DE-GWO-SVR的中长期电力需求预测

张运厚¹, 李婉莹², 董福贵²

1. 国家电网有限公司东北分部，辽宁沈阳 110180;
2. 华北电力大学经济与管理学院，北京 102206

收稿日期:2021-05-07 修回日期:2021-07-27 发布日期:2021-09-14
作者简介:张运厚(1965-),男,高级工程师,从事电网规划研究,E-mail:zhangyunhou@126.com;李婉莹(1996-),女,通信作者,硕士研究生,从事能源管理理论与方法研究,E-mail:lwy1016@yeah.net;董福贵(1974-),男,博士,教授,从事能源管理理论与方法研究,E-mail:dfg@yeah.net
基金资助:
国家社会科学基金项目(配额制实施背景下面向区域差异的新能源发展战略研究，19BJY074)

Medium and Long-Term Power Demand Forecasting Based on DE-GWO-SVR

ZHANG Yunhou¹, LI Wanying², DONG Fugui²

1. Northeast Branch of State Grid Corporation of China, Shenyang 110180, China;
2. School of Economics and Management, North China Electric Power University, Beijing 102206, China

Received:2021-05-07 Revised:2021-07-27 Published:2021-09-14
Supported by:
This work is supported by Chinese National Funding of Social Sciences (Research on New Energy Development Strategy Facing Regional Differences Under the Background of Renewable Portfolio Standard Implementation, No.19BJY074)

摘要/Abstract

摘要： 电力需求预测是电力系统科学规划与运行的重要前提。根据相关性分析，从经济发展水平、城镇化水平、工业化水平、人口数量、产业结构、居民消费水平、电价和用电基数8个方面筛选出电力需求关键影响因素。利用差分进化（differential evolution，DE）和灰狼优化（grey wolf optimization，GWO）算法对支持向量回归模型（support vector regression，SVR）的参数进行优化，建立差分进化-灰狼优化-支持向量回归电力需求预测模型。选取北京市电力需求历史数据进行实证分析，比较不同模型的预测结果，验证组合优化模型的有效性及其预测的准确率，并对北京市2021—2025年电力需求进行预测。

关键词: 电力需求预测, 差分进化, 灰狼优化算法, 支持向量回归

Abstract: Power demand forecasting is an important prerequisite for the scientific planning and operation of power systems. According to the results of the correlation analysis, the key influencing factors of power demand are selected from eight aspects: economic development level, urbanization level, industrialization level, population size, industrial structure, household consumption level, electricity price and electricity base. Using differential evolution (DE) and grey wolf optimization (GWO) algorithms to optimize the parameters of the support vector regression (SVR), the power demand forecasting model is established. Based on the historical data of power demand in Beijing, this paper makes an empirical analysis, compares the prediction results of different models, verifies the effectiveness of the combined optimization model and the accuracy of prediction, forecasts the power demand of Beijing from 2021 to 2025.

Key words: power demand forecasting, differential evolution, grey wolf optimization algorithm, support vector machine

张运厚, 李婉莹, 董福贵. 基于DE-GWO-SVR的中长期电力需求预测[J]. 中国电力, 2021, 54(9): 83-88.

ZHANG Yunhou, LI Wanying, DONG Fugui. Medium and Long-Term Power Demand Forecasting Based on DE-GWO-SVR[J]. Electric Power, 2021, 54(9): 83-88.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202105016

