Implementation of adaptive neuro fuzzy inference system and back propagation neural network for the appraisal of power system contingency analysis

Yusufu Yakubu Yusufu Yakubu,Mohammed Mukhtar Magaji Mohammed Mukhtar Magaji,Usman Aliyu Magaji Usman Aliyu Magaji,Mb Jibril Mb Jibril,Bara’u Gafai Najashi Bara’U Gafai Najashi

doi:10.30574/gscaet.2022.3.1.0024

Yusufu Yakubu Yusufu Yakubu, Mohammed Mukhtar Magaji Mohammed Mukhtar Magaji + Show 3 more

Open Access

https://doi.org/10.30574/gscaet.2022.3.1.0024

Copy DOI

Abstract

Power System Security and Contingency analysis is one of the most important tasks in power systems. In operation, contingency analysis assists engineers to operate the power system at a secure and safe operating point where equipment are loaded within their safe operating area (SOA). Power is dispatched to customers with acceptable quality standards. The results of off-line load flow calculations are used to estimate performance indices (PI flow, PI V). MATLAB toolbox was the proposed methodology used for the implementation. The proposed approach for contingency analysis was found to be appropriate for screening and ranking fast voltage and line flow contingencies.

Highlights

Power system security is a method of achieving, planned to maintain the system during the cost of processor activities when the components stop or fail to respond [1]
This study presented the comparative analysis of both Back Propagation neural network (BPNN) nonlinear artificial intelligence model (ANFIS) for the estimation ofImplementation of adaptive Neuro Fuzzy inference system, and Back Propagation Neural Network for the Appraisal of Power system Contingency analysisthe modeling results were evaluated using R2, R, Root mean square error (RMSE), and Mean square error (MSE) in both training and testing phase
It can be clearly observed that Adaptive Neuro Fuzzy Inference System (ANFIS) gives out a better result as compared in the columns of tables that correspond to the contingency ranking load condition as it is nearer to the same obtained by the Analytical technique (NR) compared to Artificial Neural Network (ANN)

Summary

Introduction

Power system security is a method of achieving, planned to maintain the system during the cost of processor activities when the components stop or fail to respond [1]. Transmission and sub-transmission power systems supply many customers and there is a need for defensive operation for more reliability in the transmission and subtransmission line in case of component failure or malfunctioning [2]. This can be remedy by applying the single contingency policy (SCP) [3]. Back propagation-neural network (BPNN) is a multi-layer feed-forward network trained according to error Back propagation and is one of the networks used to a great extent, and the network can be used to study and store a great deal of mapping relationship of input/output model, and no need to expose in advance the mathematical equation that describes these mapping relations [5]. This paper focuses on the analysis of the characteristics and mathematical theory of the Back Propagation neural network (BPNN) and points out the fault of the Back Propagation neural network (BPNN) algorithm as well as several methods for improvement [6]

Objectives

Methods

Results

Conclusion