多段型ニューラルネットを用いた日射量予測

抄録

So far a single-stage neural network has been proposed to forecast insolation of next day. In the present paper, a multi-stage neural network is developed to reduce forecasting error further. A first-stage neural network forecasts average atmospheric pressure of next day from atmospheric pressure data of previous day. A second-stage neural network forecasts insolation level of next day from the average atmospheric pressure and weather data of previous day. A third-stage neural network forecasts insolation of next day form the insolation level and weather data of previous day. Meteorological data of Omaezaki, Shizuoka at April 1994 are chosen as input data. The insolation values forecasted by the multi-stage and the single-stage neural networks are compared with the measurement ones. The results show that the forecasting error is reduced to 24% (by the multi-stage) from 33% (by the single-stage).