The project aims to assess, predict levels of risk in the distribution power system and subsequently mitigate possible adverse effects. The historical datasets including weather data, assets condition and maintenance reports, outage management practices, lightning data, vegetation management data etc are utilized to comprise a complex dataset. Combination of cutting-edge technologies such as Big Data, Machine Learning and Geographical Information Systems are used to clean, correlate, preprocess and transform data. The prediction algorithm is developed and used to timely predict State of Risk levels in the network. The utilities incorporate State of Risk levels into their daily operations and planning, as a result a set of mitigation actions is applied to reduce the risk. Reduced levels of risk in the system lead to improved resiliency and reliability of the power grid, potentially saving fault incurred costs on the economy.
References
Conferences:
- Kezunovic, Z. Obradovic, Y. Hu, “Use of Machine Learning on PMU Data for Transmission System Fault Analysis,” CIGRE General Session, Paper # 191, Paris, France, August 2022.
- Kezunovic, Z. Obradovic, Y. Hu, “Automated System-wide Event Detection and Classification Using Machine Learning on Synchrophasor Data,” CIGRE General Session, Paper # 224, Paris, France, August 2022.
- Dokic, R. Baembitov, A. A. Hai, Z. Cheng, Y. Hu, M. Kezunovic and Z. Obradovic., “Machine Learning Using a Simple Feature for Detecting Multiple Types of Events from PMU Data,” in 2022 International Conference on Smart Grid Synchronized Measurements and Analytics (SGSMA), 24-26 May 2022 2022, pp. 1-6, doi: 10.1109/SGSMA51733.2022.9806000.
- Cheng, Y. Hu, Z. Obradovic, M. Kezunovic, “Using Synchrophasor Status Word as Data Quality Indicator: What to Expect in the Field?” 2022 International Conference on Smart Grid Synchronized Measurements and Analytics (SGSMA), 24-26 May 2022 2022, doi: 10.1109/SGSMA51733.2022.9806010.
- M. Kezunovic, R. Baembitov, and M. Khoshjahan, “Data-driven State of Risk Prediction and Mitigation in Support of the Net-zero Carbon Electric Grid,” in 11th Bulk Power Systems Dynamics and Control Symposium – IREP’2022, Banff, Canada, 2022, doi:10.48550/arXiv.2207.03472.
- R. Baembitov, M. Kezunovic, Z. Obradovic, “Graph Embeddings for Outage Prediction,” The 53rd NAPS, College Station, USA, Nov, 2021, DOI: 10.1109/NAPS52732.2021.9654696.
- M. Khoshjahan, R. Baembitov and M. Kezunovic, “Impacts of Weather-Related Outages on DER Participation in the Wholesale Market Energy and Ancillary Services” 2021 CIGRE Grid of the Future Symposium, Providence, Rhode Island, USA, October 2021.
Journals:
- R. Baembitov, M. Kezunovic, K. A. Brewster and Z. Obradovic, “Incorporating Wind Modeling into Electric Grid Outage Risk Prediction and Mitigation Solution,” in IEEE Access, doi: 10.1109/ACCESS.2023.3234984.
- M. Kezunovic, P. Pinson, Z. Obradovic, S. Grijalva, T. Hong, and R. Bessa, “Big Data Analytics for Future Electricity Grids,” Electric Power Systems Research, Vol. 189, No., pp. 106788, 2020, DOI: 10.1016/j.epsr.2020.106788.
- J. Leite, J. R. S. Mantovani, T. Dokic, Q. Yan , P.-C. Chen, and M. Kezunovic, “Resiliency Assessment in Distribution Networks Using GIS Based Predictive Risk Analytics,”IEEE Transactions on Power Systems, Vol., No., pp., April 24, 2019, DOI: 10.1109/TPWRS.2019.2913090.
- P. Dehghanian, B. Zhang, T. Dokic and M. Kezunovic, “Predictive Risk Analytics for Weather-Resilient Operation of Electric Power Systems,” IEEE Transactions on Sustainable Energy, Vol. 10, No., pp. 3-15, January 2019, DOI: 10.1109/TSTE.2018.2825780.
- T. Dokic, M. Kezunovic, “Predictive Risk Management for Dynamic Tree Trimming Scheduling for Distribution Networks,” IEEE Transactions on Smart Grid, Vol. 10, No. 5, pp. 4776-4785, September 2018, DOI: 10.1109/TSG.2018.2868457.