Power Quality Improvement using Artificial Neural Network Controller based Dynamic Voltage Restorer

Authors

  • Shubham Yadav  Electrical Engineering, RSRRCET Bhilai, Chhattisgarh, India
  • Manish Chandrakar  Electrical Engineering, RSRRCET Bhilai, Chhattisgarh, India

Keywords:

Power quality, Dynamic voltage restorer, Proportional Integral, Artificial Neural Network (ANN)

Abstract

The importance of power quality (PQ) concerns amplifies as the number of voltage-sensitive loads rises within distribution systems. Industrial distribution systems commonly face voltage disturbances, which primarily include voltage sags, voltage swells, and voltage unbalances. Voltage sags or swells can occur throughout the entire system or affect a substantial portion of it due to faults occurring at either the transmission or distribution level. Additionally, when the system experiences high demand, a notable voltage reduction, or drop, can take place. Voltage sag and swell can lead to the failure or shutdown of sensitive equipment found in industries like semiconductor or chemical plants. These voltage disturbances can also result in a significant current imbalance, potentially causing fuses to blow or breakers to trip. The consequences of these effects can be financially burdensome for customers, ranging from minor fluctuations in quality to costly production downtime and equipment damage. The DVR (Dynamic Voltage Restorer) is a power electronic converter-based mitigation device that is connected in series. It is widely recognized as an effective custom power device for mitigating the adverse effects of voltage disturbances originating from upstream sources on sensitive loads. While the primary purpose of the DVR is to mitigate voltage sags and swells, there are instances where additional functionalities, such as harmonic compensation and reactive power compensation, are incorporated into the device. When it comes to controlling the DVR, the most commonly employed option is the PI (Proportional-Integral) controller. It offers a straightforward structure and can deliver satisfactory performance across a broad operational range. However, the main challenge with this simple controller lies in selecting the appropriate PI gains. Fixed gains may not always provide the desired control performance when there are changes in system parameters and operating conditions. Therefore, an online tuning process is necessary to ensure that the controller can effectively handle all variations in the system. The paper introduces the Dynamic Voltage Restorer (DVR) and explains its operating principle. Additionally, it presents a proposed controller based on Artificial Neural Network. The performance of ANN controller has been analysed using MATLAB Simulink model in this paper.

References

  1. Shuhong, Kong & Zhongdong, Yin & Renzhong, Shan & Weidong, Shang. (2009). A Survey on the Principle and Control of Dynamic Voltage Restorer. 57 - 60. 10.1109/ICEET.2009.250.
  2. R. Omar and N. A. Rahim, "New control technique applied in dynamic voltage restorer for voltage sag mitigation," 2009 4th IEEE Conference on Industrial Electronics and Applications, Xi'an, China, 2009, pp. 848-852, doi: 10.1109/ICIEA.2009.5138322.
  3. Kantaria R. A. ; Joshi S.K.; Siddhapura K. R., "A novel technique for mitigation of voltage sag/swell by Dynamic Voltage Restorer (DVR)," Electro/Information Technology (EIT), 2010 IEEE International Conference on , vol., no., pp.1,4, 20- 22 May 2010.
  4. Elango, S.; Chandra Sekaran, E., "Mitigation of Voltage Sag by Using Distribution Static Compensator (D-STATCOM)," Process Automation, Control and Computing (PACC), 2011 International Conference on, vol., no., pp.1,6, 20- 22 July 2011.
  5. M. Faisal, M. S. Alam, M. I. M. Arafat, M. M. Rahman and S. M. G. Mostafa, "PI controller and park's transformation based control of dynamic voltage restorer for voltage sag minimization," 2014 9th International Forum on Strategic Technology (IFOST), Cox's Bazar, Bangladesh, 2014, pp. 276-279, doi: 10.1109/IFOST.2014.6991121.
  6. P. V. Dhote, B. T. Deshmukh and B. E. Kushare, "Generation of power quality disturbances using MATLAB-Simulink," 2015 International Conference on Computation of Power, Energy, Information and Communication (ICCPEIC), Melmaruvathur, India, 2015, pp. 0301-0305, doi: 10.1109/ICCPEIC.2015.7259479.
  7. M. H. Bollen, R. Das, S. Djokic, P. Ciufo, J. Meyer, S. K. Rönnberg, et al., "Power quality concerns in implementing 5571 smart distribution-grid applications," IEEE Transactions on Smart Grid, vol. 8, pp. 391-399, 2017.
  8. C. Subramani, A. A. Jimoh, S. H. Kiran and S. S. Dash, "Artificial neural network based voltage stability analysis in power system," 2016 International Conference on Circuit, Power and Computing Technologies (ICCPCT), Nagercoil, India, 2016, pp. 1-4, doi: 10.1109/ICCPCT.2016.7530255.
  9. M. S. Haque Sunny, E. Hossain, M. Ahmed and F. Un-Noor, "Artificial Neural Network Based Dynamic Voltage Restorer for Improvement of Power Quality," 2018 IEEE Energy Conversion Congress and Exposition (ECCE), Portland, OR, USA, 2018, pp. 5565-5572, doi: 10.1109/ECCE.2018.8558470.
  10. Tekwani, P. N. & Chandwani, Ashwin & Sankar, Sagar & Gandhi, Neel & Chauhan, Siddharthsingh. (2020). Artificial neural network-based power quality compensator. International Journal of Power Electronics. 11. 256. 10.1504/IJPELEC.2020.105151.

International Journal of Scientific Research in Science, Engineering and Technology

Downloads

Published

2023-06-16

Issue

Volume 10, Issue 3, May-June-2023

Section

Research Articles

License

Copyright (c) IJSRSET

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Shubham Yadav, Manish Chandrakar "Power Quality Improvement using Artificial Neural Network Controller based Dynamic Voltage Restorer" International Journal of Scientific Research in Science, Engineering and Technology (IJSRSET), Print ISSN : 2395-1990, Online ISSN : 2394-4099, Volume 10, Issue 3, pp.464-470, May-June-2023.