EPSOを用いたGRBFNによる太陽光発電出力予測

カテゴリ: 論文誌(論文単位)

グループ名: 【B】電力・エネルギー部門

発行日: 2013/01/01

タイトル(英語): A GRBFN-EPSO-based Method for Predicting PV Generation Output

著者名: 高橋　政人（明治大学理工学部電気電子生命学科），森　啓之（明治大学理工学部電気電子生命学科）

著者名(英語): Masato Takahashi (Department of Electronics and Bioinformatics, Meiji University), Hiroyuki Mori (Department of Electronics and Bioinformatics, Meiji University)

キーワード: 太陽光発電，予測，ニューラルネットワーク，過学習，メタヒューリスティクス，クラスタリング　　PV systems，forecasting，artificial neural network (ANN)，overfitting，metaheuristics，clustering

要約(英語): In this paper, a new method is presented to predicting PV generation output. The method makes use of a hybrid intelligent system of EPSO (Evolutionary Particle Swarm Optimization) of meta heuristics and GRBFN (Generalized Radial Basis Function Network) of artificial neural network (ANN). GRBFN is an extension of RBFN in a sense that the center and the width of the radial basis functions are determined by the learning process although the conventional RBFN does not update them through the learning process. EPSO is used to evaluate better the weights between the hidden and the output layers because it is useful for solving nonlinear optimization problems from a standpoint of global optimization. In particular, EPSO has advantage to adjust the algorithm parameters with the evolutionary strategy to make the search process more diverse by the replication. In addition, DA (Deterministic Annealing) clustering that corresponds to a global clustering technique is employed to evaluate the initial solutions of the center and the width so that the performance of GRBFN is improved. Furthermore, the weight decay method is utilized at the learning processes to avoid the overfitting to learning data since the conventional methods are inclined to provide erroneous results due to overfitting to complicated time series data of PV generation output. The proposed method is successfully applied to real data of a PV system.

本誌: 電気学会論文誌B（電力・エネルギー部門誌） Vol.133 No.1 （2013） 特集：平成24 年電力・エネルギー部門大会

本誌掲載ページ: 72-78 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejpes/133/1/133_72/_article/-char/ja/