Research On Comprehensive State Evaluation Method Of Intelligent Microgrid Based On Data Mining

The self-healing of intelligent microgrid is one of its biggest features,and it is also the key guarantee to ensure the safe,stable,economic,reliable and environmental protection operation of the system.At present,the self-healing control technology of intelligent microgrid is mainly focused on the theoretical and technical research,and the exploration of the specific implementation approach is still in the initial stage.In order to realize self-healing of smart microgrid,it is necessary to evaluate the realtime running status of smart microgrid accurately.Therefore,this paper studies the real-time evaluation method of smart microgrid operation,which lays a foundation for selecting appropriate self-healing control strategy.Firstly,the difference and correlation between smart microgrid and conventional power system are analyzed,evaluation indicators that can truly reflect the operating status of smart microgrid are selected,and a scientific evaluation system is constructed.The entropy weight method is used to obtain the weight of each indicator in the evaluation system.Secondly,according to the principle of maximum membership degree,the state of a single node of smart microgrid is comprehensively evaluated.Thirdly,based on node load level and correlation degree between nodes and paths,a new node weight evaluation method based on node load and path is proposed to obtain real-time detection status of the whole intelligent microgrid.Finally,the BP neural network algorithm based on time series is used to predict the state of the smart microgrid,and the 10 k V smart microgrid in a region is verified by an example.This paper evaluates the overall operating status of smart microgrid,and provides a new idea...