Numerical Weather Prediction (NWP) and hybrid ARMA/ANN model to predict global radiation

TL;DR

This paper introduces a hybrid ARMA/ANN model utilizing numerical weather prediction data to accurately forecast hourly global radiation, outperforming traditional models across multiple Mediterranean locations.

Contribution

The study develops an innovative hybrid ARMA/ANN approach with optimized architecture and pre-input layer selection, enhancing global radiation prediction accuracy.

Findings

Hybrid model achieves 14.9% nRMSE, outperforming naive persistence and standalone ANN models.

Model effectively predicts hourly global radiation for five Mediterranean locations.

Confidence interval analysis supports the reliability of the forecasts.

Abstract

We propose in this paper an original technique to predict global radiation using a hybrid ARMA/ANN model and data issued from a numerical weather prediction model (ALADIN). We particularly look at the Multi-Layer Perceptron. After optimizing our architecture with ALADIN and endogenous data previously made stationary and using an innovative pre-input layer selection method, we combined it to an ARMA model from a rule based on the analysis of hourly data series. This model has been used to forecast the hourly global radiation for five places in Mediterranean area. Our technique outperforms classical models for all the places. The nRMSE for our hybrid model ANN/ARMA is 14.9% compared to 26.2% for the na\"ive persistence predictor. Note that in the stand alone ANN case the nRMSE is 18.4%. Finally, in order to discuss the reliability of the forecaster outputs, a complementary study concerning the confidence interval of each prediction is proposed