基于DWT-MOSMA-SVM的多目标优化短期母线负荷预测

doi:10.12204/j.issn.1000-7229.2023.03.005

电力建设 ›› 2023, Vol. 44 ›› Issue (3): 49-55.doi: 10.12204/j.issn.1000-7229.2023.03.005

• 新型电力系统下配电网规划与运行优化关键技术研究及应用·栏目主持王守相教授、赵倩宇博士· • 上一篇下一篇

基于DWT-MOSMA-SVM的多目标优化短期母线负荷预测

陈逸枞(), 张大海(), 李宇欣(), 王颖()

北京交通大学电气工程学院,北京市 100044

收稿日期:2022-03-11 出版日期:2023-03-01 发布日期:2023-03-02
通讯作者: 张大海 E-mail:20126123@bjtu.edu.cn;dhzhang1@bjtu.edu.cn;21121453@bjtu.edu.cn;wangying1@bjtu.edu.cn
作者简介:陈逸枞(1998),男,硕士研究生,主要研究方向为电力系统负荷及母线预测,E-mail:20126123@bjtu.edu.cn
李宇欣(1999),女,硕士研究生,主要研究方向为电力系统监控,E-mail:21121453@bjtu.edu.cn
王颖(1992),女,博士,高聘副教授,主要研究方向为韧性电网、配电网故障恢复、电力系统优化等,E-mail: wangying1@bjtu.edu.cn
基金资助:
国家自然科学基金青年基金项目(52107067)

Multi-Objective Optimization Based on DWT-MOSMA-SVM for Short-Term Bus Load Forecasting

CHEN Yicong(), ZHANG Dahai(), LI Yuxin(), WANG Ying()

School of Electrical Engineering, Beijing Jiaotong University, Beijing 100044, China

Received:2022-03-11 Online:2023-03-01 Published:2023-03-02
Contact: ZHANG Dahai E-mail:20126123@bjtu.edu.cn;dhzhang1@bjtu.edu.cn;21121453@bjtu.edu.cn;wangying1@bjtu.edu.cn
Supported by:
National Natural Science Foundation Youth Fund Program(52107067)

摘要/Abstract

摘要：

母线负荷基数小,波动性和不确定性大,随着光伏、风电等可再生能源的接入,母线负荷受天气等随机性因素的影响增加,母线负荷的高精度预测受到很大影响。针对小样本场景下母线负荷预测问题,提出了一种基于离散小波变换-多目标黏菌算法-支持向量机 (discrete wavelet transformation-multiple objective slime mould algorithm-support vector machine, DWT-MOSMA-SVM)的多目标优化短期母线负荷预测方法。首先采用离散小波变换对母线负荷数据进行处理;然后兼顾预测的精度和稳定性两个目标函数,采用多目标黏菌算法对支持向量机的惩罚因子和核函数参数进行优化;最后在优化所得的Pareto前沿面上选择Pareto最优解,以此搭建支持向量机(support vector machine, SVM)预测模型进行训练,并将预测结果与长短期记忆网络(long short-term memory, LSTM)、未优化的SVM以及多目标黏菌算法(multi-objective slime mold algorithm, MOSSA)优化的SVM模型预测结果进行对比。实验结果表明,提出的MOSMA-SVM模型的预测精度和稳定性更佳。

关键词: 母线负荷预测, 支持向量机(SVM), 多目标黏菌算法(MOSMA), 多目标优化

Abstract:

The bus load has small base, high volatility and uncertainty. With the access of renewable energy such as photovoltaic and wind power, the bus load is increasingly disturbed by random factors such as weather, and high precision forecasting of bus load is greatly affected. Aiming at the problem of bus load forecasting in small-sample scenario, this paper proposes a short-term bus load forecasting method based on discrete wavelet transformation-multiple objective slime mould algorithm-support vector machine (DWT-MOSMA-SVM). Firstly, discrete wavelet transform is used to process bus load data. Then giving consideration to the accuracy and stability of the forecasting, multiple-objective slime mold algorithm (MOSMA) is used to optimize the penalty factor and kernel function parameters of SVM. Finally, selecting the Pareto optimal solution on the Pareto front, SVM forecasting model is built for training. The forecasting results are compared with those of LSTM, un-optimized SVM and MOSSA-optimized SVM model. Experimental results show that the proposed MOSMA-SVM model has better forecasting accuracy and stability.