https://www.electricpower.com.cn/CN/Y2021/V54/I9/83

参考文献

[1] HE Y X, JIAO J, CHEN Q, et al. Urban long term electricity demand forecast method based on system dynamics of the new economic normal: The case of Tianjin[J]. Energy, 2017, 133: 9-22.
[2] 章江. 时间序列预测方法及其在电力系统中的应用[D]. 长沙: 湖南大学, 2018.
ZHANG Jiang. Time series forecasting method and its application in power system[D]. Changsha: Hunan University, 2018.
[3] XU N, DANG Y G, GONG Y D. Novel grey prediction model with nonlinear optimized time response method for forecasting of electricity consumption in China[J]. Energy, 2017, 118: 473-480.
[4] 石玉恒, 赵娜, 王凌, 等. 北京地区日最大电力负荷预测模型初探[J]. 中国电力, 2019, 52(8): 157-163
SHI Yuheng, ZHAO Na, WANG Ling, et al. Study on forecasting model of maximum daily power load in Beijing area[J]. Electric Power, 2019, 52(8): 157-163
[5] 李震, 张思, 任娴婷, 等. 基于数据驱动的线性聚类ARIMA长期电力负荷预测[J]. 科学技术与工程, 2020, 20(16): 6497-6504
LI Zhen, ZHANG Si, REN Xianting, et al. Long-term power load forecasting based on data-driven linear clustering ARIMA[J]. Science Technology and Engineering, 2020, 20(16): 6497-6504
[6] 邢晓敏, 何铁新, 郑雪瑞, 等. 基于ANN-dropout的配电网可靠性预测方法[J]. 南方电网技术, 2019, 13(2): 66-73
XING Xiaomin, HE Tiexin, ZHENG Xuerui, et al. Reliability prediction method of distribution network based on ANN-dropout[J]. Southern Power System Technology, 2019, 13(2): 66-73
[7] YANG Y L, CHE J X, DENG C Z, et al. Sequential grid approach based support vector regression for short-term electric load forecasting[J]. Applied Energy, 2019, 238: 1010-1021.
[8] LIANG H B, ZOU J L, LI Z L, et al. Dynamic evaluation of drilling leakage risk based on fuzzy theory and PSO-SVR algorithm[J]. Future Generation Computer Systems, 2019, 95: 454-466.
[9] 田书欣, 周全, 程浩忠, 等. 基于鸽群优化算法的支持向量机在电力需求总量预测中的应用[J]. 电力自动化设备, 2020, 40(5): 173-181
TIAN Shuxin, ZHOU Quan, CHENG Haozhong, et al. Application of pigeon-inspired optimization algorithm based SVM in total power demand forecasting[J]. Electric Power Automation Equipment, 2020, 40(5): 173-181
[10] 海涛, 范恒, 王楷杰, 等. 基于PSO-SVM算法的风电机组结冰故障诊断[J]. 智慧电力, 2021, 49(4): 1-6, 74
HAI Tao, FAN Heng, WANG Kaijie, et al. Icing fault diagnosis of wind turbines based on PSO-SVM algorithm[J]. Smart Power, 2021, 49(4): 1-6, 74
[11] 温珏. 基于改进人工鱼群算法优化参数的支持向量机研究—中长期电力需求预测应用[J]. 软件导刊, 2018, 17(3): 183-186
WEN Jue. Parameter optimization for support vectorm achine based on improved artificial fish swarm algorithm—mid-and-long term power demand forecasting[J]. Software Guide, 2018, 17(3): 183-186
[12] 何忠华. 基于蚁狮优化GM(1, 1)模型的北京市电力需求预测[J]. 现代工业经济和信息化, 2017, 7(22): 57-60, 83
HE Zhonghua. Beijing electricity demand forecast based on ant lion optimizer GM(1, 1) model[J]. Modern Industrial Economy and Informationization, 2017, 7(22): 57-60, 83
[13] 何廷一, 田鑫萃, 李胜男, 等. 基于蜂群算法改进的BP神经网络风电功率预测[J]. 电力科学与技术学报, 2018, 33(4): 22-28
HE Tingyi, TIAN Xincui, LI Shengnan, et al. Improved BP neural network based on Artificial Bee Colony algorithm for wind power prediction[J]. Journal of Electric Power Science and Technology, 2018, 33(4): 22-28
[14] 汤安迪, 韩统, 徐登武, 等. 基于混沌麻雀搜索算法的无人机航迹规划方法[J]. 计算机应用. 2021, 41(7): 2128-2136.
TANG Andi, HAN Tong, XU Dengwu, et al. Path planning method of unmanned aerial vehicle based on chaos sparrow search algorithm[J]. Journal of Computer Applications. 2021, 41(7): 2128-2136.
[15] 范海虹. 基于萤火虫算法的短期电力负荷预测方法[J]. 中国电力, 2021, 54(3): 141-148
FAN Haihong. Short-term power load forecasting method based on glowworm swarm optimization algorithm[J]. Electric Power, 2021, 54(3): 141-148
[16] 戴丽珍, 付涛, 杨刚, 等. 一种改进灰狼算法优化LSSVM的交通流量预测[J]. 小型微型计算机系统, 2020, 41(12): 2672-2676
DAI Lizhen, FU Tao, YANG Gang, et al. Traffic flow prediction method by LSSVM optimized by an improved GWO[J]. Journal of Chinese Computer Systems, 2020, 41(12): 2672-2676
[17] 王凌谊, 王志敏, 钱纹, 等. 适应供给侧结构性改革的中长期负荷预测拓展索洛模型研究[J]. 电力系统保护与控制, 2019, 47(18): 49-59
WANG Lingyi, WANG Zhimin, QIAN Wen, et al. Extended Solow regression model for mid/long-term load forecasting adapted to supply-side structural reform[J]. Power System Protection and Control, 2019, 47(18): 49-59
[18] 黄元生, 胡建军, 蔡雅倩. 基于耦合GPR-PSO的北京地区中长期电力需求预测[J]. 电测与仪表, 2020, 57(2): 74-80
HUANG Yuansheng, HU Jianjun, CAI Yaqian. Medium and long-term power demand forecasting in Beijing based on coupled GPR-PSO[J]. Electrical Measurement & Instrumentation, 2020, 57(2): 74-80
[19] 徐阳. 基于经济新常态的城市电网电量需求预测研究[D]. 北京: 华北电力大学, 2017.
XU Yang. Electricity demand forecast of city power grid based on the new economic normal[D]. Beijing: North China Electric Power University, 2017.
[20] GE T Z, HE K M, KE Q F, et al. Optimized product quantization for approximate nearest neighbor search[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, OR, USA. IEEE, 2013: 2946-2953.
[21] MIRJALILI S, MIRJALILI S M, LEWIS A. Grey wolf optimizer[J]. Advances in Engineering Software, 2014, 69: 46-61.
[22] 张慧, 贺松, 张硕, 等. 基于GWO-SVR的冠心病住院费用预测[J]. 智能计算机与应用, 2020, 10(11): 42-46
ZHANG Hui, HE Song, ZHANG Shuo, et al. Prediction of hospitalization costs for coronary heart disease based on GWO-SVR[J]. Intelligent Computer and Applications, 2020, 10(11): 42-46
[23] 任超. 基于DE-GWO-BP神经网络的电动汽车电池SOC预测[D]. 合肥: 合肥工业大学, 2020.
REN Chao. SOC prediction of ev battery based on DE-GWO-BP neural network[D]. Hefei: Hefei University of Technology, 2020.
[24] 杜尊峰, 邵玄玄, 王晓梅. 基于CP结合DE-GWO-SVR的海上风电基础结构损伤识别[J]. 振动与冲击, 2020, 39(22): 110-118
DU Zunfeng, SHAO Xuanxuan, WANG Xiaomei. Damage identification of an offshore wind turbine foundation based on a CP algorithm combined with the method of DE-GWO-SVR[J]. Journal of Vibration and Shock, 2020, 39(22): 110-118
[25] 李建民, 陈慧, 杨冬芹, 等. 改进GWO优化SVM的服务器性能预测[J]. 计算机工程与设计, 2019, 40(11): 3099-3105, 3163
LI Jianmin, CHEN Hui, YANG Dongqin, et al. Prediction of server performance based on SVM algorithm of improved GWO[J]. Computer Engineering and Design, 2019, 40(11): 3099-3105, 3163

