Optimized Complex Power Quality Classifier Using One vs. Rest Support Vector Machines

Yong, David Marcelo de; Bhowmik, S.; Magnago, Fernando

doi:10.4236/epe.2017.910040

Cited by 7 publications

(3 citation statements)

References 32 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The current power distribution framework is implemented by renewable energy source. The current distribution framework is implemented using a generation of power gadgets circuits that are delivered in an explicit synchronized forward distribution framework [1]. In the generation of distribution, the random load power supply configuration, however, loading power gadgets present numerous power quality issues.…”

Section: Introductionmentioning

confidence: 99%

Multi-Level Inverter Linear Predictive Phase Composition Strategy for UPQC

Prabhu¹,

Sundararaju²

2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

The power system is facing numerous issues when the distributed generation is added to the existing system. The existing power system has not been planned with flawless power quality control. These restrictions in the power transmission generation system are compensated by the use of devices such as the Static Synchronous Compensator (STATCOM), the Unified Power Quality Conditioner (UPQC) series/shunt compensators, etc. In this work, UPQC's plan with the joint activity of photovoltaic (PV) exhibits is proposed. The proposed system is made out of series and shunt regulators and PV. A boost converter connects the DC link to the PV source, allowing it to compensate for voltage sags, swells, voltage interferences, harmonics, and reactive power issues. In this paper, the features of a seven-level Cascaded H-Bridge Multi-Level idea are applied to shunt and series active filter changeovers to reduce Total Harmonic Distortion and compensate for voltage issues. Despite its power quality capacity for common coupling, the proposed system can inject the grid's dynamic power. During voltage interference, it can also provide a piece of delicate burden power. The simulation is carried out with the help of MATLAB/SIMULINK programming, and the results are compared to those of other conventional methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-Level Inverter Linear Predictive Phase Composition Strategy for UPQC

Prabhu¹,

Sundararaju²

2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

show abstract

“…IEEE-1159 [1] stated the behavior of a standard waveform and categorized a different kind of disturbances. A complex power quality scenario is a specific disturbance that consists of an amalgamation of two or more individual disturbances, for instance, fluctuation or harmonics for a small period distortion such as, sags or surges [2].…”

Section: Introductionmentioning

confidence: 99%

Construction and Performance Investigation of Three-Phase Solar PV and Battery Energy Storage System Integrated UPQC

et al. 2020

View full text Add to dashboard Cite

This study examines the use of Unified Power Quality Conditioner (UPQC) to mitigate the power quality problems existed in the grid and the harmonics penetrated by the non-linear loads. The UPQC is supported by the Photovoltaic (PV) and Battery Energy Storage System (BESS) in this work. Generally, the PV system supplies the active power to the load. However, if the PV is unable to supply the power then the BESS activates and provides power especially during the longer-term voltage interruption. The standalone PV-UPQC system is less reliable compared to a hybrid PV-BESS system because of its instability and high environment-dependency. Therefore, BESS will improve the voltage support capability continuously in the longer-term, reduce the complexity of the DC-link voltage regulation algorithm, and keep producing clean energy. The phase synchronization operation of the UPQC controller is directed by a self-tuning filter (STF) integrated with the unit vector generator (UVG) technique. Implementation of STF will make sure the UPQC can successfully operate under unbalanced and distorted grid voltage conditions. Thus, the requirement of a phase-locked loop (PLL) is omitted and the STF-UVG is utilized to produce the synchronization phases for the series and shunt active power filter (APF) compensator in UPQC controller. Finally, the proposed STF-UVG method is compared with the conventional synchronous references frame (SRF-PLL) method based UPQC to show the significance of the proposed technique. Several case studies are further considered to validate the study in MATLAB-Simulink software.INDEX TERMS Battery energy storage system (BESS), power quality, self-tuning filter (STF), solar photovoltaic (PV), unified power quality conditioner (UPQC).

show abstract

“…Support vector machine (SVM) is a good option for classification purposes, especially when dealing with small samples, nonlinearity, or high dimension in pattern recognition [2,16,22,34,35]. Among the advantages of SVM are the lack of local extremum, feature mapping of nonlinear separable data, low space complexity, and the capability to adjust only a reduced number of features as compared to, for example, the ANNs [36].…”

Section: Introductionmentioning

confidence: 99%

Hybrid Machine Learning Models for Classifying Power Quality Disturbances: A Comparative Study

2020

View full text Add to dashboard Cite

The economic impact associated with power quality (PQ) problems in electrical systems is increasing, so PQ improvement research becomes a key task. In this paper, a Stockwell transform (ST)-based hybrid machine learning approach was used for the recognition and classification of power quality disturbances (PQDs). The ST of the PQDs was used to extract significant waveform features which constitute the input vectors for different machine learning approaches, including the K-nearest neighbors’ algorithm (K-NN), decision tree (DT), and support vector machine (SVM) used for classifying the PQDs. The procedure was optimized by using the genetic algorithm (GA) and the competitive swarm optimization algorithm (CSO). To test the proposed methodology, synthetic PQD waveforms were generated. Typical single disturbances for the voltage signal, as well as complex disturbances resulting from possible combinations of them, were considered. Furthermore, different levels of white Gaussian noise were added to the PQD waveforms while maintaining the desired accuracy level of the proposed classification methods. Finally, all the hybrid classification proposals were evaluated and the best one was compared with some others present in the literature. The proposed ST-based CSO-SVM method provides good results in terms of classification accuracy and noise immunity.

show abstract

Optimized Complex Power Quality Classifier Using One vs. Rest Support Vector Machines

Cited by 7 publications

References 32 publications

Multi-Level Inverter Linear Predictive Phase Composition Strategy for UPQC

Multi-Level Inverter Linear Predictive Phase Composition Strategy for UPQC

Construction and Performance Investigation of Three-Phase Solar PV and Battery Energy Storage System Integrated UPQC

Hybrid Machine Learning Models for Classifying Power Quality Disturbances: A Comparative Study

Contact Info

Product

Resources

About