Key words: bus load forecasting, support vector machine (SVM), multiple-objective slime mould algorithm (MOSMA), multi-objective optimization

中图分类号:

TM715

陈逸枞, 张大海, 李宇欣, 王颖. 基于DWT-MOSMA-SVM的多目标优化短期母线负荷预测[J]. 电力建设, 2023, 44(3): 49-55.

CHEN Yicong, ZHANG Dahai, LI Yuxin, WANG Ying. Multi-Objective Optimization Based on DWT-MOSMA-SVM for Short-Term Bus Load Forecasting[J]. ELECTRIC POWER CONSTRUCTION, 2023, 44(3): 49-55.

图/表 6

图1 MOSMA优化流程图

Fig.1 Flow chart of MOSMA optimization

图2 十天母线负荷曲线

Fig.2 10-days bus load curve

图3 离散小波变换分解图

Fig.3 DWT decomposition diagram

表1 参数优化表

Table 1 Parameter optimization table

图4 母线负荷日前预测曲线

Fig.4 Daily forecast curve of bus load

表2 预测误差表

Table 2 Forecasting error table

参考文献 18

[1]	范士雄, 刘幸蔚, 於益军, 等. 基于多源数据和模型融合的超短期母线负荷预测方法[J]. 电网技术, 2021, 45(1): 243-250.
	FAN Shixiong, LIU Xingwei, YU Yijun, et al. Multi-source data and hybrid neural network based ultra-short-term bus load forecasting[J]. Power System Technology, 2021, 45(1): 243-250.
[2]	熊图, 赵宏伟, 陈明辉, 等. 基于特征排序与深度学习的母线负荷预测方法[J]. 可再生能源, 2019, 37(10): 1511-1517.
	XIONG Tu, ZHAO Hongwei, CHEN Minghui, et al. Bus load forecasting based on feature ranking and deep learning[J]. Renewable Energy Resources, 2019, 37(10): 1511-1517.
[3]	刘文杰, 刘禾, 王英男, 等. 基于完整自适应噪声集成经验模态分解的LSTM-Attention网络短期电力负荷预测方法[J]. 电力建设, 2022, 43(2): 98-108. doi: 10.12204/j.issn.1000-7229.2022.02.012
	LIU Wenjie, LIU He, WANG Yingnan, et al. Short-term power load forecasting method based on CEEMDAN and LSTM-attention network[J]. Electric Power Construction, 2022, 43(2): 98-108. doi: 10.12204/j.issn.1000-7229.2022.02.012
[4]	唐戈, 余一平, 秦川, 等. 基于CNN-LSTM分位数回归的母线负荷日前区间预测[J]. 电力工程技术, 2021, 40(4): 123-129.
	TANG Ge, YU Yiping, QIN Chuan, et al. Day-ahead interval prediction of bus load based on CNN-LSTM quantile regression[J]. Electric Power Engineering Technology, 2021, 40(4): 123-129.
[5]	鲁斌, 霍泽健, 俞敏. 基于LSTNet-Skip的综合能源系统多元负荷超短期预测[J/OL]. 中国电机工程学报. [2022-03-11]. https://kns.cnki.net/kcms/detail/11.2107.tm.20220410.1832.003.html.
	LU Bin, HUO Zejian, YU Min. Multi load ultra short-term forecasting of integrated energy system based on LSTNet-skip[J/OL]. Proceedings of the CSEE. [2022-03-11]. https://kns.cnki.net/kcms/detail/11.2107.tm.20220410.1832.003.html.
[6]	LIN G Q. An improved moth-flame optimization algorithm for support vector machine prediction of photovoltaic power generation[J]. Journal of Cleaner Production, 2020, 253: 119966. doi: 10.1016/j.jclepro.2020.119966 URL
[7]	刘波, 秦川, 鞠平, 等. 基于XGBoost与Stacking模型融合的短期母线负荷预测[J]. 电力自动化设备, 2020, 40(3): 147-153.
	LIU Bo, QIN Chuan, JU Ping, et al. Short-term bus load forecasting based on XGBoost and Stacking model fusion[J]. Electric Power Automation Equipment, 2020, 40(3): 147-153.
[8]	任建吉, 位慧慧, 邹卓霖, 等. 基于CNN-BiLSTM-Attention的超短期电力负荷预测[J]. 电力系统保护与控制, 2022, 50(8): 108-116.
