Emergency control of load shedding based on coordination of artificial neural network and Analytic Hierarchy Process Algorithm

Abstract

This paper proposed a new emergency control of load shedding model to ensure sustained power system stability when short circuit incidents occur based on the basis of coordination algorithms applied technology knowledge: K-means clustering, artificial neural network and analytic hierarchy process algorithms. This is a load shedding model allowing to make quick decisions of strategy selection, to reduce the decision time, to recovery time and to improve frequency stability compared to traditional methods. The main purpose of the presented coordinated control system is to reduce the recovery time and maintain dynamic stability of power systems. K-means clustering algorithm divided instability mode into clusters. The results of analysis of these clusters were used as the basis for classification control. Load shedding strategies were built consists of pre-designed rules based on AHP algorithm. The load shedding was considered to cut the less important factor loads first for contributing to reduce the damages. The effectiveness of the algorithm was demonstrated through the load shedding experiment on IEEE 39 bus 10 generators compared with traditional methods.