基于黑翅鸢优化长短期记忆网络的短期电力负荷预测  

Short-Term Power Load Forecasting Based on Black-Winged Kite Optimised Long and Short-Term Memory Networks

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)

机构地区：[1]辽宁工程技术大学电气与控制工程学院,辽宁葫芦岛125000

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

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.

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 

分 类 号：TM715[电气工程—电力系统及自动化] TP309[自动化与计算机技术—计算机系统结构]