摘要 |
The present invention addresses the problem of enhancing the prediction accuracy of the prediction of a natural energy power generation amount, amount of solar radiation, or wind speed using a statistical method using machine learning. To address this problem, a prediction device (10) is provided that has a feature value extraction unit (13) for extracting a feature value that is the fluctuation of a time series from meteorological data from m (where m is at least 2) hours before a target time to the target time and an estimation unit (first estimation unit (14)) for estimating the natural energy power generation amount, amount of solar radiation, or wind speed at the target time on the basis of the feature values for a plurality of days. |