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

doi:10.12204/j.issn.1000-7229.2023.03.005

Abstract

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

CLC Number:

TM715

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.

Figures/Tables 6

Fig.1 Flow chart of MOSMA optimization

Fig.2 10-days bus load curve

Fig.3 DWT decomposition diagram

Table 1 Parameter optimization table

Fig.4 Daily forecast curve of bus load

Table 2 Forecasting error table

References 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