Multi-step wind speed forecast based on sample clustering and an optimized hybrid system

Abstract

At present, accurate forecast of very-short-term wind speed is still a critical issue, mainly due to the complex characteristics of wind variations such as intermittence, fluctuation and randomness. On this topic, our paper contributes to the development of an effective multi-step forecasting method termed ECKIE, which provides multi-step forecast for the very-short-term wind speed in specific stations. This method consists of three stages: a data filtering process driven by the ensemble empirical mode decomposition (EEMD), an improved K-harmonic mean (KHM) clustering optimized by the Cuckoo search (CS) algorithm and a single-hidden-layer feedforward network (SLFN) trained by the incremental extreme learning machine (IELM) algorithm. The developed method is capable of clustering the model inputs into groups according to their characteristics and of constructing the models for each group. It is further capable of reducing forecasting errors by choosing a suitable model. It is a purely data-driven process and is an effective method for very-short-term wind speed forecasts. The simulation demonstrates that the developed method drastically improves upon original model performance and performs the best among comparable models.