Tatjana Dokic
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tatjana Dokic has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
Mladen Kezunovic
Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USA
11 shared publications- Po-Chen Chen
Texas A&M University, College Station, TX, USA
6 shared publications - Mladen Kezunovic
Texas A&M University
5 shared publications Qin Yan
Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USA
4 shared publicationsZoran Obradovic
Computer and Information Sciences Department Temple University Philadelphia PA U.S.A
3 shared publicationsBei Zhang
GE Energy Consulting, Schenectady, NY, USA
2 shared publications
Latest Publications
- 12 May 2022
- Published by Wiley
- p. 1-28
Fault Location: The Models, Methods, and Solutions
- 14 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 37 (5) , 3434-3442
Fault Detection Utilizing Convolution Neural Network on Timeseries Synchrophasor Data From Phasor Measurement Units
An end-to-end supervised learning method is proposed for fault detection in the electric grid using Big Data from multiple Phasor Measurement Units (PMUs). The approach consists of preprocessing steps aimed at reducing data noise and dimensionality, followed by utilization of six classification models considered for detecting faults. Three of the models were variants of Convolutional Neural Network (CNN) architectures that consider a single type of measurement (voltage, current or frequency) at all PMUs or all types together also at all PMUs. CNN based models were compared to traditional methods of Logistic Regression (LR), Multi-layer Perceptron (MLP) and Support Vector Machine (SVM). Evaluation was conducted on two-year data measured by PMUs at 37 locations in a large electric grid. The response variable for classification were extracted from the grid-wide outage event log. Experiments show that CNN-based models outperformed traditional methods on one year out-of-sample outage detection over the entire grid.
- 14 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 37 (5) , 3434-3442
Fault Detection Utilizing Convolution Neural Network on Timeseries Synchrophasor Data From Phasor Measurement Units
An end-to-end supervised learning method is proposed for fault detection in the electric grid using Big Data from multiple Phasor Measurement Units (PMUs). The approach consists of preprocessing steps aimed at reducing data noise and dimensionality, followed by utilization of six classification models considered for detecting faults. Three of the models were variants of Convolutional Neural Network (CNN) architectures that consider a single type of measurement (voltage, current or frequency) at all PMUs or all types together also at all PMUs. CNN based models were compared to traditional methods of Logistic Regression (LR), Multi-layer Perceptron (MLP) and Support Vector Machine (SVM). Evaluation was conducted on two-year data measured by PMUs at 37 locations in a large electric grid. The response variable for classification were extracted from the grid-wide outage event log. Experiments show that CNN-based models outperformed traditional methods on one year out-of-sample outage detection over the entire grid.
- 24 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 70 (00189456) , 1-13
Hierarchical Convolutional Neural Networks for Event Classification on PMU Measurements
Event classification is one of the central components of automated disturbance analysis based on phasor measurement unit (PMU) measurements. Obtaining high-quality event labels remains a challenge for supervised learning-based classification of local and system-wide events in power grids due to its labor-intensive requirement. We present a sensitivity study considering rapidly refined, partially, and fully inspected event labels that leads to evidence that hierarchical convolutional neural networks (HCNNs) outperform traditional classification models regardless of the quality of the available event labels. It is demonstrated that performance similar to the one obtained using entirely domain-driven labeling can be achieved as long as the involved expert does not mislabel more than ~5% of the event data captured by PMU measurements.
- 24 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 70 (00189456) , 1-13
Hierarchical Convolutional Neural Networks for Event Classification on PMU Measurements
Event classification is one of the central components of automated disturbance analysis based on phasor measurement unit (PMU) measurements. Obtaining high-quality event labels remains a challenge for supervised learning-based classification of local and system-wide events in power grids due to its labor-intensive requirement. We present a sensitivity study considering rapidly refined, partially, and fully inspected event labels that leads to evidence that hierarchical convolutional neural networks (HCNNs) outperform traditional classification models regardless of the quality of the available event labels. It is demonstrated that performance similar to the one obtained using entirely domain-driven labeling can be achieved as long as the involved expert does not mislabel more than ~5% of the event data captured by PMU measurements.
