Adaptive variable weight combination load prediction method and device

The present invention provides an adaptive variable weight combination load prediction method and device, and relates to the technical field of electrical power system load prediction. The technical problem is solved that a combination prediction method is low in accuracy in the prior art. The accur...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: XI PEIYU, FANG YIN, WANG QINGBO, WAN SHULU, WU YUJIAN, LIU JIE, GU YUGUI, DONG WUJUN, ZHANG QIAN, WANG CHUNYAN, YUAN XIAOPENG, TAO LI, ZHANG LIN, LI SHOUBAO, LYU JUNLIANG, WANG LEI, ZHAO XIAN, LIU DONG, LI RUIXIAO, WANG TAO, LYU WENTAO, SHI SHUHONG, TAN XIANG, GAO CHUNCHENG, WANG HAINING, DAI YONG, YUAN MINGZHU, LIU YONGHUI, CHENG LIN
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The present invention provides an adaptive variable weight combination load prediction method and device, and relates to the technical field of electrical power system load prediction. The technical problem is solved that a combination prediction method is low in accuracy in the prior art. The accuracy of combination prediction is improved, the data is simple in demand, high in flexibility and adaptive. The method comprises the steps of: performing modeling based on day-ahead load prediction of a plurality of prediction methods, and obtaining a plurality of single-day day-ahead load predictionmodels; establishing a day-ahead load combination prediction model based on the plurality of single-day day-ahead load prediction models; and performing updating of the weight of the day-ahead load combination prediction model based on reinforcement learning. 本发明提供了种自适应变权重组合负荷预测方法及装置,涉及电力系统负荷预测技术领域,以缓解现有技术中组合预测方法存在精确度低的技术问题,能够提高组合预测的精确度,且具有数据需求简单、灵活性强、自适应性等特点。该自适应变权重组合负荷预测方法包括:基于多种预测方法的日前负荷预测建模,得到多个单日前负荷预测模型;基于多个单日前负荷预测模