文章基本信息

标题：Cluster analysis for classification and forecasting of solar irradiance in Durban, South Africa
其他标题：Cluster analysis for classification and forecasting of solar irradiance in Durban, South Africa
本地全文：下载
作者：Govender, Paulene ; Brooks, Michael J. ; Matthews, Alan P. 等
期刊名称：Journal of Energy in Southern Africa
印刷版ISSN：1021-447X
出版年度：2018
卷号：29
期号：2
页码：51-62
DOI：10.17159/2413-3051/2017/v29i2a4338
出版社：Energy Research Centre
摘要：Clustering of solar irradiance patterns was used in conjunction with cloud cover forecasts from Numerical Weather Predictions for day-ahead forecasting of irradiance. Beam irradiance as a function of time during daylight was recorded over a one-year period in Durban, to which k-means clustering was applied to produce four classes of day with diurnal patterns characterised as sunny all day, cloudy all day, sunny morning-cloudy afternoon, and cloudy morning-sunny afternoon. Two forecasting methods were investigated. The first used k-means clustering on predicted daily cloud cover profiles. The second used a rule whereby predicted cloud cover profiles were classified according to whether their average in the morning and afternoon were above or below 50%. In both methods, four classes were found, which had diurnal patterns associated with the irradiance classes that were used to forecast the irradiance class for the day ahead. The two methods had a comparable success rate of about 65%; the cloud cover clustering method was better for sunny and cloudy days; and the 50% rule was better for mixed cloud conditions. Highlights: • Clustering produced four classes of beam irradi-ance profiles for Durban • Numerical weather prediction cloud cover patterns into four classes • Association of classes used for day-ahead forecasting of beam irradiance • Forecasting had a moderate success rate of about 65%
其他摘要：Clustering of solar irradiance patterns was used in conjunction with cloud cover forecasts from Numerical Weather Predictions for day-ahead forecasting of irradiance. Beam irradiance as a function of time during daylight was recorded over a one-year period in Durban, to which k-means clustering was applied to produce four classes of day with diurnal patterns characterised as sunny all day, cloudy all day, sunny morning-cloudy afternoon, and cloudy morning-sunny afternoon. Two forecasting methods were investigated. The first used k-means clustering on predicted daily cloud cover profiles. The second used a rule whereby predicted cloud cover profiles were classified according to whether their average in the morning and afternoon were above or below 50%. In both methods, four classes were found, which had diurnal patterns associated with the irradiance classes that were used to forecast the irradiance class for the day ahead. The two methods had a comparable success rate of about 65%; the cloud cover clustering method was better for sunny and cloudy days; and the 50% rule was better for mixed cloud conditions. Highlights: • Clustering produced four classes of beam irradi-ance profiles for Durban • Numerical weather prediction cloud cover patterns into four classes • Association of classes used for day-ahead forecasting of beam irradiance • Forecasting had a moderate success rate of about 65%
关键词：numerical weather prediction; cloud cover; k-means; classes.
其他关键词：numerical weather prediction;cloud cover;k-means;classes