Hybrid self‐learning controller for restoration of voltage power quality using optimized multilayer neural network

Abstract

The main objective of this paper is to develop a hybrid predictor based on intelligence techniques for dynamic voltage restorer (DVR) to estimate the reference load voltage and self-tuned voltage regulation to enhance voltage power quality issues. The best fitted predictor model is obtained by using the potential merits of metaheuristic algorithms coupled with Antlion Optimization (ALO) and Genetic Algorithm (GA). This article proposes ALO optimized multilayer perceptron (MLP) neural network (NN) control algorithm for appropriate selection of weights and biases to generate the subsequent switching signal with lower error rates for load voltage estimation. The ANFIS-GA control algorithm is implemented for automatic tuning of fuzzy rules with fewer membership functions (MFs) to obtain the perfect ANFIS (Takagi-Sugeno) predictive models for effective DC and AC link voltage regulation. The proposed hybrid controller counteracts the drawbacks of traditional ANN such as early convergence, slow learning mechanism, less probability of local entrapment, and difficulties to achieve the estimated target under parametric uncertainties, namely, sag, swell, unbalance, and distortion. The accuracy of the prediction model is computed by considering the error indices for the training and testing data set. The result confirms that the hybrid system ALO-MLP NN establishes satisfactory performance in extracting the reference with the least error values.

Solar photovoltaic‐interfaced shunt active power filter implementation for power quality enhancement in grid‐connected systems

“…Because it takes advantage of the NN and the fuzzy logic control (FLC), it has been highly preferred among all soft computing techniques. [28][29][30] The ANFIS-based technique has recently been used to enhance performance in various nonlinear systems. Hosseini and Zekri 31 describe how ANFIS has been shown to perform effectively in a variety of medical applications.…”

“…It possesses the capabilities of learning, remembering, and making decisions. Because it takes advantage of the NN and the fuzzy logic control (FLC), it has been highly preferred among all soft computing techniques 28–30 . The ANFIS‐based technique has recently been used to enhance performance in various nonlinear systems.…”

Design and development of leaky least mean fourth control algorithm for single‐phase grid‐connected multilevel inverter

“…The DSTATCOM can be configured to solve PQ problems such as harmonics filtering, reactive power compensation, voltage support in low‐voltage distribution networks, load balancing, and lowering SPV power fluctuations using several control algorithms. These algorithms include synchronous reference frame theory (SRFT), 10 P‐Q theory, 11 salp swarm optimization algorithm (SSOA), 12 cascaded enhanced second‐order general integrator with a prefilter (CESOGI‐WPF) control technique, 13 LCL‐filter‐based DSTATCOM, 14 ANOVA Kernel Kalman filter (AKKF), 15 Hermite function‐based ANN, 16 optimized multi‐layer perceptron (MLP) neural network, 17 Bernoulli polynomial‐based control technique, 18 proportionate affine projection algorithm (PAPA), 19 Laguerre polynomial (LP)‐based algorithm, 20 instantaneous symmetrical components theory (ISCT), 21 normalized least mean absolute third (NLMAT) algorithm, 22 and immune feedback control algorithm 23 . The DC link of the DSTATCOM can also be used to interface solar photovoltaic (SPV) arrays to extract DC power to three‐phase system 24 .…”

Advanced adaptive algorithm controlled single‐phase DSTATCOM operation during weak grid conditions

“…Adaptive neural network (ADALINE) control offers a better training procedure but suffers from the linear separability constraint of the perceptron. However, the hardware implementation of ADALINE requires a microcontroller with parallel processing 5–26 …”