The Investigation And Application Of Hybrid Wind Speed Forecasting Model Based On Phase Space Reconstruction Theory And Error Correction Model

Recently, the development and utilization of renewable energy have become a hot issue, in which wind energy is widely used for its great potential, and the most important form of wind energy is wind power. But due to the randomness and intermittent traits of wind, wind power has strong volatility and uncontrollability. Regarding the reality that the large-scale wind power is connected into power grid as well as the intermittent characteristics of wind power, if more accurate wind speed forecasts is obtained, that will be conducive to develop a scheduling plan by dispatching department timely, alleviate the adverse impact caused by intermittency characteristic of wind power, and ensure the security and stability of the power grid. With the aim of developing accurate tools for forecasting wind speed, this paper presents a novel hybrid intelligent forecasting model based on Least Square Support Vector Machine and the Markov model. However, the fluctuation of wind speed affected by many factors such as temperature, pressure, and humidity is a complex nonlinear dynamic system. So we group the space theory into the wind speed forecasting in this paper, and employ C-C method to determine the input form. Subsequently, the LSSVM model, which is optimized using the hybrid optimization algorithm PSOGSA, is employed to forecast the nonlinear parts of the wind speed for its faster convergence property. Additionally, because of the complex fluctuation of wind speed, the upper forecasting model may dig limited characteristics of wind speed fluctuations, and leave some important information that reflect the fluctuation of wind speed in residual series. Therefore, we construct an error correction model that is based on Markov model and FCM model to make adjustments with the hope of achieving better forecasting results. The simulation results indicate that the proposed model can outperform the other models discussed in this paper with respect to forecasting accuracy.