Data Analytics and Machine Learning to Enhance the Operational Visibility and Situation Awareness of Smart Grid High Penetration Photovoltaic Systems

Authors

Aditya Sundararajan, Department of Electrical and Computer Engineering, Florida International UniversityFollow

Document Type

Dissertation

Degree

Doctor of Philosophy (PhD)

Major/Program

Electrical Engineering

First Advisor's Name

Arif I. Sarwat

First Advisor's Committee Title

Committee Chair

Second Advisor's Name

Malek Adjouadi

Second Advisor's Committee Title

Committee Member

Third Advisor's Name

Jean Andrian

Third Advisor's Committee Title

Committee Member

Fourth Advisor's Name

Bogdan Carbunar

Fourth Advisor's Committee Title

Committee Member

Fifth Advisor's Name

Deepal Rodrigo

Fifth Advisor's Committee Title

Committee Member

Keywords

High penetration distributed energy resources, High penetration photovoltaic systems, Machine learning, Neural networks, Situation awareness, Cyber-physical systems, Operational visibility, Energy storage, DER controller, Human-on-the-loop cybersecurity

Date of Defense

11-5-2019

Abstract

Electric utilities have limited operational visibility and situation awareness over grid-tied distributed photovoltaic systems (PV). This will pose a risk to grid stability when the PV penetration into a given feeder exceeds 60% of its peak or minimum daytime load. Third-party service providers offer only real-time monitoring but not accurate insights into system performance and prediction of productions. PV systems also increase the attack surface of distribution networks since they are not under the direct supervision and control of the utility security analysts.

Six key objectives were successfully achieved to enhance PV operational visibility and situation awareness: (1) conceptual cybersecurity frameworks for PV situation awareness at device, communications, applications, and cognitive levels; (2) a unique combinatorial approach using LASSO-Elastic Net regularizations and multilayer perceptron for PV generation forecasting; (3) applying a fixed-point primal dual log-barrier interior point method to expedite AC optimal power flow convergence; (4) adapting big data standards and capability maturity models to PV systems; (5) using K-nearest neighbors and random forests to impute missing values in PV big data; and (6) a hybrid data-model method that takes PV system deration factors and historical data to estimate generation and evaluate system performance using advanced metrics.

These objectives were validated on three real-world case studies comprising grid-tied commercial PV systems. The results and conclusions show that the proposed imputation approach improved the accuracy by 91%, the estimation method performed better by 75% and 10% for two PV systems, and the use of the proposed forecasting model improved the generalization performance and reduced the likelihood of overfitting. The application of primal dual log-barrier interior point method improved the convergence of AC optimal power flow by 0.7 and 0.6 times that of the currently used deterministic models. Through the use of advanced performance metrics, it is shown how PV systems of different nameplate capacities installed at different geographical locations can be directly evaluated and compared over both instantaneous as well as extended periods of time. The results of this dissertation will be of particular use to multiple stakeholders of the PV domain including, but not limited to, the utility network and security operation centers, standards working groups, utility equipment, and service providers, data consultants, system integrator, regulators and public service commissions, government bodies, and end-consumers.

