K nearest neighbour optimal selection in fuzzy inductive reasoning for smart grid applications

Abstract

Energy recasting has been an area of great interest in the last years. It unlocks, not only the Smart Grid's potential with load balancing but also new business models and added value services. To achieve an accurate, robust and fast prediction, model's parametrization is key and becomes a bottleneck in the value-chain. In this article, we present an improved version of Flexible Fuzzy Inductive Reasoning (Flexible FIR) that selects the most optimal number of nearest neighbours during FIR prediction phase, called K nearest neighbour Optimal Selection (KOS). To this end, a real smart grid forecasting application, i.e. electricity load forecasting, has been chosen in this study. The results show that the best forecasting accuracy, on average, is when the KOS is used on Flexible FIR. While with KOS the optimal parameter k is found online, without it is not, which increases the computational time.