Search

High‐accuracy predictions of future solar power generations are important for monitoring, maintenance, dispatching, and scheduling. The goal of this study is to create a forecasting workflow that increases prediction accuracy independent of the machine learning method and has minimal computational requirements. The proposed trend decomposition method incorporates irradiance and seasonal features as exogenous inputs. In order to extract the linear part of the data, a moving average filter is used. The nonlinear (stable) component of the time series is then calculated by subtracting this linear part from the original data. The stable portion is modeled using several machine learning methods, while the ordinary least squares method is applied to the linear series. By aggregating both results, the final forecast is obtained. The forecasting performances of the machine learning algorithms on unprocessed data are used as baselines for evaluations. Improvements up to 39% in the mean absolute error and up to 31% in the root mean square error metrics are observed compared to the baselines. Experimental results show that the proposed trend decomposition with extrapolation method increases the forecasting performance and generalization capacity of machine learning algorithms. High‐accuracy predictions of future solar power generations are important for monitoring, maintenance, dispatching, and scheduling. The goal of this study is to create a forecasting workflow that increases prediction accuracy independent of the machine learning method and has minimal computational requirements. The proposed trend decomposition method increases the forecasting performance and generalization capacity of machine learning algorithms.