Abstract
In recent years, due to shifts in the global climate and environment, a variety of extreme weather events have become more frequent, resulting in numerous accidents. The increased occurrence of extreme weather not only poses risks to the functioning of the power grid but also impacts the accuracy of power grid fault diagnosis outcomes. By integrating research on power grid fault risks during extreme weather events, this study introduces weather data and self-check information to develop a fault diagnosis approach for the power grid based on a random self-regulating algorithm. The fault diagnosis method comprises two main components: Firstly, an analytical model for fault diagnosis is constructed using alarm data, weather information, and self-check data from the affected power outage area. Three types of self-adjusting trust factors are incorporated into the model to enhance its fault diagnosis capabilities in the context of extreme weather events. Subsequently, a random self-regulating algorithm is applied to optimize the model and generate a hypothesis regarding the fault. Through a simulation test on a sample calculation, the results demonstrate that the fault diagnosis method exhibits robust fault tolerance towards abnormal operation of protective devices and inaccuracies in alarm data.