	REN Jianji, WEI Huihui, ZOU Zhuolin, et al. Ultra-short-term power load forecasting based on CNN-BiLSTM-Attention[J]. Power System Protection and Control, 2022, 50(8): 108-116.
[9]	陈梓行, 金涛, 郑熙东, 等. 基于新型日期映射法和ISGU混合模型的短期电力负荷预测[J]. 电力系统保护与控制, 2022, 50(15): 72-80.
	CHEN Zixing, JIN Tao, ZHENG Xidong, et al. Short-term power load forecasting based on a new date mapping method and an ISGU hybrid model[J]. Power System Protection and Control, 2022, 50(15): 72-80.
[10]	狄曙光, 刘峰, 孙建宇, 等. 基于改进ABC和IDPC-MKELM的短期电力负荷预测[J]. 智慧电力, 2022, 50(9): 74-81.
	DI Shuguang, LIU Feng, SUN Jianyu, et al. Short term power load forecasting based on improved ABC and IDPC-MKELM[J]. Smart Power, 2022, 50(9): 74-81.
[11]	张淑清, 李君, 姜安琦, 等. 基于FPA-VMD和BiLSTM神经网络的新型两阶段短期电力负荷预测[J]. 电网技术, 2022, 46(8): 3269-3279.
	ZHANG Shuqing, LI Jun, JIANG Anqi, et al. A novel two-stage model based on FPA-VMD and BiLSTM neural network for short-term power load forecasting[J]. Power System Technology, 2022, 46(8): 3269-3279.
[12]	刘可真, 阮俊枭, 赵现平, 等. 基于麻雀搜索优化的Attention-GRU短期负荷预测方法[J]. 电力系统及其自动化学报, 2022, 34(4): 99-106.
	LIU Kezhen, RUAN Junxiao, ZHAO Xianping, et al. Short-term load forecasting method based on sparrow search optimized attention-GRU[J]. Proceedings of the CSU-EPSA, 2022, 34(4): 99-106.
[13]	吴松梅, 蒋建东, 燕跃豪, 等. 基于VMD-PSO-多核极限学习机的短期负荷预测[J]. 电力系统及其自动化学报, 2022, 34(5): 18-25.
	WU Songmei, JIANG Jiandong, YAN Yuehao, et al. Short-term load forecasting based on VMD-PSO-MKELM method[J]. Proceedings of the CSU-EPSA, 2022, 34(5): 18-25.
[14]	赵佩, 代业明. 基于实时电价和加权灰色关联投影的SVM电力负荷预测[J]. 电网技术, 2020, 44(4): 1325-1332.
	ZHAO Pei, DAI Yeming. Power load forecasting of SVM based on real-time price and weighted grey relational projection algorithm[J]. Power System Technology, 2020, 44(4): 1325-1332.
[15]	唐捷, 杨银, 刘斯亮, 等. 基于改进SVM与NSGA-Ⅲ的台区相序在线优化方法[J]. 电力系统自动化, 2022, 46(3): 50-58.
	TANG Jie, YANG Yin, LIU Siliang, et al. On-line optimization method for phase sequence in station area based on improved support vector machine and non-dominated sorting genetic algorithm-Ⅲ[J]. Automation of Electric Power Systems, 2022, 46(3): 50-58.
[16]	LI S M, CHEN H L, WANG M J, et al. Slime mould algorithm: A new method for stochastic optimization[J]. Future Generation Computer Systems, 2020, 111: 300-323. doi: 10.1016/j.future.2020.03.055 URL
[17]	刘爱国, 薛云涛, 胡江鹭, 等. 基于GA优化SVM的风电功率的超短期预测[J]. 电力系统保护与控制, 2015, 43(2): 90-95.
	LIU Aiguo, XUE Yuntao, HU Jianglu, et al. Ultra-short-term wind power forecasting based on SVM optimized by GA[J]. Power System Protection and Control, 2015, 43(2): 90-95.
[18]	PREMKUMAR M, JANGIR P, SOWMYA R, et al. MOSMA: multi-objective slime mould algorithm based on elitist non-dominated sorting[J]. IEEE Access, 2020, 9: 3229-3248. doi: 10.1109/ACCESS.2020.3047936 URL

