Yuheng Zhang

Room 1004 Wangkezhen Building

Peking University, 5 Yiheyuan Road

Beijing 100871, P.R. China

I am a Ph.D candidate in the Department of Industrial Engineering and Management at Peking University, advised by Prof. Guannan He. I received my B.S. degree in Department of Energy and Resources Engineering at Peking University in 2022. In the past years’ study, I had a deep understanding of environmental and energy systems in a high level and felt the importance of such systems in the carbon neutrality context and sustainable development.

Research Interests

My research interests include energy system optimization and machine learning. I am also interested in the synergy applications of machine learning in energy system optimization. Currently I’m researching on the system evolution of energy systems in the carbon neutrality context and dedicated to find fusion points of machine learning and energy system optimization. If you feel interested in my research, please feel free to contact me via emial.

Hobbies

My hobbies include reading books, especially whodunits and scientific fictions. Classic scientific movies are also appropriate for my taste. Regarding sports, billiards and badminton attracts me most.

Selected Publications

2022

A model-adaptive clustering-based time aggregation method for low-carbon energy system optimization

Yuheng Zhang, Vivian Cheng, Dharik S Mallapragada, and 2 more authors

IEEE Transactions on Sustainable Energy, 2022

Abs Code

Intermittent renewable energy resources like wind and solar introduce uncertainty across multiple time scales, from minutes to years, on the design and operation of power systems. Energy system optimization models have been developed to find the least-cost solution that manages the multi-timescale variability using an optimal portfolio of flexible resources. However, input data that capture such multi-timescale uncertainty are characterized with a long time horizon and high resolution, which brings great difficulty to solving the optimization model. Here we propose a model-adaptive time aggregation method based on clustering to alleviate the computational complexity, in which the energy system is solved over selected representative time periods instead of the full time horizon. The proposed clustering method is adaptive to various energy system optimization models or settings, because it extracts features from the optimization models to inform the clustering process. Results show that the proposed adaptive method can significantly lower the error in approximating the solution of the optimization model with the full time horizon, compared to traditional time aggregation methods.