电工技术学报  2015, Vol. 30 Issue (23): 110-115    DOI:
电力系统及其自动化 |
大用户电力负荷的多模型模糊综合预测
谷云东1, 张素杰1, 冯君淑2
1.华北电力大学数理学院 北京 102206
2.华北电力大学电气与电子工程学院 北京 102206
Multi-model Fuzzy Synthesis Forecasting of Electric Power Loads for Larger Consumers
Gu Yundong1, Zhang Sujie1, Feng Junshu2
1.School of Mathematics and Physics North China Electric Power University Beijing 102206 China
2.School of Electrical and Electronic Engineering North China Electric Power University Beijing 102206 China
全文: PDF (1926 KB)  
输出: BibTeX | EndNote (RIS)      
摘要 研究大用户的短期电力负荷预测问题,给出一种基于变权综合模糊推理的多模型综合预测方法。该方法首先引入基于质心相似度聚类的负荷模式分析算法,挖掘历史负荷数据中合群的典型负荷模式,并按相似性进行分组,同时剔除少量的离群异常记录;然后给出基于共轭梯度的RBF神经网络训练算法,分别对每类典型负荷模式建立相应的单元预测模型;最后利用基于相似度加权的多模型变权综合模糊推理策略,实现各单元模型预测结果的自适应融合。案例仿真验证了多模型模糊综合预测方法的可靠性。
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
谷云东
张素杰
冯君淑
关键词 大用户负荷预测质心相似度聚类RBF神经网络多模型模糊综合预测模糊推理    
Abstract:A multi-model based variable weighted fuzzy synthesis forecasting method is proposed for the power load forecasting of large consumers.A clustering algorithm based on Renyi-entropy and centroid similarity is introduced to mining typical load patterns from historical load data and grouping them according to similarities as well as detecting atypical outliers.A conjugate gradient based learning algorithm for the RBF neural network is designed to construct unit forecasting model for each group of typical load patterns.Then,the forecasting results of all unit models are integrated adaptively by using variable weighted fuzzy synthesis inference.The simulation results show that the multi-model fuzzy synthesis forecasting method can raise the prediction accuracy and stability significantly.
Key wordsElectric power load forecasting for large consumers    centroid similarity based clustering    RBF neural network    multi-model fuzzy synthesis forecasting    fuzzy reasoning   
收稿日期: 2015-01-05      出版日期: 2015-12-18
PACS: TM76  
基金资助:国家自然科学基金(71171080)和中央高校基本科研业务费专项资金(12MS84、2015MS51)资助项目。
通讯作者: 张素杰 女,1991年生,硕士研究生,研究方向为模糊系统建模与优化等。   
作者简介: 谷云东 男,1976年生,博士,副教授,研究方向为模糊系统建模、评估与优化决策等
引用本文:   
谷云东, 张素杰, 冯君淑. 大用户电力负荷的多模型模糊综合预测[J]. 电工技术学报, 2015, 30(23): 110-115. Gu Yundong, Zhang Sujie, Feng Junshu. Multi-model Fuzzy Synthesis Forecasting of Electric Power Loads for Larger Consumers. Transactions of China Electrotechnical Society, 2015, 30(23): 110-115.
链接本文:  
https://dgjsxb.ces-transaction.com/CN/Y2015/V30/I23/110