What drives the accuracy of PV output forecasts?

TL;DR

This paper reviews 180 studies on PV output forecasting, identifying key factors affecting accuracy, highlighting hybrid models' superiority, and proposing benchmarks for future assessments.

Contribution

It systematically analyzes factors influencing PV forecast accuracy and introduces a benchmark framework for evaluating PV output models.

Findings

Hybrid models outperform other forecast models.

Data processing techniques improve forecast accuracy.

Longer forecast horizons and smaller test sets reduce accuracy.

Abstract

Due to the stochastic nature of photovoltaic (PV) power generation, there is high demand for forecasting PV output to better integrate PV generation into power grids. Systematic knowledge regarding the factors influencing forecast accuracy is crucially important, but still mostly unknown. In this paper, we review 180 papers on PV forecasts and extract a database of forecast errors for statistical analysis. We show that among the forecast models, hybrid models consistently outperform the others and will most likely be the future of PV output forecasting. The use of data processing techniques is positively correlated with the forecast quality, while the lengths of the forecast horizon and out-of-sample test set have negative effects on the forecast accuracy. We also found that the inclusion of numerical weather prediction variables, data normalization, and data resampling are the most effective data processing techniques. Furthermore, we found some evidence for cherry picking in reporting errors and recommend that the test sets be at least one year to better assess model performance. The paper also takes the first step towards establishing a benchmark for assessing PV output forecasts.