基于混沌理论及PSO-LS-SVM的新能源出力短期预测方法

为减少新能源出力的不确定性对并网系统安全稳定的影响,提高新能源出力预测的精准度成为新能源系统所需解决的首要问题。以光伏系统为例,基于光伏出力时间序列的混沌特性,提出了一种基于混沌理论及最小二乘支持向量机的光伏出力短期预测模型。通过与实际数据和改进前模型进行对比,证明了该模型在光伏出力短期预测中的有效性。

Short-term Prediction Method of New Energy Output Based on Chaos Theory and PSO-LS-SVM

In order to reduce the impact of new energy uncertainty on the safety and stability of the grid-connected system, improving the accuracy of new energy forecast has become the primary problem to be solved in new energy system. Taking photovoltaic system as an example, based on the chaotic characteristics of photovoltaic output time series, a short-term prediction model of photovoltaic output is proposed based on chaos theory and PSO-LS-SVM. The validity of the model in short-term prediction of photovoltaic output is proved by comparing with the actual data and the model before improvement.