- 24 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 34 (6) , 4249-4257
Resiliency Assessment in Distribution Networks Using GIS-Based Predictive Risk Analytics
A new predictive risk-based framework is proposed to increase power distribution network resiliency by improving operator understanding of the status of the grid. This paper expresses the risk assessment as the correlation between likelihood and impact. The likelihood is derived from the combination of Naive Bayes learning and Jenks natural breaks classifier. The analytics included in a geographic information system platform fuse together a massive amount of data from outage recordings and weather historical databases in just one semantic parameter known as failure probability. The financial impact is determined by a time-series-based formulation that supports spatiotemporal data from fault management events and customer interruption cost. Results offer prediction of hourly risk levels and monthly accumulated risk for each feeder section of a distribution network allowing for timely tracking of the operating condition.
- 24 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 34 (6) , 4249-4257
Resiliency Assessment in Distribution Networks Using GIS-Based Predictive Risk Analytics
A new predictive risk-based framework is proposed to increase power distribution network resiliency by improving operator understanding of the status of the grid. This paper expresses the risk assessment as the correlation between likelihood and impact. The likelihood is derived from the combination of Naive Bayes learning and Jenks natural breaks classifier. The analytics included in a geographic information system platform fuse together a massive amount of data from outage recordings and weather historical databases in just one semantic parameter known as failure probability. The financial impact is determined by a time-series-based formulation that supports spatiotemporal data from fault management events and customer interruption cost. Results offer prediction of hourly risk levels and monthly accumulated risk for each feeder section of a distribution network allowing for timely tracking of the operating condition.
- Open Access
- 1 January 2019
- Published by HICSS Conference Office
Spatially Aware Ensemble-Based Learning to Predict Weather-Related Outages in Transmission
This paper describes the implementation of a prediction model for real-time assessment of weather related outages in the electric transmission system. The network data and historical outages are correlated with a variety of weather sources in order to construct the knowledge extraction platform for accurate outage probability prediction. An extension of the logistic regression prediction model that embeds the spatial configuration of the network was used for prediction. The results show that the developed model manifests high accuracy and is able to differentiate an outage area from the rest of the network in 1 to 3 hours before the outage. The prediction model is integrated inside a weather testbed for real-time mapping of network outage probabilities based on incoming weather forecast.
- 1 January 2019
- Published by HICSS Conference Office
Open AccessSpatially Aware Ensemble-Based Learning to Predict Weather-Related Outages in Transmission
This paper describes the implementation of a prediction model for real-time assessment of weather related outages in the electric transmission system. The network data and historical outages are correlated with a variety of weather sources in order to construct the knowledge extraction platform for accurate outage probability prediction. An extension of the logistic regression prediction model that embeds the spatial configuration of the network was used for prediction. The results show that the developed model manifests high accuracy and is able to differentiate an outage area from the rest of the network in 1 to 3 hours before the outage. The prediction model is integrated inside a weather testbed for real-time mapping of network outage probabilities based on incoming weather forecast.
- 2 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 10 (5) , 4776-4785
Predictive Risk Management for Dynamic Tree Trimming Scheduling for Distribution Networks
This paper introduces a predictive method for distribution feeder vegetation management based on a risk framework. The state of risk is calculated for each feeder section using a variety of factors extracted from network parameters and historical outage data, historical weather data and weather forecasts, and a variety of vegetation indices. The framework implements the spatiotemporal correlation of all the collected data. The prediction model used is the Gaussian conditional random field, which takes into account spatial interdependencies between different feeder sections. This enables better prediction accuracy, and also offers the capability to deal with missing and bad data. Based on the calculated risk, the dynamic optimal tree trimming schedule, which minimizes the overall risk for the system under a given predetermined budget, is developed. Results obtained on a real utility network show that optimal tree trimming based on the developed risk framework for vegetation management could significantly decrease the overall risk of the feeder outages without increasing the budget.
- 2 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 10 (5) , 4776-4785
Predictive Risk Management for Dynamic Tree Trimming Scheduling for Distribution Networks
This paper introduces a predictive method for distribution feeder vegetation management based on a risk framework. The state of risk is calculated for each feeder section using a variety of factors extracted from network parameters and historical outage data, historical weather data and weather forecasts, and a variety of vegetation indices. The framework implements the spatiotemporal correlation of all the collected data. The prediction model used is the Gaussian conditional random field, which takes into account spatial interdependencies between different feeder sections. This enables better prediction accuracy, and also offers the capability to deal with missing and bad data. Based on the calculated risk, the dynamic optimal tree trimming schedule, which minimizes the overall risk for the system under a given predetermined budget, is developed. Results obtained on a real utility network show that optimal tree trimming based on the developed risk framework for vegetation management could significantly decrease the overall risk of the feeder outages without increasing the budget.
