Dynamic Voltage Restorer (DVR) is a custom power device used as an effective solution in protecting sensitive loads from voltage disturbances in power distribution systems. The efficiency of the control technique, that conducts the switching of the inverters, determines the DVR efficiency.Proportional-Integral-Derivative (PID) control is the general technique to do that. The power quality restoration capabilities of this controller are limited, and it produces significant amount of harmonics – all of which stems from this linear technique’s application for controlling non-linear DVR. As a solution, this paper proposes an Artificial Neural Network (ANN) based controller for enhancing restoration and harmonics suppression capabilities of DVR. A detailed comparison of Neural Network controller with PID driven controller and Fuzzy logic driven controller is also illustrated, where the proposed controller demonstrated superior performance with a mere 13.5% Total Harmonic Distortion.
- Power quality
- Dynamic Voltage Restorer (DVR)
- Fuzzy logic
- Artificial Neural Network (ANN)
Fig. 1. Block diagram of the proposed DVR system to mitigate voltage instabilities.
EXPECTED SIMULATION RESULTS:
Fig. 2. Three phase sag mitigation based on ANN controlled DVR. (a) Instantaneous voltage at stable condition; (b) Instantantaneous voltage when sag occurs; (c) Voltage required to mitigate voltage sag; (d) Output voltage of the inverter circuit; (e) Generated PWM for inverter; (f) Instantaneous voltage after voltage restoration.
Fig. 3. Restored Voltage Using (a) PID controller; (b) Fuzzy controller; (c) ANN controller; (d)THD comparison: the least THD can be seen at ANN based DVR, the range of the harmonics is also truncated by a huge amount by this method.
DVRs are a popular choice for enhancing power quality in power systems, with an array of control system on offer to drive these devices. In this paper, application of ANN to operate DVR for providing better performance than existing systems to mitigate voltage sag, swell, and harmonics has been demonstrated. Problem statement and theoretical background, structure of the proposed method, training procedure of the ANN used have been described in detail. Simulation results showing the DVR performance during voltage sag have been presented. Comparison of the proposed method with the popular PID controller, and nonlinear Fuzzy controller has been carried out, where the proposed ANN controller appeared as the best option to restore system voltage while mitigating THD to the greatest extent.
 M. H. Bollen, R. Das, S. Djokic, P. Ciufo, J. Meyer, S. K. Rönnberg, et al., “Power quality concerns in implementing smart distribution-grid applications,” IEEE Transactions on Smart Grid, vol. 8, pp. 391-399, 2017.
 V. Khadkikar, D. Xu, and C. Cecati, “Emerging Power Quality Problems and State-of-the-Art Solutions,” IEEE Transactions on Industrial Electronics, vol. 64, pp. 761-763, 2017.
 X. Liang, “Emerging power quality challenges due to integration of renewable energy sources,” IEEE Transactions on Industry Applications, vol. 53, pp. 855-866, 2017.
 T. Sutradhar, J. R. Pal, and C. Nandi, “Voltage Sag Mitigation by using SVC,” International Journal of Computer Applications, vol. 71, 2013.
 F. M. Mahdianpoor, R. A. Hooshmand, and M. Ataei, “A new approach to multifunctional dynamic voltage restorer implementation for emergency control in distribution systems,” IEEE transactions on power delivery, vol. 26, pp. 882-890, 2011.