Scholarlink

In order to solve the problems of power load series volatility, limited fore-casting accuracy and long training time, a prediction model based on linear transformer, variational mode decomposition (VMD) and Golden Jackal optimization algorithm (GJO) was proposed to optimize hyperparameters. First, the original load sequence is decomposed using VMD optimized by GJO parameters. Finally the results of each model are combined to obtain the final predicted value. Experiments show that the root mean square error (RMSE) of the prediction model in this paper is 105.399, the mean absolute error (MAE) is 77.98, and the mean absolute percentage error (MAPE) is 1.11. The training time is reduced by 275.24 s at most, and the error is smaller than that of other prediction models. It has higher prediction accuracy, lower training cost and better fit to the actual value.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Short-Term Load Forecasting Based on Linear Transformer Joint Optimization

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • JinChi Dai,
  • YaoSong Xu

摘要

In order to solve the problems of power load series volatility, limited fore-casting accuracy and long training time, a prediction model based on linear transformer, variational mode decomposition (VMD) and Golden Jackal optimization algorithm (GJO) was proposed to optimize hyperparameters. First, the original load sequence is decomposed using VMD optimized by GJO parameters. Finally the results of each model are combined to obtain the final predicted value. Experiments show that the root mean square error (RMSE) of the prediction model in this paper is 105.399, the mean absolute error (MAE) is 77.98, and the mean absolute percentage error (MAPE) is 1.11. The training time is reduced by 275.24 s at most, and the error is smaller than that of other prediction models. It has higher prediction accuracy, lower training cost and better fit to the actual value.