基于趋势指标与长短时记忆网络的电力市场日前电价预测  

Day-ahead Electricity Price Forecasting of Power Market Based on Trend Index and Long Short Term Memory

作　　者：郭贺宏[1] 武灵耀 赵庆生[3] 梁定康 王旭平[3] 程昱舒[1] GUO Hehong;WU Lingyao;ZHAO Qingsheng;LIANG Dingkang;WANG Xuping;CHENG Yushu(State Grid Shanxi Electric Power Company,Taiyuan 030021,China;State Grid Shanxi Jinzhong Power Supply Company,Jinzhong 030600,China;Shanxi Key Laboratory of Power System Operation and Control,Taiyuan University of Technology,Taiyuan 030024,China)

机构地区：[1]国网山西省电力公司,山西太原030021 [2]国网晋中供电公司,山西晋中030600 [3]太原理工大学电力系统运行与控制山西省重点实验室,山西太原030024

出　　处：《智慧电力》2022年第9期97-103,共7页Smart Power

基　　金：国家自然科学基金青年科学基金资助项目(51907138)。

摘　　要：为提高电力市场日前电价的预测精度,提出一种基于趋势指标与长短时记忆网络(LSTM)的日前电价预测模型。首先,计算日前电价的随机指标(KDJ)与异同移动平均线指标(MACD),挖掘电价的内在规律信息;然后,将计算出的趋势指标与电价信息输入LSTM,对电力市场日前电价进行预测;最后,利用电力市场日前电价数据进行验证。算例分析表明该模型相比反向传播神经网络(BPNN)、LSTM和门控循环单元网络(GRU)等模型预测精度更高。In order to improve the forecasting accuracy of day ahead price in power market,a day ahead price forecasting model based on trend index and long-term and short-term memory neural network is proposed.Firstly,the KDJ index and MACD index of the day ahead electricity price are calculated,the inherent law information of electricity price is mined;Secondly,the calculated trend index and electricity price information are input into LSTM to forecast the day ahead electricity price in the electricity market;Finally,the experiment is carried out by using the electricity market day ahead price data.The example analysis shows that the prediction accuracy of the proposed model is higher than that of BPNN,LSTM and GRU.

关 键 词：长短时记忆网络 KDJ指标 MACD指标 电力市场 日前电价 

分 类 号：TM715[电气工程—电力系统及自动化]