摘要
基于对双向长短期记忆神经网络模型的搭建,通过输入已知的部分数据对模型进行训练,使其对另一部分数据进行预测,并使预测结果与已知数据的另一部分进行对比,通过仿真结果验证了双向长短期记忆神经网络模型应用于电力负荷预测的优良性。双向长短期记忆神经网络(BILSTM)进行电力负荷预测可以提高预测的准确性、处理复杂的非线性关系、实现实时性,并且节约电力系统运营成本,具有重要的实际意义。
The model is trained by inputting part of the known data,so that it can predict the other part of the data and compare the prediction results with the other part of the known data,and the results of the simulation are verified to show the excellent performance of the model applied to power load forecasting.The simulation results verify the excellence of the two-way long short-term memory neural network model applied to power load forecasting.It is of great practical significance that BILSTM can improve the accuracy of forecasting,handle complex nonlinear relationships,achieve real-time performance,and save the operating cost of power system.
作者
韩宇
史麦瑞
王际涵
吕峥
Han Yu;Shi Mairui;Wang Jihan;Lyu Zheng(School of Electrical and Control Engineering,Liaoning Technical University,Huludao Liaoning 125105,China;Liaoning Radio and Television Huludao Suizhong Wave Station,Huludao Liaoning 125105,China)
出处
《现代工业经济和信息化》
2024年第4期205-207,共3页
Modern Industrial Economy and Informationization
关键词
负荷预测
神经网络
模型
电力系统
load forecasting
neural network
modelling
power system
作者简介
第一作者:韩宇(2002-),男,辽宁朝阳人,辽宁工程技术大学本科在读,研究方向为电力系统及其自动化。
