基于Fast ICA和改进LSSVM的短期风速预测

Short-term Wind Speed Forecasting Based on Fast ICA Algorithm and Improved LSSVM Model

对风速的准确预测能有效减轻风电场对整个电网的不利影响,同时能提高风电场在电力市场中的竞争能力。首先提出一种基于快速独立分量分析算法和改进最小二乘支持向量机的风速预测模型,对运用fast ICA算法对风速时间序列进行多层分解,得到一系列的独立分量;然后运用改进最小二乘支持向量机模型对分解后的各独立分量风速进行预测;最后对各预测结果进行叠加作为最终的预测风速。算例结果表明,该预测模型能准确进行短期风速的预测。

The accuracy forecasting of the wind speed can effectively reduce the adverse effect of the wind farm on the power grid,in the meanwhile,it can strengthen the competition ability of wind farm in electricity market.In this paper,a short-term wind speed forecasting method based on fast independent compenent analysis （ICA） algorithm and the improved least squares support vector machine （LSSVM） is proposed.The wind speed time series are decomposed in different scales by the fast ICA algorithm.The decomposed wind speed time series are predicted separately by the improved LSSVM model,and then the predicted results are accumulated to be the final prediction.The numerical results indicate that the proposed method can be utilized to forecast the wind speed accurately.