Power Quality Enhancement in Hybrid AC/DC Microgrid using ANN

Abstract

This study proposes an intelligent control technique to enhance power quality in hybrid AC/DC microgrids integrated with renewable energy sources. Hybrid microgrids combine AC and DC subsystems to efficiently supply diverse loads, but they often suffer from voltage disturbances, harmonic distortion, and poor reactive power management due to nonlinear loads and fluctuating renewable generation. Conventional controllers such as PI and droop methods are limited in handling these dynamic and nonlinear operating conditions. To address these limitations, an Artificial Neural Network (ANN)-based controller is employed for controlling the interfacing converters between the AC and DC networks. The ANN adapts in real time by learning system behavior from voltage, current, and error signals, enabling effective harmonic reduction, improved voltage regulation, and balanced power flow. Simulation results obtained using MATLAB/Simulink confirm that the ANN-based controller achieves lower Total Harmonic Distortion (THD), faster transient response, and superior power quality compared to traditional control techniques.

Introduction

Hybrid AC/DC microgrids integrate renewable energy sources like solar PV and wind, providing flexibility to supply both AC and DC loads. However, intermittent generation and nonlinear loads often cause voltage fluctuations, harmonics, and power quality issues, challenging conventional control strategies such as PI or Fuzzy controllers.

Problem & Objective:
Traditional PI and Fuzzy controllers struggle with dynamic load changes and rapid renewable variability. The objective of this study is to implement an Artificial Neural Network (ANN)-based controller that can adapt in real time, improving voltage and current regulation, reducing Total Harmonic Distortion (THD), and enhancing overall microgrid stability.

Methodology:

• A hybrid AC/DC microgrid was modeled in MATLAB/Simulink, including PV, wind, battery storage, AC/DC converters, and nonlinear loads.

• Controllers tested: PI, Fuzzy Logic, and ANN.

• ANN was trained on system data to predict and correct voltage/current deviations, adapting dynamically to disturbances.

• Performance metrics: voltage stability, current stability, THD, and transient response.

Results:

• PI Controller: Voltage THD = 1.33%, Current THD = 3.85%; moderate harmonic suppression, slower transient response.

• Fuzzy Controller: Voltage THD = 0.80%, Current THD = 2.32%; better adaptation to load changes, smoother waveforms.

• ANN Controller: Voltage THD = 0.61%, Current THD = 1.29%; highest power quality, fast transient response, minimal overshoot, and excellent voltage/current regulation.

Conclusion

The Hybrid AC/DC Microgrid effectively integrates renewable energy sources, such as solar and wind, to deliver stable, reliable power. In this study, three control methods—PI, Fuzzy, and Artificial Neural Network (ANN)—were tested to improve system performance. The PI controller-maintained voltage but had a slower response and higher harmonics. The Fuzzy controller showed smoother operation and lower voltage ripple but struggled with sudden load changes. The ANN controller performed best, offering faster response, lower total harmonic distortion, and better voltage and current control. It achieved values of 0.80 V and 2.32 A, compared to PI (1.33 V, 3.85 A) and Fuzzy. Overall, the ANN controller proved to be the most efficient and intelligent option for maintaining stable and high-quality power in hybrid AC/DC microgrids.

References

[1] Kumar N., Singh B., and Mishra S., “ANN-based control approach for enhanced dynamic performance in hybrid AC/DC microgrids,” IEEE Transactions on Industry Applications, vol. 54, no. 6, pp. 6294–6304, Nov.–Dec. 2018. [2] Shanmugapriya M., Subramaniyan V., Mayurappriyan P. S., and Anuradha T., “Power management of a microgrid using fuzzy logic controller,” International Journal of Advanced Science and Technology (IJAST), vol. 29, no. 10S, pp. 7169–7180, Jun. 2020. [3] Sahoo S., Rout A. K., and Prusty R. C., “Performance analysis of hybrid microgrid using PI and fuzzy logic controllers,” International Journal of Emerging Electric Power Systems, vol. 31, no. 1, pp. 1–10, Jan. 2020. [4] Hossain M. J., Pota H. R., Ugrinovskii V., and Ramos R. A., “Robust control for power sharing and voltage regulation in microgrids with uncertainties,” IEEE Transactions on Smart Grid, vol. 4, no. 2, pp. 856–868, Jun. 2013. [5] Selvam R., Anuradha T., Jayakumar S., Venkatesh P. M., and Vijay Babu A. R., “IoT-based energy management for hybrid solar and wind energy systems,” International Journal of Future Generation Communication and Networking, vol. 13, no. 2, pp. 426–438, Apr. 2020. [6] Blaabjerg F., Chen Z., and Kjaer S. B., “Power electronics as efficient interfaces in distributed power generation systems,” IEEE Transactions on Power Electronics, vol. 19, no. 5, pp. 1184–1194, Sep. 2004. [7] Chen S. X., Gooi H. B., and Wang M. Q., “Optimal sizing of energy storage systems for microgrid applications,” IEEE Transactions on Smart Grid, vol. 3, no. 1, pp. 142–151, Mar. 2012.

Copyright

Copyright © 2026 Gundamalla Geethanjali, Sharma K. V.. 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.