摘要
针对电力负荷具有随机性、波动性、以及易受外界干扰造成不确定性等特点,大大降低了其预测精度的准确性。为此,提出了一种基于黑翅鸢优化算法(Black-winged Kite Algorithm,BKA)。通过搭建预测仿真模型,利用BKA对LSTM网络的超参数进行优化,并测试该预测模型的各项性能指标。数据显示:该模型对实际电力负荷数据的预测精度更为精确,各项性能更具稳定性,并验证该预测方法的有效性和优越性。
Power loads are characterised by randomness,volatility,and uncertainty due to external disturbances,which greatly reduce the accuracy of their forecasting precision.For this reason,a Black-winged Kite Algorithm(BKA)is proposed.By building a prediction simulation model,the hyperparameters of the LSTM network are optimised using BKA,and the performance indexes of this prediction model are tested.The data show that the model is more accurate in predicting the actual power load data,and the performance is more stable,and verifies the effectiveness and superiority of the prediction method.
作者
黄文涛
路林艳
徐思文
Huang Wentao;Lu Linyan;Xu Siwen(School of Electrical and Control Engineering,Liaoning University of Engineering and Technology,Huludao Liaoning 125000,China)
出处
《现代工业经济和信息化》
2025年第3期272-273,281,共3页
Modern Industrial Economy and Informationization
关键词
电力负荷预测
长短期记忆网络
黑翅鸢优化算法
超参数优化
power load forecasting
long and short-term memory network
black-winged kite optimisation algorithm
hyperparameter optimisation
作者简介
第一作者:黄文涛(2003-),男,安徽宿州人,辽宁工程技术大学本科在读,研究方向为自动化。
