摘要
负荷预测的准确率会影响电力生产和经济发展,根据目前广东电力现货市场的出清机制,超短期负荷预测的准确度对未来电力现货市场出清电价有着重大影响。文章采用数据横向纵向修正法对历史负荷数据进行修正,通过长短期记忆网络(Long Short Term Memory Network,LSTM)的预测方法,同时考虑现货市场实际运行时间间隔,对未来15min的负荷进行预测。根据应用情况表明,该方法简单实用,能满足现货市场实际运行出清时的负荷预测要求。
The accuracy of load forecasting affects power production and economic development.According to the current clearing mechanism of Guangdong spot electricity market,the accuracy of ultra-short term load forecasting has a significant impact on the future clearing price of spot electricity market.In this paper,the historical load data are corrected by the method of data horizontal and vertical correction.Considering the actual running time interval of the spot market,the load of the next 15 minutes is forecasted by using the method of long-term and short-term memory network(LSTM).The application shows that the method is simple and practical,and can meet the demand of load forecasting when the spot market is actually running out of liquidation.
作者
罗日欣
钟永城
张中超
俞晓峰
LUO Rixin;ZHONG Yongcheng;ZHANG Zhongchao;YU Xiaofeng(Heyuan Power Supply Bureau of Guangdong Power Grid Co.,Ltd.,Heyuan,Guangdong 517000,China)
出处
《自动化应用》
2023年第1期125-127,134,共4页
Automation Application
关键词
超短期负荷预测
长短时记忆网络(LSTM)
横向变化率修正法
15min负荷预测
现货市场
ultra-short term load forecasting
long-term and short-term memory network(LSTM)
lateral change rate correction method
15—minute load forecasting
spot market
