Classification of Fault Using Artificial Neural Network and Power Quality Improvement Using DVR in a PV Integrated Hybrid Power System

Pal, Kumaresh; Akella, Ashok Kumar; Namrata, Kumari; Pati, Subhendu

doi:10.1109/iciccsp53532.2022.9862499

Cited by 9 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the event of a disruption, DVR is used to enhance the real power of the inverter. The DVR may be utilized as a voltage sag restorer and voltage distortion compensator with ANN to reduce harmonics and voltage sag/swell caused by zero sequence components when attached between the power source and the booster transformer [143].…”

Section: Artificial Neural Network Control (Ann)mentioning

confidence: 99%

A review on the state of the art of dynamic voltage restorer: topologies, operational modes, compensation methods, and control algorithms

Shah,

Ullah,

Nouman

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

The state-of-the-art dynamic voltage restorers (DVRs) have advanced significantly in recent years. Modern DVRs can detect voltage sags or dips on the power line in real-time and are able to rapidly inject a compensating voltage to maintain a constant voltage at the load. This helps to improve the power quality of the electrical distribution system and to protect sensitive electronic equipment from voltage fluctuations. One key development in the field of DVRs has been the use of advanced control algorithms that enable the DVR to track the voltage more accurately on the power line and to inject a compensating voltage more accurately. These algorithms can be implemented using digital signal processors (DSPs) or field-programmable gate arrays (FPGAs), which allow for fast and precise control of the DVR. Another important development has been the use of high-frequency inverters in DVRs. These inverters can operate at much higher frequencies than traditional inverters, which allows them to switch on and off more quickly and to inject a more precise compensating voltage. This can help to further improve the power quality of the electrical distribution system. Overall, the state-of-the-art DVR technology continues to evolve, and new advances are being made all the time to improve the performance and reliability of these devices.

show abstract

Section: Artificial Neural Network Control (Ann)mentioning

confidence: 99%

A review on the state of the art of dynamic voltage restorer: topologies, operational modes, compensation methods, and control algorithms

Shah,

Ullah,

Nouman

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

show abstract

“…This transformation can remove zero sequence components from abc components. The PI controllers with d-and qcoordinates are distinct from one another [17,18]. Figure 4 depicts a PI controller that regulates the overall error as well as the integral value.…”

Section: A Mathematical Model For Voltage Injection By Dvrmentioning

confidence: 99%

Improvements in Voltage Profile of JDW Sugar Mills’ Jawar Distribution Feeder RYK Pakistan Using ANN Based Dynamic Voltage Restorer

Siddique,

Mujahid,

Aslam

et al. 2024

JESA

View full text Add to dashboard Cite

Voltage-related power quality issues, including voltage sag, swell, and total harmonic distortion (THD), have become a significant concern in recent times. These issues, particularly harmonics, are known to degrade utility performance and lifespan, necessitating urgent rectification to ensure a high-quality power supply. This is crucial as our generation increasingly depends on electricity for enhanced living standards. Flexible AC transmission system (FACTS) devices are gaining considerable interest as effective solutions to these problems. Among these, the dynamic voltage restorer (DVR) is particularly noteworthy for its potential to reduce power quality disturbances in the distribution network. In this study, we developed a DVR based on an artificial neural network (ANN) controller. The activation function employed was Train LM for the input and hidden layers, and pure linear for the output layer, with the Levenberg Marquardt back propagation (LMBP) serving as the training algorithm. The designed model was then tested to tackle voltage-related power quality problems in the distribution network of Jamal Din Wala (JDW) sugar mills. The comprehensive model featured a three-phase voltage source inverter, a scheme utilizing rotating reference frame theory, and sine pulse width modulation (SPWM) for voltage sag and swell sensing along with insulated gate bipolar transistor (IGBT) switching. We analyzed three types of DVR output defects using MATLAB/Simulink and compared the results of the ANN controller with those of a conventional PI controller. The DVR output was modeled in MATLAB/Simulink for three types of defects and two degrees of voltage sag and swell. The results demonstrated that the DVR effectively mitigated voltage sags and swells in the JDW sugar mills distribution network. Furthermore, during the validation of the proposed ANN, a comparison of results with the conventional PI controller under balanced and unbalanced sags and swells showed a significant improvement. The ANN achieved a voltage restoration of up to 99.8% and a total harmonic distortion of 13.5%, a marked improvement over the PI controller, which achieved 97% voltage restoration and 19.5% total harmonic distortion, respectively.

