Forecasting global solar irradiance for various resolutions using time series models - case study: Algeria

ABSTRACT

The objective of this research is to build models for various time resolutions to predict global solar irradiation using data mining and statistical techniques. The time resolutions analyzed are 5 min, 1 hour and one-day horizon ahead. The models tested herein are three supervised machine learning (ML) techniques: nonlinear autoregressive neural network (NAR), support vector regression (SVR) and random forest (RF). A linear autoregressive (AR) model and the naive persistence (PER) model have also been included. The datasets come from two sites situated in Algeria: Algiers and Ghardaia that have different climatic conditions during the year corresponding to two types of climate, Mediterranean and Arid. One important contribution of this research to global irradiance forecasting is the benchmarking of the ML used, taking into account the lack of practical results and the needs detected in the literature, especially for the case of RF model; according to our best knowledge, the random forest method has never been tested as it has been done in our study: it is just based on past values of the same variable without exogenous data to forecast the future ones. The results of this research show that RF is the best technique with a slight difference in performance, specially for hourly forecasts ahead. The proposed models appear to be less outstanding both in the case of unstable sky conditions (Algiers) and when the resolution is 1 day, due to the fact that time series become significantly less correlated by including more randomness characteristic.

KEYWORDS:

• Global horizontal solarirradiance
• Forecasting
• data mining techniques
• temporal resolution
• statistical analysis

Additional information

Notes on contributors

A. Takilalte

A. Takilalte is researcher in the Renewable Energy Developement Center (CDER) at Algiers, and is currently working on his PhD at the Université de la Science et de la Technologie Houari Boumediene (USTHB). His field of research is the modelling and instrumentation of solar radiation.

S. Harrouni

S. Harrouni received the Ingénieur in Electronics, Magister in Electronics and Doctor in Electronics degrees from USTHB (Université des Sciences et de la Technologie Houari Boumediene) University, Algiers, Algeria, in 1994, 2000 and 2006, respectively, and the HDR (accreditation to supervise research) degree in electronics from the same university, in 2009. She is currently a Teacher-Researcher in Electronics at the USTHB University. Her research interests include solar and wind resources modeling, renewable energy potential evaluation and site characterization, photovoltaic systems and energy storage.

J. Mora

J. Mora is Professor of Statistics and Econometrics at Universidad de Alicante. His research activity has focused on the study of nonparametric and semiparametric statistical methods, analyzing how they can contribute to solve econometric problems of interest in different contexts, both with theoretical and applied perspective. As a result of this research activity he has published numerous articles in specialized journals of Statistics and Econometrics, including some of the best international journals in these areas (such as Biometrika, Econometrica and Computational Statistics & Data Analysis), and also various articles in prestigious interdisciplinary journals (such as Environmental Modelling & Software and Expert Systems with Applications).