摘要
针对气象参数预测的问题,提出应用经验模态分解法(EMD)对研究地区的历史气象数据按时间序列进行分解和特征提取,以粒子群优化的核极限学习机(PSO-KELM)进行预测的方法.该气象参数的预测结果将作为输电线路最大载流量概率模型的源数据.基于载流量密度函数的概率建模,提出基于气象参数的输电线路最大载流量的计算方法.某地区电网的应用分析结果表明,在用电高峰期时可根据气象参数预测结果动态调整输电线路的载流量,在确保输电线路安全可靠性的前提下,提高输电线路的输送能力.
In order to implement the decomposition and feature extraction of the historical meteorological data of the studied area according to solve the problem of meteorological parameter prediction,the empirical meteorological decomposition( EMD) method is used trying to the time series,and the prediction is performed in the framework of the kernel limit learning machine of the particle swarm optimization methods( PSO-KELM). The prediction results of the meteorological parameters are taken as the source data of the maximum current carrying capacity probability model of the transmission line,the computation method of the maximum current carrying capacity of the transmission line based on the probability modeling of the current density function and the meteorological parameters is proposed. The results of application analysis of a regional power grid show that the current capacity of the transmission line can be dynamically adjusted according to the prediction results of the meteorological parameters during the peak period of electricity consumption,and the transmission capacity of the transmission line can be improved under the premise of ensuring the safety and reliability of the transmission line.
作者
张斌
金涛
江岳文
叶荣
温步瀛
ZHANG Bin;JIN Tao;JIANG Yuewen;YE Rong;WEN Buyin(College of Electrical Engineering and Automation,Fuzhou University,Fuzhou,Fujian 350116,China;Economic and Technological Research Institute,State Grid Fujian Electric Power Co.Ltd.,Fuzhou,Fujian 350003,China)
出处
《福州大学学报（自然科学版）》
CAS
北大核心
2018年第6期853-859,共7页
Journal of Fuzhou University(Natural Science Edition)
基金
欧盟EP7国际科技基金资助项目(909880)
国家自然科学基金资助项目(61304260)
关键词
经验模态分解
核极限学习机
概率建模
动态增容
empirical mode decomposition
kernel extreme learning machine
probabilistic modeling
dynamic rating
