Development of Hybrid Intelligent System for Electricity Price Time-Series Forecasting
Project/Area Number |
26420252
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Power engineering/Power conversion/Electric machinery
|
Research Institution | Meiji University |
Principal Investigator |
Mori Hiroyuki 明治大学, 総合数理学部, 専任教授 (70174381)
|
Project Period (FY) |
2014-04-01 – 2017-03-31
|
Project Status |
Completed (Fiscal Year 2016)
|
Budget Amount *help |
¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
Fiscal Year 2016: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2015: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2014: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
|
Keywords | 電力価格予測 / 地域別限界価格 / ガウシアンプロセス / クラスタリング / 進化的計算 / ニューラルネットワーク / ファジィ論理 / 予測 / 時系列予測 / 電力価格 / カーネルマシン / 階層的ベイズ推定 / ハイブリッドシステム / エラーバー / 不確定性 |
Outline of Final Research Achievements |
n this research, new models for GP of Kernel Machine have been proposed to deal with electricity price forecasting in power markets. So, intelligent systems are the mainstream of the methods due to the good nonlinear approximation. However, there is still room for improvement of intelligent systems for electricity price forecasting. This research proposes three strategies for GP, Use of Mahalanobis Functions in GP, Application of EPSO to determination of parameters, and Precondition of learning data by crisp and fuzzy clustering. In addition, the effectiveness of the strategies was investigated for an alternative model of GRBFN (Generalized Radial Basis Function Network) of ANN (Artificial Neural Network).
|
Report
(4 results)
Research Products
(21 results)