基于优化粒子群K-means聚类算法在风功率预测中的应用

Application of Wind Power Prediction Based on Particle Swarm Optimization K-Means Clustering Algorithm

由于风的间隙性、随机性、波动性很大,为了提高电网运行稳定性,有必要进行风功率预测。由于风电机组在实际当中运行受地理环境因素的限制,所以传统风电场建模进行风功率预测的方法不再适用,而通过K-means聚类算法求取风电机组的风速-功率曲线虽然准确性有所提高,但由于k-means聚类中心随机选择,仍然存在很多缺陷。本文提出利用优化粒子群的K-means聚类算法进行风功率预测,通过仿真结果验证了利用优化粒子群的K-means聚类算法进行风功率预测的准确性要比传统的方法以及K-means聚类算法的准确性高。

Because of the randomness, gap property and volatility of wind, it is necessary to predict wind power in order to improve the stability of power grid network operation. In the actual wind turbine operation due to the restrictions of geographic environmental factors, so traditional wind power forecasting method is no longer applicable. The accuracy of predicting wind power by using K-means clustering algorithm is increased, but due to the random K-means clustering center selection, there are still a lot of defects. This paper proposes a wind power prediction by using Particle Swarm Optimization （pso） and K-means clustering algorithm. The simulation results show that the accuracy of wind power prediction by using Particle Swarm Optimization and K-means clustering algorithm is better than traditional method and K-means clustering algorithm.