Systems Ph.D. student Ning Zhao’s paper selected De Gruyter Best Paper Award runner-up

Ning Zhao

Systems Ph.D. student Ning Zhao recently took runner-up honors for the De Gruyter Best Paper Award at the PRES'24 conference, held October 31-November 3 in Brno, Czech Republic. Zhao's paper, titled "Unit Commitment under Uncertainty using Data-Driven Optimization with Clustering Techniques," was co-authored by Fengqi You, the Roxanne E. and Michael J. Zak Professor in Energy Systems Engineering.

Zhao’s paper proposes a novel robust unit commitment (UC) framework with data-driven disjunctive uncertainty sets for volatile wind power outputs, assisted by machine learning techniques. Specifically, to flexibly identify the uncertainty space based on wind power forecast error data with disjunctive structures, the uncertainty data are grouped using K-means and density-based spatial clustering of applications with noise (DBSCAN) following the optimal cluster number determined by the Calinski-Harabasz index. The disjunctive uncertainty sets are constructed accordingly as the union of multiple basic uncertainty sets, including conventional box and budget uncertainty sets, and data-driven uncertainty sets using Dirichlet process mixture model, principal component analysis coupled with kernel density estimation, and support vector clustering. Subsequently, the problem is formulated into a two-stage adaptive robust UC model with data-driven disjunctive uncertainty sets and a multi-level optimization structure. A tailored decomposition-based optimization algorithm is developed to facilitate the solution process and improve computational efficiency. The effectiveness and scalability of the proposed framework are illustrated using two case studies based on the IEEE 39-bus and 118-bus systems. The results show that the proposed framework can reduce the price of robustness by 8-48% compared to the conventional “one-set-fits-all” robust optimization approaches. Benchmarking with stochastic programming indicates that the proposed approach can achieve the same or better economic performance with over 75% less computational time.

“This work presents an example of how machine learning can facilitate the decision-making process under uncertainty for the operations of energy systems, as shown by the improved economic performances and enhanced computational efficiency,” said Zhao, who received a B.S. degree in chemical engineering from Tsinghua University in 2018 and is currently working toward a Ph.D. in systems at Cornell. His research interests include the modeling and optimization for energy systems decarbonization.

Other Articles of Interest