面向全景调控统一数据模型的缺失数据填补算法

缺失数据填补是构建调度控制系统全景数据的关键步骤之一,有助于保证全景数据的完整性和准确性。文中根据电力调度控制系统的历史数据特征,提出了一种面向全景调控统一数据模型的缺失数据填补算法。针对构建全景数据过程中出现的不完整数据,该算法采用改进的混沌遗传优化方法估计不完整数据的均值和协方差对应的最佳参数,再利用改进马尔可夫蒙特卡洛方法根据已知数据估计缺失数据。结果表明,该算法能通过较少的迭代次数获得不完整调控数据的最佳参数,可以提高缺失数据估计值的准确性,进而保证数据的完整性和准确性。

Missing Data Filling Algorithm for Uniform Data Model in Panoramic Dispatching and Control System

Filling missing data is one of the key steps in building panoramic data of the dispatching and control system to ensure the completeness and accuracy of information. According to the features of the historical data in the power dispatching and control system, a missing data filling algorithm for the uniform data model in the panoramic dispatching and control system is proposed. In view of the incomplete data appearing in the process of building panoramic data, the best parameters corresponding to the mean and covariance of the incomplete data are estimated by the improved chaos genetic optimization algorithm. Then, based on the known data, the missing data are estimated by the improved Markov Chain Monte Carlo(MCMC)method. The results show that the algorithm is able to get the best parameters of incomplete data with less iterations, while improving the estimated value accuracy of missing data to ensure the completeness and accuracy of the data.