电力需求侧管理2025，Vol.27Issue(3)：58-64,7.DOI:10.3969/j.issn.1009-1831.2025.03.009
基于SEResNet-BiLSTM网络的综合能源负荷预测方法
Integrated energy system load forecasting based on SEResNet-BiLSTM network
摘要
Abstract
Accurate prediction of multi-energy load is crucial for the optimal scheduling and economic operation of integrated energy sys-tems(IES).Aiming at the strong randomness of regional IES and the coupling relationship between multi-energy sources,a multi-task short-term load prediction model based on SEResNet-BiLSTM network and attention mechanism is proposed.Firstly,the model of squeeze-and-excitation networks-residual network(SEResNet)is used as the high-dimensional feature extraction unit to mine the coupling relation-ship between multiple energy sources.The high-dimensional feature extraction of multi-energy load data is realized.Then,bidirectional long short-term memory(BiLSTM)network is used to capture the time series characteristics between data to realize the prediction of load data.Multi-task load learning is realized by hard weight sharing to realize multivariate load forecasting.Finally,the effectiveness of pro-posed method is verified by simulation experiments,and the accuracy of the proposed method is significantly improved compared with oth-er models.关键词
综合能源系统/多能源负荷预测/残差网络/双向长短期记忆网络/多任务学习Key words
integrated energy system/multi-energy load forecasting/residual network/bidirectional long short-term memory network/multi-task learning分类
动力与电气工程引用本文复制引用
宋峥峥,辛锐,赵黎媛,王经书,张鹏飞,李士林..基于SEResNet-BiLSTM网络的综合能源负荷预测方法[J].电力需求侧管理,2025,27(3):58-64,7.基金项目
天津市自然科学基金项目(23JCQNJC01060) （23JCQNJC01060）
天津市教委科研计划项目(2022KJ088) （2022KJ088）