基于DWT-MOSMA-SVM的多目标优化短期母线负荷预测

Multi-Objective Optimization Based on DWT-MOSMA-SVM for Short-Term Bus Load Forecasting

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 18

相关文章 15

编辑推荐

Metrics

本文评价

[1]	任鑫芳, 张志朝, 许李天伦, 王诗超, 刘展志, 许方圆. 计及电动汽车与温控负荷需求响应的分层能源系统优化调度[J]. 电力建设, 2022, 43(9): 77-86.
[2]	徐艳春, 张进, 汪平, MI Lu. 考虑配电网静态电压稳定性的微电网优化配置[J]. 电力建设, 2022, 43(8): 87-101.
[3]	金国锋, 邢敬舒, 张林, 张秀路, 赵立军, 刘自发, 丛彪. 考虑用户舒适度的蓄热式电采暖参与风电消纳的多目标优化[J]. 电力建设, 2022, 43(3): 12-21.
[4]	邢超, 奚鑫泽, 何廷一, 李胜男, 刘明群. 计及风电调频的备用容量滚动优化方法[J]. 电力建设, 2022, 43(2): 117-125.
[5]	檀勤良, 郭明鑫, 刘源, 韩健, 梅书凡, 丁毅宏. 基于大规模V2G的区域电源低碳优化策略[J]. 电力建设, 2022, 43(12): 56-65.
[6]	陈睿彬, 陆玲霞, 包哲静, 于淼. 电池储能系统参与用户侧削峰填谷的鲁棒优化调度策略[J]. 电力建设, 2022, 43(10): 66-76.
[7]	胡戎, 邱晓燕, 张志荣. 计及无功裕度的配电网两阶段无功优化调度策略[J]. 电力建设, 2021, 42(9): 129-139.
[8]	陈伟, 路源, 何欣, 张海龙, 杨勇, 崔建斌. 计及风光就地消纳的设施农业产业园区综合能源系统多目标优化调度方法[J]. 电力建设, 2021, 42(7): 20-27.
[9]	匡萃浙, 张勇军, 王群, 邹舟诣奥. 基于区域能源中心的居民电——热用能多目标优化[J]. 电力建设, 2021, 42(2): 58-67.
[10]	檀勤良, 丁毅宏, 李渝, 李锐. 考虑经济环境平衡的风光火联合外送调度策略多目标优化[J]. 电力建设, 2020, 41(8): 129-136.
[11]	方朝雄，吴晓升，江岳文. 考虑暂态稳定性的网储多目标双层优化[J]. 电力建设, 2020, 41(7): 58-66.
[12]	魏震波，任小林，黄宇涵. 考虑综合需求侧响应的区域综合能源系统多目标优化调度[J]. 电力建设, 2020, 41(7): 92-99.
[13]	杨蕾，吴琛，黄伟，郭成，向川，何鑫，邢超，奚鑫泽，周鑫，杨博，张孝顺. 含高比例风光新能源电网的多目标无功优化算法[J]. 电力建设, 2020, 41(7): 100-109.
[14]	沈青文，程若发，付鑫. 一种计及脆弱性指标的分布式电源优化配置方法[J]. 电力建设, 2020, 41(3): 54-61.
[15]	张军六，樊伟，谭忠富，鞠立伟，德格吉日夫，杨莘博，孙婧霞. 计及需求响应的气电互联虚拟电厂多目标调度优化模型[J]. 电力建设, 2020, 41(2): 1-10.