GAANN Program in AI and Data Science for Complex Engineering Applications

AI and data science are crucial enabling technologies across a range of domains, and they are center pieces for understanding complex systems. The US electric power industry is increasingly adopting machine learning and data analytics technologies to improve the reliability, resiliency, and efficiency of power systems. The intersection of the power systems and information systems technologies helps define new architectures for the electric system with enhanced ability to accommodate a range of options from distributed to central station assets. As a result, the power industry is looking for people who “speak” both data science and power engineering. Moreover, advancements in algorithms, software, and computing platforms have made AI empower and influence almost every aspect of our lives. Software engineers should not only know how to build and maintain complex software, but they also need to know how to extract knowledge from massive amounts of available data and adapt that knowledge to consider different human factors. Thus, there is huge demand for highly skilled cross-disciplinary manpower across these domains, but the talent to meet this demand is critically lagging. 

To fill in this critical national need, the School of Electrical Engineering and Computer Science (EECS) at Washington State University (WSU) established a Department of Education-funded Graduate Assistance in Areas of National Need (GAANN) program in 2022 to educate and train the highest quality domestic PhD students at the intersections of AI, data science, and engineering. Specific objectives of the program include: 

1. increasing the number of domestic PhD students focusing on the application of AI and data science for use in complex engineering applications and 
2. providing excellent academic experiences to GAANN fellows through integrated mentoring and engagement opportunities at national labs, industry settings, and technology/community alliances. 

Having strong and thriving programs in machine learning and AI, software engineering, and power engineering, EECS is ideally situated to provide opportunities for this interdisciplinary education. The GAANN program is led by Dr. Assefaw Gebremedhin, and Drs. Anamika Dubey, Venera Aranoudova, and Noel Schulz serve as Co-PIs.

---

GAANN Fellows Being Trained

---

---

Publications

---

• J. Halvorsen, C. Izurieta, H. Cai and A. Gebremedhin. Applying Generative Machine Learning to Intrusion Detection: A Systematic Mapping Study and Review, ACM Computing Surveys 56(10), Article 257 (2024).

• J. Halvorsen and A. Gebremedhin. Generative Machine Learning for Cyber Security, Military Cyber Affairs 7(1), Article 4 (2024).
• J. Halvorsen, Y. Yan and A. Gebremedhin. Denoising Diffusion Implicit Models for Generating Cyber Defense Network Traffic, IEEE International Conference on Communications (ICC 2025), 2025.

• J. Briscoe, C. DeSmet, K. Wuestney, A. Gebremedhin, R. Fritz and D. J. Cook. Exploring Geriatric Clinical Data and Mitigating Bias with Multi-Objective Synthetic Data Generation for Equitable Health Predictions, Journal of Biomedical Engineering and Biosciences (2024).
• J. Briscoe, G. Kepler, D. Deford and A. Gebremedhin. Algorithmic Accountability in Small Data: Reliability and Fairness in Classification Metrics, International Conference on Artificial Intelligence and Statistics (AISTATS 2025), 2025.
• J. Briscoe and A. Gebremedhin. Facets of Disparate Impact: Evaluating Legally Consistent Bias in Machine Learning, ACM International Conference on Information and Knowledge Management (CIKM 2024), 2024.
• J. Briscoe, C. DeSmet, K. Wuestney, A. Gebremedhin, R. Fritz and D. J. Cook. Reducing Sample Selection Bias in Clinical Data through Generation of Multi-Objective Synthetic Data, 11th International Conference on Biomedical Engineering and Systems (ICBES 2024), 2024.

• L. Wang, J. Halvorsen, S. Pannala, A. Srivastava, A. H. Gebremedhin and N. Schulz. CPSyNet: A Tool for Generating Customized Cyber-Power Synthetic Network for Distribution System with Distributed Energy Resources, IET Smart Grid 5(6), 463–477 (2022)
• D. Glover, P. Pareek, D. Deka and A. Dubey. Power Flow Approximations for Multiphase Distribution Networks using Gaussian Processes, IEEE Power & Energy Society General Meeting (PESGM 2025), 2025.
• D. Glover and A. Dubey. Learning Volt-VAR Droop Curves to Optimally Coordinate Photovoltaic (PV) Smart Inverters, IEEE Transactions on Industry Applications (TIA 2025), 2025.
• D. Glover and A. Dubey. Centralized Coordination of DER Smart Inverters using Deep Reinforcement Learning, IEEE Industry Applications Society Annual Meeting (IAS 2023), 2023.
• A. Dubey, D. Glover and G. Krishnamoorthy. Grid-edge Optimization and Control with Machine Learning, Big Data Application in Power Systems, 2nd ed. (Elsevier 2024), 2024.
• A. Poudyal, S. Lamichhane, C. Wertz, S. U. Mahmud and A. Dubey. Hurricane and Storm Surges-Induced Power System Vulnerabilities and their Socioeconomic Impact, IEEE Power & Energy Society General Meeting (PESGM 2024), 2024.
• A. Poudyal, C. Wertz, A. M. Nguyen, S. U. Mahmud, A. Dubey and V. Gunturi. Spatiotemporal Impact Assessment of Hurricanes and Storm Surges on Electric Power Systems, IEEE Power & Energy Society General Meeting (PESGM 2023), 2023.