Abstract
Smart meters are versatile metering devices and the basic equipment of power grid data acquisition. However, large installation quantity, wide installation area and long detection cycle aroused the requirement that the reliability prediction model with real-time analysis capability should be established to provide the basis for the maintenance and replacement plan of smart meters. Dynamic Bayesian network (DBN) has flexible structure, can update the model parameters according to the real-time information, which can meet the needs of real-time analysis. In this paper, the dynamic Bayesian Networks of smart meter is constructed according to the functional structure firstly. for expressing the degradation processes of functional modules and calculating the reliability curve of smart meter system secondly, the failure rates of functional modules are used to value the dynamic nodes. Finally, the backward reasoning ability of dynamic Bayesian network is used for fault diagnosis, and the weak links order in the smart meter system in different time is determined to provide a reference for the design optimization of smart meter.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have