基于长短期记忆网络的电力负荷预测模型  

Power Load Forecasting Model Based on Long Short-Term Memory Network

作　　者：胡晶 HU Jing(School of Information and Intelligent Transportation,Fujian Chuanzheng Communications College,Fuzhou 350007,China)

机构地区：[1]福建船政交通职业学院信息与智慧交通学院,福建福州350007

出　　处：《许昌学院学报》2025年第2期117-122,共6页Journal of Xuchang University

基　　金：第二批中国高校产学研创新基金项目(2020ITA03033);福建船政交通职业学院科教发展基金项目(Z202311033)。

摘　　要：准确预测电力负荷对电力系统的资源配置至关重要,提出了一种基于长短期记忆网络(LSTM)的预测模型,以历史供电数据和相关影响因素为输入,实现对未来电力负荷的预测.实验结果表明,与传统回归模型和机器学习模型相比,新模型采用基于LSTM的时序数据建模,在预测准确性和稳定性方面具有明显优势,融入极端天气影响因子后能更好捕捉极端天气导致的负荷异常,提高模型应用价值.Accurate prediction of electrical load is crucial for resource allocation in the power system.A prediction model based on the Long Short-Term Memory(LSTM)network is proposed,which takes historical power supply data and relevant influencing factors as input to predict future electrical load.Experimental results show that compared with traditional regression models and machine learning models,the new model adopts time series data modeling based on LSTM,having significant advantages in prediction accuracy and stability.After incorporating extreme weather influence factors,the model can better capture abnormal loads caused by extreme weather,enhancing its application value.

关 键 词：LSTM 时序数据建模 均方误差 电力负荷 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]