Fault Detection and Self-healing Algorithm of High Reliability Distribution Network Based on Big Data Analysis Method

The intelligentization of high-reliability distribution network is an important aspect of the construction of a unified and robust smart grid, and self-healing is the core and important approach to the intelligentization of the distribution network. Currently, although many intelligent algorithms have been introduced in fault diagnosis of distribution networks, the methods are still relatively limited in terms of practical application. In terms of self-healing control, due to the complex topology and large amount of protection information in actual power grids, there are often cases of long recovery time and low power quality. Big data analysis technology can empower fault detection and self-healing of high-reliability distribution networks. Neural networks, as a typical big data analysis technology, are widely used in smart grids. In this paper, a fault diagnosis method based on fuzzy min-max neural network classifier is proposed. Secondly, a self-healing control method based on multi-agent particle swarm optimization is proposed. Based on the accurate positioning of the fault location, switch reconfiguration is performed through this algorithm, which improves the reliability and robustness of the smart distribution network, shortens the switch reconfiguration time, and achieves self-healing evaluation criteria.