Power Quality Enhancement in Distributed PV-Wind Systems Using Neuro-Fuzzy Based Unified Power Quality Conditioner

Abstract

This project proposes an ANFIS-based Unified Power Quality Conditioner (UPQC) for a grid-connected hybrid system integrating solar PV and wind energy sources to address power quality issues such as harmonics, voltage imbalance, and current disturbances at the point of common coupling (PCC). Replacing the ANN controller in the series inverter with an Adaptive Neuro-Fuzzy Inference System (ANFIS) improves DC-link voltage regulation and grid current quality by generating reference DC current (Idc) with faster dynamic response and higher accuracy. Simulation results under varying conditions show that the ANFIS-based UPQC achieves lower total harmonic distortion (THD) and better transient performance than conventional ANN-based systems, offering a reliable and cost-effective solution for distributed generation power quality enhancement.

Introduction

This project aims to enhance power quality in renewable energy-based distributed generation (DG) systems that integrate solar photovoltaic (PV) and wind energy sources. Such systems often face challenges like voltage imbalance, harmonics, and current disturbances due to the intermittent nature of renewable sources. To address these issues, a Unified Power Quality Conditioner (UPQC) is used, and its performance is improved by incorporating an Adaptive Neuro-Fuzzy Inference System (ANFIS) controller into the series inverter. The ANFIS-tuned UPQC provides better DC-link voltage stability, faster dynamic response, and lower total harmonic distortion (THD) than conventional controllers.

The system comprises a series inverter (controlled by ANFIS for voltage regulation) and a shunt inverter (controlled by an ANN for harmonic compensation). It is simulated in MATLAB/Simulink using a grid-connected hybrid renewable setup that includes MPPT algorithms, DC-DC converters, and nonlinear load models. The design is tested under various scenarios such as load variation, voltage sag/swell, source disconnection, and harmonic injection.

Simulation results show that the ANFIS-based UPQC effectively mitigates harmonics and voltage disturbances, maintaining cleaner sinusoidal waveforms and stable DC-link voltage compared to ANN-controlled systems. The approach demonstrates high potential for improving power quality, system stability, and efficiency in modern hybrid renewable energy networks.

Conclusion

The proposed Unified Power Quality Conditioner (UPQC) developed for a hybrid renewable energy system comprising solar PV and wind sources. A key contribution lies in replacing the conventional Artificial Neural Network (ANN) used in the series controller with an Adaptive Neuro-Fuzzy Inference System (ANFIS), aiming to enhance the system\'s dynamic response and power quality performance. Simulation results under six different operating power conditions—including varying load profiles, generation states, and transient disturbances—demonstrate that the ANFIS-based controller consistently achieves better harmonic mitigation compared to the ANN-based approach. Improvements in Total Harmonic Distortion (THD) were observed across grid voltage, grid current, load voltage, and load current waveforms. The enhanced control strategy ensures smoother voltage regulation, stable current flow, and greater resilience under dynamic conditions. Overall, the proposed ANFIS-enhanced UPQC provides a reliable and effective solution for maintaining power quality in distributed generation systems integrated with renewable energy sources.

References

[1] B. Singh, A. Chandra, and K. Al-Haddad, “Power quality problems and mitigation techniques,” John Wiley & Sons, 2014. [2] Manku Priya , Chada Prathyusha, “A Novel ANFIS-controlled Unified Power Quality Conditioner (UPQC) for Enhanced Power Quality” ,IEEE 2024 [3] NOOR ZANIB ,MUNIRABATOOL ,SALEEM RIAZ ,AND FAWADNAWAZ, Performance Analysis of Renewable Energy Based Distributed Generation System Using ANN Tuned UPQC,IEEE Access, vol 10, 2022, 110034 [4] Leonardo Bruno Garcia Campanhol ,Sergio Augusto Oliveira da Silva Azauri Albano de Oliveira, “Power Flow and Stability Analyses of a Multifunctional Distributed Generation System Integrating a Photovoltaic System With Unified Power Quality Conditioner”, IEEE Access, VOL.34,NO.7,JULY2019 [5] Fathima S, Dr.Uma Syamkumar,”ANFIS driven DC Link Voltage Control and Power Quality Enhancement in PV-Battery Incorporated UPQC”,IEEE-2022 [6] M. K. Elango, T. Tamilarasi, “Improvement of Power Quality Using a Hybrid UPQC with Distributed Generator”.IEEE 2016 [7] M. Abedi, M. Tarafdar Hagh, and M. S. Ghazizadeh, “UPQC performance enhancement using ANN-based controllers under non-linear loads,” International Journal of Electrical Power & Energy Systems, vol. 43, no. 1, pp. 1036–1045, 2012. [8] R. Arulmurugan and N. Suthanthira Vanitha, “Simulation and performance analysis of UPQC using artificial intelligence-based controllers for power quality improvement,” International Journal of Electrical and Computer Engineering (IJECE), vol. 7, no. 1, pp. 1–10, 2017. [9] S. K. Khadem, M. Basu, and M. F. Conlon, “Power quality in grid connected renewable energy systems: Role of custom power devices,” International Journal of Renewable Energy Research, vol. 1, no. 3, pp. 1–8, 2011. [10] J. W. Dixon, J. J. Garcia, and L. E. Moran, “Control system for three-phase active power filter which simultaneously compensates power factor and unbalanced loads,” IEEE Transactions on Industrial Electronics, vol. 42, no. 6, pp. 636–641, 1995. [11] A. M. Sharaf, and A. A. Al-Khalidi, “An adaptive neuro-fuzzy controlled UPQC for power quality enhancement in distributed generation systems,” International Journal of Emerging Electric Power Systems, vol. 13, no. 1, 2012. [12] MATLAB and Simulink Documentation – MathWorks, www.mathworks.com S. K. Jain and P. Agarwal, “Fuzzy logic controlled shunt active power filter for power quality improvement,” Electric Power Applications, IEE Proceedings, vol. 149, no. 5, pp. 317–328, 2002. [13] H. Akagi, “Active harmonic filters,” Proceedings of the IEEE, vol. 93, no. 12, pp. 2128–2141, 2005. [14] R. Omar and N. A. Rahim, “Modeling and simulation for voltage sags/swells mitigation using dynamic voltage restorer (DVR),” Australian Journal of Basic and Applied Sciences, vol. 5, no. 12, pp. 379–396, 2011. [15] M. Kesler and E. Ozdemir, “Synchronous-reference-frame-based control method for UPQC under unbalanced and distorted load conditions,” IEEE Transactions on Industrial Electronics, vol. 58, no. 9, pp. 3967–3975, 2011. [16] S. A. Zulkifli, A. H. M. Yatim, and M. W. Mustafa, “Comparison between ANFIS and PI controller for UPQC,” International Journal of Electrical and Computer Engineering, vol. 6, no. 6, pp. 2596–2604, 2016.

Copyright

Copyright © 2025 Ellaboina Raghavendra Prasad, M. T. Naik. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.