基于天气聚类的光伏电站辐照度预测.docxVIP

ISSN 1671—1815 CN 11 —4688/T 引用格式：张 玉，王瑜琳.基于天气聚类的光伏电站辐照度预测[J].科学技术与工程，202X, 21(3)： 1030T036. Zhang Yu, Wang Yulin. The prediction of irradiation degree of photovoltaic power station based on weather clustering[ J ]. Science Technology and Engineering, 202X , 21(3)： 1030-1036. 基于天气聚类的光伏电站辐照度预测 张玉微，王瑜琳 (1.桂林理工大学机械与控制工程学院，桂林541004； 2.广西建筑新能源与节能重点实验室，桂林541004) 摘 要 太阳辐照度是影响光伏输出功率最直接、最显著的因素，其预测精度关系到电力系统部门的调度以及规划。受到地 理纬度、海拔高度、气候复杂性的影响，传统地表辐照度预测模型精度较低。基于辐照度的天文学模型结合天气类型进行辐 照度预测，通过建立太阳光照与地球大气层的几何模型，求解地外辐照度计算公式并修正晴天透明度系数，然后依据天气类 型与历史辐照度进行聚类分析,计算相应的权重系数，建立基于天气聚类的太阳辐照度预测模型。通过实测数据验证，与传 统的晴天模型、递推最小二乘法(recursive least square,RLS)模型、小波变换(wavelet transform, WT)模型、相比，夭气聚类模型 的适应性更强、准确率更高、误差更小。 关健词 光伏电站；辐照度；天气类型；聚类 中图法分类号TM615； 文献标志码A The Prediction of Irradiation Degree of Photovoltaic PowerStation Based on Weather Clustering ZHANG Yu* 2, WANG Yu4in (I. School of Mechanical and Control Engineering, Guilin University of Technology, Guilin 541004, China； 2. Guangxi Key Laboratory of New Energy and Energy for Buildings, Guilin 541004, China) [Abstract Solar irradiance is a kind of most direct and significant factor affecting photovoltaic output power, and its prediclion accuracy is related to the scheduling and planning of power system departments. Due to the influence of geographic latitude, altitude and climate complexity, the accuracy of traditional suiface irradiance prediction models is low. Based on the irradiance astronomy model combined with the weather type to predict irradiance, the calculation formula for extrateiTestnal irradiance was solved and the transparency coefficienl of the sunny day was corrected by establishing a geometric model of the sun illumination and the earth atmosphere. Then according to the weather type and historical irradiance, the cluster analysis was performed, the corresponding weight coefficient was calculated, and the solar irradiance prediclion model based on weather clustering was established. Through the verification of the measured data, compare