基于DE-GWO-SVR的中长期电力需求预测

Medium and Long-Term Power Demand Forecasting Based on DE-GWO-SVR

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	钟成, 翟迪, 陆阳, 刘晓波, 王心如, 赵雄文. 基于改进灰狼算法的电力管廊覆盖优化技术[J]. 中国电力, 2023, 56(8): 68-76.
[2]	贾宏刚, 王主丁, 岳园园, 严欢, 闫娜, 曹强飞. 微电网调度模型的寻优性能与求解效率改进优化[J]. 中国电力, 2023, 56(6): 107-113,131.
[3]	庄俊, 王德顺, 盖晨昊, 薛金花, 朱红保, 李常刚. 基于约束共识和差分进化的多直流馈入电网紧急控制协调优化[J]. 中国电力, 2023, 56(6): 40-50.
[4]	徐宇颂, 邹山花, 卢先领. 基于特征选择和组合模型的短期电力负荷预测[J]. 中国电力, 2022, 55(7): 121-127.
[5]	陈正雄, 帕孜来·马合木提, 沈玮. 基于改进支持向量回归的IGBT老化预测[J]. 中国电力, 2022, 55(7): 1-10.
[6]	张娜, 任强, 刘广忱, 郭力萍, 李静宇. 基于VMD-GWO-ELMAN的光伏功率短期预测方法[J]. 中国电力, 2022, 55(5): 57-65.
[7]	余潇潇, 宋福龙, 周原冰, 梁海峰. “新基建”对中国“十四五”电力需求和电网规划的影响分析[J]. 中国电力, 2021, 54(7): 11-17.
[8]	谭显东, 刘俊, 徐志成, 姚力, 汲国强, 单葆国. “双碳”目标下“十四五”电力供需形势[J]. 中国电力, 2021, 54(5): 1-6.
[9]	刘宏伟. 基于场路耦合模型与改进差分进化算法的电容隔直装置多目标优化配置[J]. 中国电力, 2020, 53(8): 100-106.
[10]	高文浩, 赵海兵, 殷爽睿, 崔德民, 田怀源, 葛杨, 李晓博, 孙海涛. 考虑负荷虚拟储能特性的商业区储能优化配置[J]. 中国电力, 2020, 53(4): 96-104.
[11]	左智科, 陈国彬, 刘超, 牛培峰. 基于CNGWO-LSSVM的汽轮机热耗率预测模型[J]. 中国电力, 2018, 51(8): 148-153.
[12]	杜忠明, 王雪松. “十三五”中国电力需求水平预测[J]. 中国电力, 2017, 50(9): 11-17.
[13]	田星, 余蕾, 董晓晶, 齐彩娟. 经济新常态下宁夏电力需求分析与展望[J]. 中国电力, 2017, 50(12): 27-32.
[14]	单葆国, 李江涛, 谭显东, 单保平. 经济转型时期电力弹性系数应用[J]. 中国电力, 2017, 50(12): 1-4.
[15]	龙禹, 王小英, 周琪, 姜楠, 罗欣. 考虑不同发展情境的江苏省中长期电力需求预测[J]. 中国电力, 2016, 49(7): 72-76.

模态框（Modal）标题

基于DE-GWO-SVR的中长期电力需求预测

Medium and Long-Term Power Demand Forecasting Based on DE-GWO-SVR

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics