A Guide to Solar Power Forecasting using ARMA Models

TL;DR

This paper presents a straightforward methodology for developing hourly ARMA models to forecast photovoltaic solar power output, emphasizing model validation, sample construction, and practical integration for energy planning.

Contribution

It introduces a simple ARMA-based approach for solar power forecasting, highlighting validation techniques and utility in stochastic energy optimization.

Findings

ARMA models provide good accuracy for solar power forecasting

Methodology facilitates integration into energy planning models

Models are validated using statistical tests

Abstract

We describe a simple and succinct methodology to develop hourly auto-regressive moving average (ARMA) models to forecast power output from a photovoltaic solar generator. We illustrate how to build an ARMA model, to use statistical tests to validate it, and construct hourly samples. The resulting model inherits nice properties for embedding it into more sophisticated operation and planning models, while at the same time showing relatively good accuracy. Additionally, it represents a good forecasting tool for sample generation for stochastic energy optimization models.