A benchmarking framework for performance evaluation of statistical wind power forecasting models

Abstract

Lack of benchmarks for wind power forecasting models undermine their potential and consequently their implementation for industry applications. Despite the extensive existing literature in the field, a unified framework has not been created yet. Therefore, we propose a benchmark set-up where statistical wind power forecasting models can be tested under standardized criteria with respect to data, time resolution, and prediction horizon, while evaluating them under varied representative operational conditions of wind farms. The utility of this framework is shown with an example case applied to mode decomposition models, which have shown a higher performance compared to other statistical models in recent times. Data collected from two Irish wind farms are used to calculate the accuracy of statistical wind power forecasting models. Their robustness is also examined by providing an assessment of such models under several scenarios of power generation. In the example case of this benchmark, results indicate that the use of variational mode decomposition as decomposition algorithm together with advanced recurrent networks provide the best performance among the evaluated forecasting models.