Minghua Chen

Minghua Chen is a Presidential Chair Professor and Director of the Design and Analysis of Networked, Computing, and Energy (DANCE) Systems Lab at the School of Data Science, The Chinese University of Hong Kong (Shenzhen). He is also affiliated with the Department of Data Science at City University of Hong Kong (on leave). His research spans machine learning, optimization, energy systems, and networked systems, with a focus on performance guarantees and real-time applications.

• Education:
  • PhD in Electrical Engineering and Computer Sciences, UC Berkeley (2006)
  • Master in Electrical Engineering, Tsinghua University (2001)

Research Interests:
Minghua Chen investigates machine learning with performance guarantees, online optimization algorithms, energy systems (smart grids, energy-efficient data centers), intelligent transportation systems, distributed optimization, delay-constrained network coding, and data-driven prediction in system design. His work bridges theoretical rigor with practical implementations in wireless networks, power systems, and peer-to-peer communications.

Publication Trends:
His recent publications demonstrate a strong focus on machine learning applications in energy and transportation systems, particularly AC optimal power flow problems and emission-minimizing truck routing. He integrates neural networks with optimization theory, emphasizing feasibility guarantees and low-complexity algorithms. His work also explores age-of-information (AoI) optimization and multi-armed bandit approaches for model freshness.

Scientific Awards:

• IEEE Transactions on Multimedia Prize Paper Award (2009)
• Eli Jury Award, EECS Department, UC Berkeley (2007)
• Best Paper Awards at ACM e-Energy 2023, IEEE INFOCOM 2022 (Poster), and ACM Multimedia 2012
• Multiple Best Paper Finalists and Runner-ups

Labs and Teams:
He leads the DANCE Systems Lab, which develops theoretical frameworks and practical systems for networked, computing, and energy optimization. His team collaborates on projects like WISER (indoor white space networking) and DeepOPF series for power flow optimization.