Smart Grid Data Analytics can be treated as the next big evolution of Smart Grid technology. Advanced data analytics allows the energy grid operators, different stakeholders and customers to take more informed decisions about energy consumption, adjust timing and quantity of energy usages. Besides, it is indeed possible to improve the efficiency, reliability and power quality with advanced monitoring and control of the measurement data. In my projects, I use a combination of data mining, machine learning and signal processing methods and algorithms which are then applied on Smart Grid for demand side management and security analysis.

Data Mining Methods (Unsupervised/Clustering):

1. Anwar, A., Mahmood, A. N., and Tari, Z., "Identification of vulnerable node clusters against false data injection attack in an AMI based Smart Grid," in Information Systems, Elsevier, 2015.
2. Ahmed, M., Anwar, A., Mahmood, A., Shah, Z., and Maher, M. J., "An Investigation of Performance Analysis of Anomaly Detection Techniques for Big Data in SCADA Systems," EAI Transactions on Industrial Networks and Intelligent Systems, 2015.
3. Anwar, A., and Mahmood, A. N., "CF-PSO based loss sensitivity clustering technique to identify optimal DG allocation nodes for energy efficient smart grid operation," In Proceedings of the 2014 9th IEEE Conference on Industrial Electronics and Applications, ICIEA 2014

Data Mining Methods (Supervised/PCA/SVD/SVM):

1. Adnan Anwar, Abdun Naser Mahmood, and Mark Pickering, "Modeling and performance evaluation of stealthy false data injection attacks on smart grid in the presence of corrupted measurements," in Journal of Computer and System Sciences, Volume 83, Issue 1, February 2017, Pages 58-72.
2. Adnan Anwar, Abdun Naser Mahmood, and Mark Pickering, "Data-Driven Stealthy Injection Attacks on Smart Grid with Incomplete Measurements," In Intelligence and Security Informatics, LNCS, Springer, 2016.
3. Adnan Anwar, Abdun Naser Mahmood, and Zubair Shah, "A Data-Driven Approach to Distinguish Cyber-Attacks from Physical Faults in a Smart Grid," In Proceedings of the 24th ACM International on Conference on Information and Knowledge Management (CIKM '15). ACM, New York, NY, USA

Machine Learning Methods (Dictionary Learning, Robust PCA) :

1. A. Anwar, A. Mahmood and M. Pickering, "Estimation of smart grid topology using SCADA measurements," IEEE International Conference on Smart Grid Communications (SmartGridComm), Sydney, Australia, 2016.
2. Adnan Anwar, Abdun Naser Mahmood, and Mark Pickering, "Modeling and performance evaluation of stealthy false data injection attacks on smart grid in the presence of corrupted measurements," in Journal of Computer and System Sciences, Volume 83, Issue 1, February 2017, Pages 58-72.

Big Data/ High Performance Computing (HPC):

1. Adnan Anwar, Abdun Mahmood, Javid Tahri, Zahir Tari, and Albert Zomaya, "HPC based Intelligent Volt/VAr Control of Unbalanced Distribution Smart Grid in the presence of Noise," in IEEE transactions on Smart Grid, 2016.
2. Ahmed, M., Anwar, A., Mahmood, A., Shah, Z., and Maher, M. J., "An Investigation of Performance Analysis of Anomaly Detection Techniques for Big Data in SCADA Systems," EAI Transactions on Industrial Networks and Intelligent Systems, 2015.
3. Zubair Shah, Adnan Anwar, Abdun Mahmood, Zahir Tari, and Albert Zomaya, "A Spatiotemporal Data Summarization Paradigm for Real-time Operation of Smart Grid ," in IEEE transactions on Big Data, 2017

Graph Matching:

1. Anwar, A., Mahmood, and A. N., "Anomaly detection in electric network database of smart grid: Graph matching approach," in Electric Power Systems Research, Elsevier, Volume 133, April 2016, Pages 51-62.