Data-driven forecasting of solar irradiance

TL;DR

This paper presents a flexible, data-driven approach for short-term solar irradiance forecasting, utilizing recent observed data and various regression models to improve prediction accuracy across multiple sites.

Contribution

It introduces a combined methodology using ARIMA-based variable selection and machine learning models for accurate one-hour-ahead solar irradiance prediction.

Findings

Models perform well across different sites.

Recent observed data improves forecast accuracy.

Neural networks and regression trees are effective.

Abstract

This paper describes a flexible approach to short term prediction of meteorological variables. In particular, we focus on the prediction of the solar irradiance one hour ahead, a task that has high practical value when optimizing solar energy resources. As D\'efi EGC 2018 provides us with time series data for multiple sensors (e.g. solar irradiance, temperature, hygrometry), recorded every minute for two years and 5 geographical sites from La R\'eunion island, we test the value of using recently observed data as input for prediction models, as well as the performance of models across sites. After describing our data cleaning and normalization process, we combine a variable selection step based on AutoRegressive Integrated Moving Average (ARIMA) models, to using general purpose regression techniques such as neural networks and regression trees.