show abstract

“…In the realm of distributed systems, voltage sag and swell are acknowledged as influential factors impacting power quality for sensitive loads [41]. To address this issue, a controller system is developed, utilizing a combination of linear and non-linear fuzzy logic [27], particle swarm optimization (PSO) [12], ant lion optimizer-optimized artificial neural network (ALO-ANN) [24] and Grasshopper Optimization Algorithm models [29]. This literature review [11] [41] provides a concise overview [23] of the configurations and control strategies of the Dynamic Voltage Restorer (DVR) as described in previous research [34] [39].…”

Section: Literature Reviewmentioning

confidence: 99%

“…The DVR, as a power electronic device [11], is specifically engineered to identify voltage dips and introduce corrective voltage adjustments to return the load voltage to its intended standard level. By incorporating an ANN [12][13][14] within the control scheme of the DVR, the system can intelligently and accurately detect voltage sags [15] and determine the optimal compensation strategy based on the sag characteristics.…”

mentioning

confidence: 99%

Intelligent Voltage Sag Compensation Using an Artificial Neural Network (ANN)-Based Dynamic Voltage Restorer in MATLAB Simulink

Mohammed Uddin,

A Bakar

2023

IJIE

View full text Add to dashboard Cite

An innovative Dynamic Voltage Restorer (DVR) system based on Artificial Neural Network (ANN) technology, implemented in MATLAB Simulink, accurately detects, and dynamically restores voltage sags, significantly improving power quality and ensuring a reliable supply to critical loads, contributing to the advancement of power quality enhancement techniques. Voltage sags are a prevalent power quality concern that can have a significant impact on sensitive electrical equipment. An innovative approach to address voltage sags through the operation of a Dynamic Voltage Restorer (DVR) based on Artificial Neural Network (ANN) technology. The proposed system, developed using MATLAB Simulink, leverages the ANN's capabilities to accurately detect voltage sags and dynamically restore the voltage to the affected load. The ANN is trained using a comprehensive dataset comprising voltage sag events, enabling it to learn the intricate relationships between sag characteristics and optimal compensation techniques. By integrating the trained ANN into the DVR control scheme, real-time compensation for voltage sags is achieved. The effectiveness of the proposed system is rigorously evaluated through extensive simulations and performance analysis. The results demonstrate the superior performance of the ANN-based DVR in terms of voltage sag detection accuracy and restoration precision. Consequently, the proposed system presents an intelligent and adaptive solution for voltage sag compensation, ensuring a reliable and high-quality power supply to critical loads. This research contributes to the advancement of power quality enhancement techniques, facilitating the implementation of intelligent power system.

show abstract

Classification of Fault Using Artificial Neural Network and Power Quality Improvement Using DVR in a PV Integrated Hybrid Power System

Cited by 9 publications

References 10 publications

A review on the state of the art of dynamic voltage restorer: topologies, operational modes, compensation methods, and control algorithms

A review on the state of the art of dynamic voltage restorer: topologies, operational modes, compensation methods, and control algorithms

Improvements in Voltage Profile of JDW Sugar Mills’ Jawar Distribution Feeder RYK Pakistan Using ANN Based Dynamic Voltage Restorer

Intelligent Voltage Sag Compensation Using an Artificial Neural Network (ANN)-Based Dynamic Voltage Restorer in MATLAB Simulink

Contact Info

Product

Resources

About