Multi-step wind speed forecasting model using a compound forecasting architecture and an improved QPSO-based synchronous optimization

Abstract

The intermittency and randomness of wind speed time series influence the forecasting accuracy. To figure out this problem and enhance the forecasting performance, a novel compound structure is developed for short-term wind speed forecasting. The developed compound method firstly eliminates the inherent noise from the original empirical wind speed time series using wavelet packet decomposition (WPD) and subsequently constructs appropriate input matrix by phase space reconstruction (PSR) for multi-kernel least square support vector machine (MKLSSVM). To take advantage of different kernel function, MKLSSVM with optimal combination of radial basis kernel function, polynomial kernel function and linear kernel function is constructed to make wind speed forecasting. Then, the proposed improved quantum particle swarm optimization algorithm (QPSO) based on the chaos initialization, Gaussian distribution local attraction points, precocity judgment, and disturbance operator, namely ADQPSO, is employed to optimize the decomposition level of WPD, reconstruction parameters of PSR, kernel parameters and weighted coefficients in MKLSSVM synchronously. To evaluate the forecasting performance of the proposed hybrid model, four sets of historical wind speed data samples from Weihai wind farm in China are utilized to make multi-step short-term wind speed forecasting tests. The experimental results illustrate that the proposed hybrid model outperforms the compared single and new recently developed forecasting models, thus, the proposed WPD-PSR-ADQPSO-MKLSSVM is an effective method for short-term wind speed forecasting.