Smart Power, Energy, and Decision-making (SPEED) Lab

Dr. Xin Chen co-directs the Consortium on AI and Large Flexible Load (CALL) at Texas A&M University with Prof. Prasad Enjeti. CALL serves as a multidisciplinary platform connecting academia and industry to advance knowledge and development at the intersection of AI, power electronics-driven energy systems, and large electric loads (particularly data centers). 

NewS 

• [09/2025] Together with Prof. Yize Chen from UAlberta and Prof. Yuanyuan Shi from UCSD, Prof. Xin Chen is co-organizing a tutorial on “Modeling and Optimization for Carbon Emissions in Power Systems” at SmartGridComm 2025. Our tutorial’s programs, presentations, slides, and coding examples are all available online. Please check our tutorial website for details.  

• [09/2025] Our project “AI-Driven High-Performance Algorithms and Tools for Stability-Constrained Optimization in Modern Electric Power Systems“, in collaboration with Prof. Lin Gong at PVAMU, was awarded a grant by the 2025 PRISE (Panther Research & Innovation for Scholarly Excellence) Grant Program. 

• [09/2025] Check out our new review and vision paper titled “Electricity Demand and Grid Impacts of AI Data Centers: Challenges and Prospects“, which presents the characteristics and patterns of AI data center loads, highlights the critical challenges for the grid, and discusses potential solutions. 

• [08/2025] Excited to share that our collaborative project “Dynamic Grid Optimization under High Renewable Penetration: Multistage Algorithms and Stability Augmentation” has been selected for an award by the National Science Foundation (NSF) under the Algorithms for Modern Power Systems (AMPS) program. 

• [07/2025] Dr. Xin Chen is invited to serve as a Technical Program Committee (TPC) Member of ACM e-Energy 2026.

• [07/2025] Check out our new preprint “Regression-Based Single-Point Zeroth-Order Optimization“, which proposes a novel yet simple single-point zeroth-order optimization (SZO) framework, termed regression-based SZO (RESZO). It substantially enhances the convergence rate by leveraging previous function evaluations. Surprisingly, the proposed RESZO not only matches but empirically outperforms two-point ZO in terms of function query complexity. 

• [05/2025] Our paper “Cost-Aware Inner-Ball Represented Economic Flexibility Characterization for Distribution Systems Under Uncertainties” won the Best Paper Award at the 2025 IEEE Power & Energy Society (PES) General Meeting. 

• [05/2025] Check out our two new preprints: 1) “Distributed Coordination of Grid-Forming and Grid-Following Inverters for Optimal Frequency Control in Power Systems“, and 2) “Alternating Methods for Large-Scale AC Optimal Power Flow with Unit Commitment“.

• [03/2025] Our paper “Bayesian Active Learning-Based Soft Data Space Calibration for System-Wise Aggregate Flexibility Characterization” has been accepted to the IEEE Transactions on Smart Grid (TSG).

• [02/2025] Our two papers “Distributed Coordination of Grid-Forming and Grid-Following Inverter-Based Resources for Optimal Frequency Control in Power Systems“ and “Cost-Aware Inner-Ball Represented Economic Flexibility Characterization for Distribution Systems Under Uncertainties” have been accepted to the 2025 IEEE PES General Meeting. See you in Austin!

• [01/2025] Our paper “Continuous-Time Zeroth-Order Dynamics with Projection Maps: Model-Free Feedback Optimization with Safety Guarantees” has been accepted to the IEEE Transactions on Automatic Control (TAC). This paper introduces a class of model-free projected zeroth-order dynamics algorithms that can autonomously drive an unknown system toward an optimal solution of an optimization problem using only output feedback.

• [01/2025] Dr. Xin Chen was invited to present a talk “Model-Free Power System Control and Optimization via Zeroth-Order Methods” at the 2025 Grid Science Winter School and Conference hosted by the Los Alamos National Laboratory.

• [11/2024] Excited to share that our project “Research, Development and Demonstration of a Natural Hazard and Large Language Model Enhanced Electric Grid Planning Tool” was selected for an award by the Department of Energy (DOE) National Energy Technology Laboratory.

• [11/2024] Our paper “Carbon-Aware Optimal Power Flow” has been accepted to the IEEE Transactions on Power Systems (TPWRS). This paper incorporates carbon emission flow equations, constraints, and carbon-related objectives into the OPF framework, formulating a generic C-OPF model to jointly optimize the grid’s electric power flow and carbon emission footprint.