船电技术2025，Vol.45Issue(1)：5-8,4.
基于Attention-LSTM的短期电力负荷预测
Short-term power load forecasting based on Attention-LSTM
摘要
Abstract
The accuracy of power load forecasting is interfered by many factors,such as climate change,economic development and regional differences,which make the power load present significant instability and complex nonlinear characteristics,thus increasing the difficulty of improving the forecasting accuracy.To address this challenge,this paper innovatively introduces a prediction method that combines self-attention mechanism with Long Short-term Memory Network(LSTM).The experimental results show that the coefficient of determination(R2)of this method is 0.96,the Mean Absolute Error(MAE)is 0.023,and the Root Mean Square Error(RMSE)is 0.029,which significantly improves the accuracy of prediction.This not only proves the effectiveness of the proposed model in improving the accuracy of power load forecasting,but also lays a certain foundation for its application in power load forecasting for ships.关键词
短期电力负荷预测/长短期记忆网络/自注意力机制/预测精度/模型泛化能力Key words
short-term power load forecasting/long short-term memory networks/self-attention mechanism/predictive accuracy/model generalisation capabilities分类
信息技术与安全科学引用本文复制引用
李璨,伍黎艳,赵威,李晟,曾加贝,苏旨音,曾进辉..基于Attention-LSTM的短期电力负荷预测[J].船电技术,2025,45(1):5-8,4.基金项目
关于多场景光储充用一体化系统容量优化配置及运行控制策略研究的辅助服务采购 （）
