A5103096101- Power Systems Fault Detection
- Power System Optimization and Stability
- Optimal Power Flow Distribution
- Model Reduction and Neural Networks
- Power Quality and Harmonics
- Islanding Detection in Power Systems
- Electrical Fault Detection and Protection
- Power Transformer Diagnostics and Insulation
- Architecture and Art History Studies
- Medical Image Segmentation Techniques
- Architecture and Computational Design
- Business Process Modeling and Analysis
- AI in cancer detection
- Energy Load and Power Forecasting
- Machine Learning and Algorithms
- Service-Oriented Architecture and Web Services
- Semantic Web and Ontologies
- Radiomics and Machine Learning in Medical Imaging
- Agricultural Engineering and Mechanization
- Plant responses to water stress
- Microgrid Control and Optimization
- Lightning and Electromagnetic Phenomena
University of Novi Sad
2014-2017
Texas A&M University
2012-2014
University of Genoa
2014
Polskie Sieci Elektroenergetyczne
2014
University of Liège
2014
University of Strathclyde
2014
A regression tree-based approach to predicting the power system stability margin and detecting impending event is proposed. The input features of tree (RT) include synchronized voltage current phasors. Modal analysis continuation flow are tools used build knowledge base for offline RT training. Corresponding metrics damping ratio critical oscillation mode MW-distance collapse point. robustness proposed predictor measurement errors topology variation analyzed. optimal placement phasor units...
An active machine learning technique for monitoring the voltage stability in transmission systems is presented. It has been shown that algorithms may be used to supplement traditional simulation approach, but they suffer from difficulties of online model update and offline training data preparation. We propose an solution enhance existing applications by actively interacting with prediction process. The identifies operating points where predictions based on power system measurements...
The presence of distributed generation (DG) in distribution networks may seriously affect accuracy the voltage sag based fault location method. An approach toward quantifying adverse effect DG on calculation is described. A series realistic scenarios used to illustrate how impacts synchrophasor measurements during disturbances. Alternative Transients Program-Electromagnetic Program models are obtain steady-state solutions time domain, while Sobol's sensitivity analysis quantify and...
This paper presents an overall analysis of how the penetration distributed generation in low-voltage secondary distribution networks affects voltage stability. It is critical that collapse point be carefully studied under different system operating points to prevent degradation service. System components have been sophisticatedly modeled ATP/EMTP. DGs are allocated a probabilistic fashion account for uncertainties future allocation. A large number experiments both light and peak load...
In this paper, the global, variance-based, sensitivity analysis is used to quantify impact of measurement imperfections on voltage sag based fault location. This kind location requires phasor information from meters be compared simulated cases in order locate faults. However, are prone imperfections. It therefore critical that imperfections, such as and loading errors, fully assessed account for uncertainty algorithm inputs. Sensitivity was attribute responsibility inputs algorithm. The...
It is necessary to accurately detect and locate sub-cycle faults in order prevent unexpected outages. However, conventional fault location methods cannot these as typically data windows longer than the fault's signature are used for phasor extraction. This paper presents an overall analysis of how single-phase-ground distribution network can be located using voltage sag. The half-cycle Discrete Fourier transform extraction timedomain simulations. Our results reveal that proposed approach...
This paper focuses on methodology to quantify uncertainty in measurements obtained from Intelligent Electronic Devices (IED). IEDs have emerged distribution systems as a prevalent source of monitoring and protection, well for different kinds applications beyond IED's primary purposes. These measurement devices are installed across system, substations down the customer locations, provide wide array quantities. We report how IED respond external disturbances, which may lead possible accuracy...
This paper investigates how correlating cross-domain big data from the lightning surge and traveling wave measurements in time space can be used to improve fault location accuracy. The integration correlation of using Global Positioning System Geographic Information respectively improves knowledge about faults on transmission lines caused by lightning. benefits proposed method are: (a) decision process accelerated through automation, (b) better accuracy result provided due correlation....
Traditional power system stability analysis based on full model computation shows its drawbacks in real-time applications where fast variations are present at both demand side and supply side. This paper presents the use of Decision Trees (DT) for evaluation oscillatory voltage current phasor measurements. An operating point is grouped into one several categories value corresponding indicator. A new methodology knowledge base creation has been elaborated to assure practical sufficient...
Analysis of synchrophasor measurements using data mining tools, in pursuit precise stability assessment, requires a sufficiently large training set. Traditionally the process learning underlying power system behavioral patterns introduces significant computational burden such that exhaustive simulations all possible operating conditions are necessary. Advancements machine make it possible, some cases, to reduce amount need be analyzed without impacting accuracy assessment. By probabilistic...
Single-phase-to-ground sub-cycle faults in the distribution network can be located using voltage sag fault location. This paper illustrates how a sensitivity study of measurement imperfections used to quantify impact on based Our results suggest that there is complex relationship between factors influencing error location because design covered wide range conditions. The more complicated, higher order interactions have stronger influence than any particular input factor alone.
Appears in: INTED2016 Proceedings Publication year: 2016Pages: 6101-6108ISBN: 978-84-608-5617-7ISSN: 2340-1079doi: 10.21125/inted.2016.0448Conference name: 10th International Technology, Education and Development ConferenceDates: 7-9 March, 2016Location: Valencia, Spain
for future power distribution networks", http://www.cdax.eu".
The utilization of agricultural mechanization is crucial to its efficient exploitation that, in turn, significantly influences the entire economy as well soil quality.Contemporary machines are GPS enabled, allowing localization and recording their motion.In this paper we present an approach spatio-temporal operations based on a linear classifier fuzzy space.We trained data labeled using order create training set for mining predictor that may be helpful automated management records describing...