Prediction of hydroelectric power generation in Japan

ABSTRACT

The prediction model for power systems based on grey model has been studied by many researches. However, the prediction accuracy of grey model is unsatisfying when original data shows great randomness. In this article, in order to improve the prediction capability of grey model, the regression model is first integrated into GM(1, 1) through compensation for the residual error series. Then Markov chain model is applied for achieving the high prediction accuracy. A real case of hydroelectric power generation in Japan is used to validate the effectiveness of the proposed model. Based on our prediction results for hydroelectric power generation in Japan by year from 2010 to 2015, the growth of hydroelectric power generation has not seen a very big change.

KEYWORDS:

• Grey prediction model
• grey system theory
• hydroelectric power generation
• Markov chain model
• regression model