A short-term load forecasting model based on relevance vector machine with nonnegative matrix factorization

作者：Huang Shuaidong^*; Wei Zhinong; Gao Zonghe; Yang Zhenglin; Sun Guoqiang; Sun Yonghui

来源：Automation of Electric Power Systems, 2012, 36(11): 62-66.

DOI：10.3969/j.issn.1000-1026.2012.11.011

• Feature extracting
• Input datas
• Input variables
• Mapping matrix
• Non-negative matrix factorization algorithms
• Nonnegative matrix factorization
• Redundant data
• Relevance Vector Machine
• Short term load forecasting

In view of the limitation of traditional feature extracting algorithm in extracting only the algebraic features of samples to the neglect of the practical significance of the original problem, a short-term load forecasting model based on the relevance vector machine (RVM) is proposed. By using the nonnegative matrix factorization (NMF) algorithm, the dimension of input variables is reduced, then a short-term load forecasting model based on the RVM is proposed. The input data is decomposed using the NMF algorithm, where the nonnegative lower-dimension mapping matrix derived is taken as the input of RVM for training and prediction. Owing to the nonnegative property of the lower-dimension matrix, it retains the practical significance of the original problem while eliminating the redundant data and reducing dimensions. Simulation results show that the dimensions of the input variables can be effectively reduced and the accuracy greatly improved.

• 出版日期2012
• 单位河海大学