Hybrid methodology for hourly global radiation forecasting in Mediterranean area

The renewable energies prediction and particularly global radiation forecasting is a challenge studied by a growing number of research teams. This paper proposes an original technique to model the insolation time series based on combining Artificial Neural Network (ANN) and Auto-Regressive and Moving Average (ARMA) model. While ANN by its non-linear nature is effective to predict cloudy days, ARMA techniques are more dedicated to sunny days without cloud occurrences. Thus, three hybrids models are suggested: the first proposes simply to use ARMA for 6 months in spring and summer and to use an optimized ANN for the other part of the year; the second model is equivalent to the first but with a seasonal learning; the last model depends on the error occurred the previous hour. These models were used to forecast the hourly global radiation for five places in Mediterranean area. The forecasting performance was compared among several models: the 3 above mentioned models, the best ANN and ARMA for each location. In the best configuration, the coupling of ANN and ARMA allows an improvement of more than 1%, with a maximum in autumn (3.4%) and a minimum in winter (0.9%) where ANN alone is the best.

💡 Research Summary

The paper addresses the persistent challenge of accurately forecasting hourly global solar radiation, a key input for renewable‑energy management, by proposing three hybrid schemes that combine an Artificial Neural Network (ANN) with an Auto‑Regressive Moving Average (ARMA) model. The authors first note that ANN excels at capturing the non‑linear dynamics associated with cloudy or partially cloudy conditions, whereas ARMA is well‑suited for the relatively linear, predictable patterns of clear‑sky days. By exploiting these complementary strengths, the study aims to improve forecast skill across the diverse meteorological regimes typical of the Mediterranean basin.

Data and preprocessing – Hourly global radiation measurements, together with auxiliary meteorological variables (temperature, humidity, wind speed, pressure), were collected from five monitoring stations located in Spain, Italy, and Greece for the period 2014‑2015. Missing values were linearly interpolated, and all series were normalized to the