计算机与现代化Issue(4)：6-11,6.DOI:10.3969/j.issn.1006-2475.2025.04.002
基于TCN与轻量Autoformer的电力负荷预测
Power Load Forecasting Based on TCN and Lightweight Autoformer
摘要
Abstract
The accuracy of power load forecasting is crucial for energy conservation and emission reduction,and higher accuracy can enable power companies to make more reasonable plans and improve economic benefits.Although Autoformer,based on the improved Transformer architecture,has achieved good results in sequence prediction tasks,it did not fully consider the causal rela-tionship of time when extracting temporal features,and there is too much redundant information in the attention layer,which leads to a decrease in model accuracy and memory consumption.To address these issues,this paper proposes a power load forecasting method that combines Time Convolutional Network(TCN)and an improved lightweight Autoformer model.Firstly,a time convolu-tional network is introduced into the Autoformer encoder to provide a larger receptive field and fully consider the causal relation-ship of the samples.Then,a distillation mechanism is added between the autocorrelation attention layers to reduce the number of model parameters.Finally,the results of experiment on five public datasets showed that the lightweight Autoformer combined with TCN reduced MSE and MAE by 8.95%to 32.40%and 4.91%to 15.51%respectively compared to the original model,and the prediction performance is significantly better than the other four mainstream methods,demonstrating its excellent performance.关键词
Transformer/Autoformer/时间卷积网络/注意力蒸馏/负荷预测Key words
Transformer/Autoformer/temporal convolutional network/attention distilling/load forecasting分类
信息技术与安全科学引用本文复制引用
李明,石超山,文贵豪,罗勇航,谭云飞..基于TCN与轻量Autoformer的电力负荷预测[J].计算机与现代化,2025,(4):6-11,6.基金项目
国家自然科学基金资助项目(61877051,61170192) （61877051,61170192）
重庆市教委项目(113143) （113143）
重庆市研究生教改重点项目(yjg182022) （yjg182022）
