Partition Fault Diagnosis of Power Grids Based on Improved PNN and GRA

Abstract

With the increase of energy demand, the scale of power grid is expanding, and the difficulty of power grid fault diagnosis is increasing. Aiming at the problem of large power grid fault diagnosis, a method of partition fault diagnosis based on improved Probabilistic neural network (PNN) and gray relational analysis (GRA) integral is proposed. Firstly, the large power grid divided into small areas for fault diagnosis through power grid partition, which reduces the difficulty of fault diagnosis. Then the PNN diagnosis module is established by the PNN optimized by GA-CPSO for diagnosing the power grid fault. Finally, the faults in the overlapping area are reanalyzed by the GRA method, in order to realize the accurate fault diagnosis of the whole power grid. The feasibility and effectiveness of the method are analyzed by two cases. The diagnosis results show that the method can effectively identify the faults in the nonoverlapping area and the overlapping area, and has strong fault tolerance and high diagnosis accuracy.

Fault Diagnosis for Power Grids Based on Stochastic Self-Regulating Algorithm Under Disaster-Causing Weather

“…The protection device sends out a self-check alarm through the self-check technology [8]. Suppose that when the alarm information is missed or falsely reported, the self-check information is alarmed, but when the self-check alarm occurs, the alarm information may not necessarily be missed or falsely reported [9]. Set the self-inspection alarm index of the protection relay as r s , when the protection relay sends out a self-inspection alarm, 1 r s  , otherwise 0 r s  .…”

“…Currently, numerous power grid fault diagnosis methods utilizing smart technology have been developed worldwide, including expert systems [8], artificial neural network [9][10][11], Petri net [12,13], Bayesian network [14,15], spiking neural P system [16,17], optimization technology [18,19 ]Wait. Among them, the power system fault diagnosis method based on optimization technology has strict mathematical logic and strong fault tolerance.…”

Partition decoupling model and method in power distribution network, part II: A novel partitioning optimisation operation method

“…Sun et al [17] proposed a data-driven network partitioning method to select key bus and assess the risk of voltage violations in each control region, enabling real-time control of reactive power for PV and EV. Zhang et al [18] divide the large power grid into small areas for fault diagnosis through power grid partitioning, and then establishes a fault diagnosis module through probabilistic neural network and grey relational analysis integration to diagnose power grid faults. Zhao et al [19] propose a multi-objective island partition model for microgrid systems, which meets the needs of island partitions to restore power supply when distribution network failures.…”

“…Zhang et al. [18] divide the large power grid into small areas for fault diagnosis through power grid partitioning, and then establishes a fault diagnosis module through probabilistic neural network and grey relational analysis integration to diagnose power grid faults. Zhao et al.…”

Fault Diagnosis for Power Grids under Disaster Weather Based on a Random Self-regulating Algorithm

“…Consequently, the fault diagnosis of power grids has always plays an important role in the rapid analysis of fault events and fast restoration of power supply [5][6][7]. Consequently, a variety of fault diagnosis methods of power grids based on smart technology have been proposed, such as expert systems [8], neural networks [9][10][11], Petri nets [12,13], Bayesian networks [14,15], spiking neural P systems [16,17], the evidence theory [18,19] and the optimization technology [20,21].…”