考虑天气类型和相似日的IWPA-LSSVM光伏发电功率预测

为了提高光伏发电功率预测精度，根据不同天气类型下光伏输出功率特点，确定光伏发电功率预测模型的输入量。针对狼群算法（wolf pack algorithm,WPA）缺陷，对狼群游走位置和奔袭步长进行改进，得到改进狼群算法（improved wolf pack algorithm,IWPA），并通过IWPA对最小二乘支持向量机（least squares support vector machine,lSSVM）进行优化，建立了考虑天气类型和相似日的IWPA-LSSVM光伏发电功率预测模型。采用不同天气类型下的光伏发电功率数据进行仿真，结果表明：无论是晴天、多云还是阴雨天气，所提方法预测精度更高，回归拟合时的误差波动更小。

Forecast of Photovoltaic Power Based on IWPA-LSSVM Considering Weather Types and Similar Days

In order to improve the prediction accuracy of photovoltaic power, the input of the photovoltaic power prediction model is determined according to the characteristics of photovoltaic output power under different weather types. Aiming at the defects of the wolf pack algorithm (WPA), an improved wolf pack algorithm (IWPA) was obtained by improving the walking position and running step of the wolf pack. The least squares support vector machine (lSSVM) was optimized by IWPA, and an IWPA-LSSVM based photovoltaic power prediction model was established considering weather types and similar days. The photovoltaic power generation data under different weather types were used for simulation, and the simulation results show that the proposed method has a higher prediction accuracy and the error fluctuation of regression fitting is smaller whether the weather is sunny, cloudy or rainy.