Short-term solar irradiance and irradiation forecasts via different time series techniques: A preliminary study

TL;DR

This study compares various short-term solar irradiance forecasting methods, finding that simpler techniques requiring less historical data outperform more data-dependent approaches in noisy conditions.

Contribution

It provides a preliminary comparison of different time series techniques for solar irradiance forecasting, highlighting the effectiveness of data-efficient methods.

Findings

Data-efficient methods perform better with noisy data

Techniques needing less historical data are more accurate in preliminary tests

Simpler models can outperform complex ones in certain conditions

Abstract

This communication is devoted to solar irradiance and irradiation short-term forecasts, which are useful for electricity production. Several different time series approaches are employed. Our results and the corresponding numerical simulations show that techniques which do not need a large amount of historical data behave better than those which need them, especially when those data are quite noisy.