欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
农网改造中变电站的规划是一项核心工作，其中对变电站所带区域的负荷，称为自然区域负荷，进行准确的预测又是关键。分析了典型的农村用电量结构，将之分为四类，并对其中三类主要用电量进行单独分析和预测。首先利用粗糙集理论对每类用电量的影响因素集合进行约简，之后利用支持向量回归机对其进行分别预测。最后的预测结果是三个预测结果相加再按比例加上其它用电量。实验结果表明粗糙集结合支持向量回归机的方法比传统方法有比较大的优势，预测精度比较好。
英文摘要：
Layout of transformer substations is a central job in rebuilding rural grid, in which accurate load forecasting for the area supplied by transformer substations, called natural area, is a key element. Typical composition of electric power consumed in countryside, which is divided into four sub-classes, is analyzed. Among the four sub-classes three main sub-classes are analyzed and forecasted separately. At first, influence factors set for each sub-class is reduced based upon rough set theory, then forecasted by support vector regression for every sub-class. The final forecasting result is three individual forecasts plus one addtional forecast pro rata. Experiment shows that rough set combined with SVM regression is superior to traditional methods and has a good prediction precision.
同期刊论文项目
同项目期刊论文
Multi-objective coordination optimal model for new power intelligence center based on hybrid algorit
Research on the wavelet neural networks based on data mining and its application in daily load forec
位置：