基于IGWO-Attention-GRU的短期电力负荷预测模型

Short-term power load forecasting model based on IGWO-Attention-GRU

徐利美 ¹贺卫华 ¹李远 ¹朱燕芳 ¹续欣莹²

扫码查看

作者信息

1. 国网山西省电力公司电力调度控制中心,太原 030021
2. 太原理工大学电气与动力工程学院,太原 030024
折叠

摘要

为了提高短期电力负荷的预测精度,针对电力负荷序列波动性强、复杂性高的特点,综合考虑气象因素及日期类型的影响,文中提出一种基于改进灰狼优化算法(IGWO)优化Attention-GRU网络的短期电力负荷预测模型.首先,构建Attention-GRU网络;其次,对灰狼优化算法(GWO)进行改进,并利用IGWO寻找Attention-GRU网络的超参数;最后,使用IGWO-Attention-GRU模型在电力负荷数据集上进行实验,并与多种预测模型进行比较.实验结果表明,IGWO-Attention-GRU模型的MAPE、RMSE和MAE值均为各种预测模型中最低,验证了 IGWO-Attention-GRU模型的优越性.

Abstract

In order to improve the accuracy of short-term power load forecasting,a short-term power load forecasting model based on Improved Grey Wolf Optimization(IGWO)algorithm to optimize Attention-GRU network is proposed on the basis of the characteristics of strong fluctuation and high complexity of power load series,as well as the influence of meteorological factors and date types.Firstly,the Attention-GRU network is constructed.Secondly,the IGWO algorithm is improved,and IGWO is used to find the hyper-parameters of Attention-GRU network.Finally,the IGWO-Attention-GRU model is used to carry out experi-ments on power load data sets,and compared with various forecasting models.The experiment results show that the MAPE,RMSE and MAE values of IGWO-Attention-GRU model are the lowest among various fore-casting models,which verifies the superiority of IGWO-Attention-GRU model.

关键词

短期电力负荷预测/GRU网络/Attention机制/改进灰狼优化算法/超参数寻优

Key words

short-term power load forecasting/GRU network/Attention mechanism/Improved Grey Wolf Optimization/hyper-parameter optimization

引用本文复制引用

出版年

2024

信息技术

黑龙江省信息技术学会中国电子信息产业发展研究院　中国信息产业部电子信息中心

信息技术

CSTPCD

影响因子：0.413

ISSN：1009-2552

段落导航