Neural Networks Based Shunt Hybrid Active Power Filter for Harmonic Elimination

Muzammil Iqbal,Muhammad Nadeem Rafiq,Saleem Akhtar,Ali R Ansari,Muhammad Bilal Qureshi,Raheel Nawaz,Mujtaba Hussain Jaffery,Muhammad Jawad

doi:10.1109/access.2021.3077065

Abstract

The growing use of nonlinear devices is introducing harmonics in power system networks that result in distortion of current and voltage signals causing damage to power distribution systems. Therefore, in power systems, the elimination of harmonics is of great significance. This paper presents an efficient techno-economical approach to suppress harmonics and improve the power factor in power distribution networks using Shunt Hybrid Active Power Filters (SHAPF) based on neural network algorithms like Artificial Neural Network (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Recurrent Neural Network (RNN). The objective of the proposed algorithms for SHAPF is to enhance system performance by reducing Total Harmonic Distortion (THD). In our filter design approach, we tested and compared conventional pq0 theory and neural networks to detect the harmonics present in the power system. Moreover, for the regulation of DC supply to the inverter of the SHAPF, the conventional PI controller and neural networks-based controllers are used and compared. The applicability of the proposed filter is tested for three different nonlinear load cases. The simulation results show that the neural networks-based filter control techniques satisfy all international standards with minimum current THD, neutral wire current elimination, and small DC voltage fluctuations for voltage regulation current. Furthermore, the three neural network architectures are tested and compared based on accuracy and computational complexity, with RNN outperforming the rest.

Highlights

The performance of electrical devices has been steadily improving with the advancements in power electronics
We present the use of Shunt Hybrid Active Power Filters (SHAPF) for harmonic elimination in the power distribution systems
Instead of presenting a completely new technique for harmonic detection, most researchers have tried to improve the response of p-q and d-q techniques with the use of new control methods based on Phase Locked Loop (PLL) and low pass filters

Summary

INTRODUCTION

The performance of electrical devices has been steadily improving with the advancements in power electronics. Instead of conducting in a smooth manner, the nonlinear loads draw current in short pulses and introduce harmonics in the system. This issue of harmonics is not confined to industrial users; it affects the domestic users as well. To limit the extent of harmonics in the power system, international standards, such as IEEE-519 and IEC61000 have been introduced [1] These standards suggest possible recommendations to minimize the current and voltage distortions to a tolerable level. The use of capacitor banks to eliminate harmonics in voltage and current signals is not encouraged. We present the use of Shunt Hybrid Active Power Filters (SHAPF) for harmonic elimination in the power distribution systems.

LITERATURE REVIEW

REFERENCE CURRENT CALCULATION USING PQ0 THEORY

NEURAL NETWORK BASED PREDICTIVE CONTROL SCHEME

ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM

RESULTS AND DISCUSSIONS

CONCLUSIONS AND FUTURE WORK