基于用户特征挖掘的电网多维数据协同可观测性模型研究

Research on Collaborative Observability Model of Multidimensional Data in Power Grid Based on User Feature Mining

目前的电网数据协同可观测性模型主要针对单个或少数几个可观测源,未考虑电网中多维度数据,导致观测的数据偏差较大,对此设计一种基于用户特征挖掘的电网多维数据协同可观测性模型。构建电网拓扑结构后进行分区,建立不同区域下电机动力学方程,获取电网多维数据,对得到数据进行关联规则挖掘,获取频繁项集后进行校正,结合联机分析处理技术实现多维数据的存储。为验证模型在实际应用中的有效性,利用算例对模型进行测试,结果表明:设计的电网多维数据协同可观测性模型在不同的数据类型中的观测数据误差更小,且与实际电网数据之间的拟合精度更高,具有良好的实用性。

The current collaborative observability model for power grid data mainly targets a single or a few observable sources,without considering multi-dimensional data in the power grid,resulting in significant deviation in observed data.Therefore,a multi-dimensional collaborative observability model for power grid data based on user feature mining is designed.After constructing the topology structure of the power grid,partition it,establish motor dynamics equations in different regions,obtain multi-dimensional data of the power grid,mine association rules on the obtained data,obtain frequent itemsets,and correct them.Combined with online analytical processing technology,realize the storage of multi-dimensional data.To verify the effectiveness of the model in practical applications,numerical examples were used to test the model.The results showed that the designed multi-dimensional data collaborative observability model for power grids had smaller observation data errors in different data types and higher fitting accuracy with actual power grid data,indicating good practicality.