Identifier

FIDC008830

ORCID

0000-0003-3577-8544

Previously Published In

1. D. Saleem, A. Sundararajan, A. Sanghvi, J. Rivera, A. I. Sarwat, and B. Kroposki, “A Multidimensional Holistic Framework for the Security of Distributed Energy and Control Systems,” IEEE Systems Journal , pp. 1–11, 2019.
2. A. Sundararajan, T. Khan, H. Aburub, A. I. Sarwat, and S. Rahman, “A tri-modular human-on-the-loop framework for intelligent smart grid cyber-attack visualization,” in IEEE Southeast Conference, IEEE, 2018.
3. A. Sundararajan, L. Wei, T. Khan, A. I. Sarwat, and D. Rodrigo, “A Tri-Modular Framework to Minimize Smart Grid Cyber-Attack Cognitive Gap in Utility Control Centers,” in Resilience Week, pp. 117–123, 2018.
4. A. Sundararajan, H. Riggs, A. Jeewani, and A. I. Sarwat, “Cluster-based Module to Manage Smart Grid Data for an Enhanced Situation Awareness: A Case Study,” in Resilience Week, pp. 1–7, 2019.
5. A. Sundararajan, Y. Mekonnen, H. Aburub, A. I. Sarwat, and S. Biswas, “An Application of Primal Dual Log-Barrier Interior Point Method to Improve Optimal Power Flow Convergence in High PV Penetration Scenarios,” Elsevier Applied Energy (under review).
6. A. I. Sarwat and A. Sundararajan, “Distributed Renewable Energy Grid Controller,” U.S. Patent US10326280, June 2019.
7. A. Sundararajan and A. I. Sarwat, “Evaluation of Missing Data Imputation Methods for an Enhanced Distributed PV Generation Prediction,” in Book: Advances in Intelligent Systems and Computing, Springer, In Press.
8. A. Sundararajan and A. I. Sarwat, “A Hybrid Data-Model Method to Improve Generation Estimation and Performance Assessment of Grid-tied PV: A Case Study,” IET Renewable Power Generation, vol. 13, pp. 2480–2490, October 2019.
9. A. Khalid, A. Sundararajan, I. Acharya, and A. I. Sarwat, “Prediction of li-ion battery state of charge using multilayer perceptron and long short-term memory models,” in 2019 IEEE Transportation Electrification Conference (ITEC)
10. A. I. Sarwat, A. Sundararajan, and I. Parvez, “Trends and future directions of research for smart grid iot sensor networks,” in Proceedings of International Symposium on Sensor Networks, Systems and Security (N. S. Rao, R. R. Brooks, and C. Q. Wu, eds.).
11. A. Khalid, A. Sundararajan, and A. I. Sarwat, “A Multi-Step Predictive Model to Estimate Li-Ion State of Charge for Higher C-Rates,” in 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe)
12. A. Anzalchi, A. Sundararajan, L. Wei, A. Moghadasi, M. M. Pour, and A. I. Sarwat, “Future directions to the application of distributed fog computing in smart grid systems,” Smart Grid Analytics for Sustainability and Urbanization , June 2018.
13. T. O. Olowu, A. Sundararajan , M. Moghaddami, and A. Sarwat, “Fleet aggregation of Photovoltaic Systems: A Survey and Case Study,” in 2019 IEEE Power Energy Society Innovative Smart Grid Technologies Conference (ISGT), Feb 2019.
14. A. Sundararajan, T. O. Olowu, L. Wei, S. Rahman, and A. I. Sarwat, “A Case Study on the Effects of Partial Solar Eclipse on Distributed Photovoltaic Systems and Management Areas,” IET Smart Grid, June 2019.
15. A. Sundararajan, T. Khan, A. Moghadasi, and A. I. Sarwat, “Survey on synchrophasor data quality and cybersecurity challenges, and evaluation of their interdependencies,” Journal of Modern Power Systems and Clean Energy, pp. 1–19, 2018.
16. A. Sundararajan, A. Chavan, D. Saleem, and A. I. Sarwat, “A survey of protocol-level challenges and solutions for distributed energy resource cyber-physical security,” MDPI Energies , p. 2360, September 2018.
17. A. Sundararajan and A. I. Sarwat and A. Pons, “A Survey on Modality Characteristics, Performance Evaluation Metrics, and Security for Traditional and Wearable Biometric Systems,” ACM Computing Surveys , vol. 52, no. 2, pp. 1–35, 2019.
18. A. Sundararajan and A. I. Sarwat, “Roadmap to Prepare Distribution Grid-Tied Photovoltaic Site Data for Performance Monitoring,” in International Conference on Big Data, IoT & Data Analytics (BID), pp. 110–115, December 2017.
19. A. Sundararajan, T. Khan, H. Aburub, A. I. Sarwat, and S. Rahman, “A Tri-Modular Human-on-the-Loop Framework for Intelligent Smart Grid Cyber-Attack Visualization,” in SoutheastCon 2018, pp. 1–8, April 2018.
20. Z. Peterson, M. Coddington, F. Ding, B. Sigrin, D. Saleem, K. Horowitz, S. E. Baldwin, B. Lydic, S. C. Stanfield, N. Enbar, S. Coley, A. Sundararajan, and C. Schroeder, “An overview of distributed energy resource (der) interconnection: Current practices and emerging solutions,” NREL Technical Report (number NREL/TP-6A20-72102), April 2019.
21. A. Anzalchi, A. Sundararajan, A. Moghadasi, and A. Sarwat, “High-penetration grid-tied photovoltaics: Analysis of power quality and feeder voltage profile,” IEEE Industry Applications Magazine, vol. 25, pp. 83–94, Sep. 2019.
22. A. Sundararajan, A. Hernandez, and A. I. Sarwat, “Adapting Big Data Standards, Maturity Models to Smart Grid Distributed Generation: Critical Review,” IET Smart Grid (accepted).
23. A. Anzalchi, A. Sundararajan, A. Moghadasi, and A. Sarwat, “Power quality and voltage profile analyses of high penetration grid-tied photovoltaics: A case study,” in 2017 IEEE Industry Applications Society Annual Meeting, pp. 1–8, Oct 2017.
24. A. Anzalchi, A. Sundararajan, A. Moghadasi, and A. I. Sarwat, “Power quality and voltage profile analyses of high penetration grid-tied photovoltaics: A case study,” IEEE Industry Applications Society Annual Meeting, 2017.
25. J. Sarochar, I. Acharya, H. Riggs, A. Sundararajan, L. Wei, T. Olowu, and A. I. Sarwat, “Synthesizing energy consumption data using a mixture density network integrated with long short term memory,” in IEEE Green Tech Conference, IEEE, 2019.
26. A. Khalid, A. Sundararajan, A. Hernandez, and A. Sarwat, “FACTS Approach to Address Cybersecurity Issues in Electric Vehicle Battery Systems,” in 2019 IEEE Technology & Engineering Management Conference (TEMSCON).
27. A. I. Sarwat, A. Sundararajan, I. Parvez, M. Moghaddami, and A. Moghadasi, “Toward a smart city of interdependent critical infrastructure networks,” in Sustainable Interdependent Networks, pp. 21–45, Springer, 2018.
28. U. Ozgur, H. T. Nair, A. Sundararajan, K. Akkaya, and A. I. Sarwat, “An efficient mqtt framework for control and protection of networked cyber-physical systems,” in IEEE Conference on Communications and Network Security, IEEE, 2017.

Creative Commons License

This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Recommended Citation

Sundararajan, Aditya, "Data Analytics and Machine Learning to Enhance the Operational Visibility and Situation Awareness of Smart Grid High Penetration Photovoltaic Systems" (2019). FIU Electronic Theses and Dissertations. 4332.
https://digitalcommons.fiu.edu/etd/4332