A review of deterministic error scores and normalization techniques for power forecasting algorithms

The evaluation of the performance of forecasting algorithms in the area of power forecasting of regenerative power plants is the basis for model comparison. There are a multitude of different forms of evaluation scores, which, however, do not seem to be universally applied. In this article, we want to broaden the understanding for the function and relationship of different error scores in the area of deterministic error scores. A categorization by normalization technique is introduced, which simplifies the process of choosing the appropriate error score for an application. A number of popular error scores are investigated in a case study which details the development of error scores given different forms of error distributions. Furthermore, the behavior of different error scores on a real-world wind farm data set is analyzed. A correlation analysis between the evaluated scores gives insights on how these scores relate to each other. Properties and notes on the applicability of the presented scores are detailed in a discussion. Finally, an outlook on future work in the area of probabilistic error scores is given.