- 12 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Sustainable Energy
- Vol. 10 (1) , 3-15
Predictive Risk Analytics for Weather-Resilient Operation of Electric Power Systems
Day-to-day operation of the electricity grid generation, transmission, and distribution is environmentally driven and closely dependent on evolving weather patterns. This paper introduces several new weather-driven analytics for accurate spatial-temporal electricity generation forecasts, asset health and reliability assessment, probabilistic load forecasts, and electricity market simulations. A new risk metric is suggested, which accounts for the weather hazards, grid vulnerability, and financial consequences in the face of changing weather patterns and associated meteorological predictions over time. New mitigation formulations for power system topology control through transmission line switching for fast and timely recovery of the weather-caused electricity outages are suggested. The proposed decision support tool enables the operators to predictively evaluate the high-risk weather threats and consequently plan on how to safeguard the grid when exposed to forecasted weather-driven incidents. The efficiency of the proposed toolset is illustrated by application to a part of the IEEE 73-Bus test system.
- 12 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Sustainable Energy
- Vol. 10 (1) , 3-15
Predictive Risk Analytics for Weather-Resilient Operation of Electric Power Systems
Day-to-day operation of the electricity grid generation, transmission, and distribution is environmentally driven and closely dependent on evolving weather patterns. This paper introduces several new weather-driven analytics for accurate spatial-temporal electricity generation forecasts, asset health and reliability assessment, probabilistic load forecasts, and electricity market simulations. A new risk metric is suggested, which accounts for the weather hazards, grid vulnerability, and financial consequences in the face of changing weather patterns and associated meteorological predictions over time. New mitigation formulations for power system topology control through transmission line switching for fast and timely recovery of the weather-caused electricity outages are suggested. The proposed decision support tool enables the operators to predictively evaluate the high-risk weather threats and consequently plan on how to safeguard the grid when exposed to forecasted weather-driven incidents. The efficiency of the proposed toolset is illustrated by application to a part of the IEEE 73-Bus test system.
- 1 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 1-6
Failure probability metric by machine learning for online risk assessment in distribution networks
The risk assessment approach is useful for monitoring and supervisory control because it provides distribution operator with the capability to quantify the tradeoff between reliability and economic performance. The risk assessment determines the likelihood of something going wrong in a distribution network through the failure probability metric. To deal with the massive variety of information required in the calculation of failure probability we propose a data mining approach. The proposed approach incorporates weather, asset and outage information for characterizing the risk in a distribution network section via GIS platform.
- 1 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 1-6
Failure probability metric by machine learning for online risk assessment in distribution networks
The risk assessment approach is useful for monitoring and supervisory control because it provides distribution operator with the capability to quantify the tradeoff between reliability and economic performance. The risk assessment determines the likelihood of something going wrong in a distribution network through the failure probability metric. To deal with the massive variety of information required in the calculation of failure probability we propose a data mining approach. The proposed approach incorporates weather, asset and outage information for characterizing the risk in a distribution network section via GIS platform.
- 22 March 2017
- Published by Springer Nature
- p. 265-299
Predicting Spatiotemporal Impacts of Weather on Power Systems Using Big Data Science
- 22 March 2017
- Published by Springer Nature
- p. 265-299
Predicting Spatiotemporal Impacts of Weather on Power Systems Using Big Data Science
- 14 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Predicting impact of weather caused blackouts on electricity customers based on risk assessment
This study evaluates the outage probability and electricity customer cost under the potential weather caused power blackouts. Risk assessment of the weather impact on customers is implemented and visualized in ArcGIS map. The methodology correlates the historical large power outage events with the corresponding weather condition of the time, uses weather forecast data to assess the risk for customers, and compares the results in different predicted weather conditions.
- 14 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Predicting impact of weather caused blackouts on electricity customers based on risk assessment
This study evaluates the outage probability and electricity customer cost under the potential weather caused power blackouts. Risk assessment of the weather impact on customers is implemented and visualized in ArcGIS map. The methodology correlates the historical large power outage events with the corresponding weather condition of the time, uses weather forecast data to assess the risk for customers, and compares the results in different predicted weather conditions.