基于果蝇优化算法的风功率预测数据可信度量化分析

Confidence and Quantitative Analysis of Wind Power Prediction Data Based on Fruit Fly Optimization Algorithm

针对风功率预测数据精度较低,可信度难以度量的问题,研究了基于果蝇优化算法的风功率预测数据可信度量化分析方法。采用一次指数平滑方法平滑处理风功率预测的历史风速数据,将完成平滑处理的数据输入LSSVM风功率预测模型中,该模型设置线性最小二乘系统作为支持向量机的损失函数。选取果蝇优化算法优化LSSVM风功率预测模型,设置风功率预测的均方根误差作为果蝇优化算法的适应度函数,获取LSSVM风功率预测模型的最优参数,量化分析了风功率预测数据可信度。实验结果表明,该方法预测风功率的均方根误差低于0.3,具有较高的风功率预测数据可信度。

Aiming at the problem of low accuracy and poor reliability of wind power prediction data,a confidence and quantitative analysis method of wind power prediction data based on fruit fly optimization algorithm is studied.The one-time exponential smoothing method is used to smooth the historical wind speed data of wind power prediction,and the smoothed data are input into the LSSVM wind power prediction model,which sets the linear least square system as the loss function of support vector machine.We select the fruit fly optimization algorithm to optimize the LSSVM wind power prediction model,set the root mean square error of wind power prediction as the fitness function of the fruit fly optimization algorithm,obtain the optimal parameters of the LSSVM wind power prediction model,and quantitatively analyze the reliability of the wind power prediction data.The experimental results show that the root mean square error of wind power predicted by this method is less than 0.3,which has high reliability of wind power prediction data.