Slime Mold Algorithm Based Hybridized Artificial Neural Network Model for Efficient Automatic Voltage Regulation Control

Abstract

A novel approach for efficient automatic voltage regulation (AVR) control using hybridized artificial neural network (ANN) model has been proposed in this research work. The novel automatic voltage regulator tuning using an improved neural network has been proposed in this paper. Artificial neural network has been used as focused time delay neural network (FTDNN). Validation is performed by comparing with the methods of feed-forward backpropagation neural networks, cascade-forward backpropagation neural networks, Elman-recurrent neural networks, focused time-delay neural networks and Distributed Time Delay Neural Networks (DTDNN). This hybridized ANN model incorporated a metaheuristic method namely Slime Mold Algorithm (SMA) for obtaining improved result on AVR control. SMA has characteristics that uses adaptive weights to simulate the process to generate feedback from the movement of biooscillator-based slime molds in foraging, exploring, and exploiting areas. The performance of the proposed method is focused on speed and rotor angle. The proposed method is compared with other neural network methods in a broad set of benchmarks to verify system efficiency. Promising results were obtained in tuning the AVR under 30 %, 60 % and 90 % loading conditions at slime mold count of 50.