基于STL-Informer-BiLSTM-XGB模型的供热负荷预测  

Heating Load Forecasting Based on STL-Informer-BiLSTM-XGB Model

作　　者：殷建华[1] 戴冠正 丁宁 辛晓钢[1] 张谦[1] 杜荣华[1] YIN Jian-hua;DAI Guan-zheng;DING Ning;XIN Xiao-gang;ZHANG Qian;DU Rong-hua(Inner Mongolia Electric Power Science and Research Institute,Huhhot 010020,China;School of Control and Computer Engineering,North China Electric Power University,Beijing 102206,China)

机构地区：[1]内蒙古电力科学研究院,呼和浩特010020 [2]华北电力大学控制与计算机工程学院,北京102206

出　　处：《科学技术与工程》2024年第21期8942-8949,共8页Science Technology and Engineering

基　　金：国家自然科学基金(52206009);内蒙古电力(集团)有限责任公司科技项目(2022-26)。

摘　　要：供热负荷预测是指导供热系统调控的重要手段。提高供热负荷预测精度十分重要,针对机器学习中输出目标的分解预测,提出了一种基于季节和趋势分解(seasonal and trend decomposition using loess,STL)的供热负荷预测方法,构建了适用于供热负荷预测的输出目标。首先利用STL算法将供热负荷时间序列数据分解为趋势分量、周期分量和残差分量,分别训练Informer、BiLSTM和XGB模型,将构建好的3个分量预测模型的输出叠加作为初步预测结果,分析误差序列,以BiLSTM预测误差提高模型精度,构建出STL-Informer-BiLSTM-XGB预测模型。将上述模型与常用预测模型进行对比,结果表明所构建的STL-Informer-BiLSTM-XGB模型的MAPE、MAE和MSE分别为0.871%、96.18和13202.2,预测效果最优,验证了所提出的方法具有较高的供热负荷预测精度。Heating load forecasting is a key method to guide the regulation of heating system.Improving the accuracy of heating load forecasting is very essential.For the decomposition prediction of output targets in machine learning,a heating load forecasting method based on seasonal and trend decomposition using loss(STL)was proposed,and output targets suitable for heating load forecasting was constructed.Initially,using the STL algorithm,the heating load time series data was decomposed into trend components,periodic components,and residual components.These components were used to train Informer,BiLSTM and XGB models respectively.The output of the constructed three component forecasting models was superimposed as the preliminary forecasting results,and the error sequence was analyzed to improve the model accuracy with BiLSTM forecasting errors.Finally,the STL-Informer-BiLSTM-XGB prediction model was constructed.The above model was compared with commonly used forecasting models,and the results showed that the constructed STL-Informer-BiLSTM-XGB model has MAPE,MAE,and MSE of 0.871%,96.18,and 13202.2,respectively,which shows the best forecasting effect and verifies the high accuracy of the heating load forecasting method proposed.

关 键 词：供热负荷 机器学习 季节和趋势分解 INFORMER 双向长短期记忆网络 极端梯度提升网络 

分 类 号：TK221[动力工程及工程热物理—动力机械及工程]