Very Short Term Time-Series Forecasting of Solar Irradiance Without Exogenous Inputs

TL;DR

This study evaluates simple, exogenous-input-free models like NNR and ARIMA for short-term solar irradiance forecasting over 3 hours, analyzing hyperparameters and data factors to optimize prediction accuracy.

Contribution

It compares and analyzes hyperparameters of NNR and ARIMA models for short-term solar irradiance forecasting without external data, proposing a faster model selection approach.

Findings

Hyperparameters significantly influence forecast quality.

A reduced search space enables faster model identification.

Models perform consistently across different locations and seasons.

Abstract

This paper compares different forecasting methods and models to predict average values of solar irradiance with a sampling time of 15 min over a prediction horizon of up to 3 h. The methods considered only require historic solar irradiance values, the current time and geographical location, i.e., no exogenous inputs are used. Nearest neighbor regression (NNR) and autoregressive integrated moving average (ARIMA) models are tested using different hyperparameters, e.g., the number of lags, or the size of the training data set, and data from different locations and seasons. The hyperparameters and their effect on the forecast quality are analyzed to identify properties which are likely to lead to good forecasts. Using these properties, a reduced search space is derived to identify good forecasting models much faster.