Enhancements in Day-Ahead Forecasts of Solar Irradiation with Machine Learning: A Novel Analysis with the Japanese Mesoscale Model

Abstract

The objective of this study is to propose and evaluate a set of modifications to enhance a machine-learning-based method for forecasting day-ahead solar irradiation. To assess the proposed modifications, they were implemented in an initial forecast method, and their effectiveness was analyzed using two years of data on a national scale in Japan. In addition, the accuracy of the modified method was compared with one of the forecast methods for solar irradiation used by the Japan Meteorological Agency (JMA), namely, the mesoscale model (MSM). Such forecasts were made publicly available only recently, which makes this study one of the first ones to compare them with machine-learning-based forecasts. The annual root-mean-square error (RMSE) of local forecasts of the JMA-MSM varied from 0.1 to 0.14 kW h m−2; the regional equivalent varied from 0.062 to 0.091 kW h m−2. In comparison with these results, the modified model achieved an average RMSE reduction of 7.5% on the local scale and 16% on the regional scale. The modified model also had a skill score that was 23% higher than that of the JMA model. Furthermore, the performance of the JMA model had strong spatial and seasonal dependencies, which were reduced in the machine-learning-based forecasts. The results show that the proposed modifications are effective in reducing large forecasts errors, but they cannot compensate for situations in which the input data used to make the forecasts are highly inaccurate.

Framework of Forecast Verification of Surface Solar Irradiance From a Numerical Weather Prediction Model Using Classification With a Gaussian Mixture Model

“…To reduce the effect of the seasonal cycle on the cluster analysis, the cluster analysis is performed for each month. In May, the forecast quality of the surface solar irradiance from the MSM model is better than at other times during the year (Fonseca et al, 2020). However, in May, Japan often experiences aerosol events and there may be an uncertainty of about 10 W/m 2 in the reference data (Damiani et al, 2018).…”

Support Vector Quantile Regression for the Post-Processing of Meso-Scale Ensemble Prediction System Data in the Kanto Region: Solar Power Forecast Reducing Overestimation

“…In order to suppress these errors, machine learning is recognized as a useful approach for the post-processing tool for NWP [33]. For example, Artificial Neural Network (ANN) [34,35], regression tree [36,37], and Support Vector Regression (SVR) [38,39]. Besides, the recent solar power forecast model research adopts an ensemble learning approach, which integrates multiple models into a hybrid model that enables the predictor to provide more accurate predictions than a conventional single unit [29].…”

Machine Learning Approach on Time Series for PV-Solar Energy

“…ere is no prescribed structure to design the ANN method. But ANN can develop according to all parameters, as shown in Figure 1 [18,23,24].…”

“…e current work developed two methods. One is the time series model in the machine learning technique for short time series, and another is machine learning to optimize or predict the accuracy of the ANN model [18]. e entire work will give a comparative analysis of the machine learning techniques.…”