publications

2025

1. ACL Findings

   Beyond numeric awards: In-context dueling bandits with LLM agents

   Findings of the Association for Computational Linguistics 2025
2. CDC

   InstructMPC: A Human-LLM-in-the-Loop Framework for Context-Aware Control

   R Wu, T Li

   The 64th IEEE Conference on Decision and Control 2025
3. SIGEnergy

   Learning-Augmented Online Control for Decarbonizing Water Infrastructures

   Proceedings of the ACM International Conference on Future and Sustainable Energy Systems 2025
4. SIGEnergy Demo

   Open In-Context Energy Management Platform

   Proceedings of the ACM International Conference on Future and Sustainable Energy Systems 2025
5. NeurIPS

   Reinforcement Learning with Imperfect Transition Predictions: A Bellman-Jensen Approach

   Advances in Neural Information Processing Systems 2025
6. EDS

   Robust machine-learned algorithms for efficient grid operation

   Environmental Data Science, Cambridge University Press 2025

2024

1. NeurIPS

   Anytime-competitive reinforcement learning with policy prior

   Advances in Neural Information Processing Systems 2024
2. NeurIPS

   Beyond black-box advice:learning-augmented algorithms for MDPs with Q-value predictions

   Advances in Neural Information Processing Systems 2024
3. ICML

   Building Socially-Equitable Public Models

   Forty-first International Conference on Machine Learning 2024
4. NeurIPS

   Disentangling Linear Quadratic Control with Untrusted ML Predictions

   T Li, Y Yue

   Advances in Neural Information Processing Systems 2024
5. TTE

   Hierarchical game for coupled power system with energy sharing and transportation system

   IEEE Transactions on Transportation Electrification 2024
6. TTE

   Out-of-Distribution-Aware Electric Vehicle Charging

   T Li, C Sun

   IEEE Transactions on Transportation Electrification 2024
7. NeurIPS

   Safe Exploitative Play with Untrusted Type Beliefs

   Advances in Neural Information Processing Systems 2024

2023

1. OJ-CSYS

   Certifying black-box policies with stability for nonlinear control

   IEEE Open Journal of Control Systems 2, 49-62 2023

2022

1. NeurIPS

   Bounded-regret MPC via perturbation analysis: prediction error, constraints, and nonlinearity

   Advances in Neural Information Processing Systems 2022
2. SIGMETRICS

   Robustness and Consistency in Linear Quadratic Control with Untrusted Predictions

   Li, Tongxin, Yang, Ruixiao, Qu, Guannan, Shi, Guanya, Yu, Chenkai, Wierman, Adam, and Low, Steven

   Proceedings of the ACM on Measurement and Analysis of Computing Systems 2022

   Abs

   We study the problem of learning-augmented predictive linear quadratic control. Our goal is to design a controller that balances consistency, which measures the competitive ratio when predictions are accurate, and robustness, which bounds the competitive ratio when predictions are inaccurate.

3. PSCC

   Towards balanced three-phase charging: Phase optimization in adaptive charging networks

   Z Ye, S Low

   Electric Power Systems Research 2022

2021

1. SIGMETRICS

   Information Aggregation for Constrained Online Control

   Li, Tongxin, Chen, Yue, Sun, Bo, Wierman, Adam, and Low, Steven H

   Proceedings of the ACM on Measurement and Analysis of Computing Systems 2021
2. TSG

   Learning-based Predictive Control via Real-time Aggregate Flexibility

   Li, Tongxin, Sun, Bo, Chen, Yue, Ye, Zixin, Low, Steven H, and Wierman, Adam

   IEEE Transactions on Smart Grid 2021

   Abs

   Aggregators have emerged as crucial tools for the coordination of distributed, controllable loads. To be used effectively, an aggregator must be able to communicate the available flexibility of the loads they control, as known as the aggregate flexibility to a system operator. However, most of existing aggregate flexibility measures often are slow-timescale estimations and much less attention has been paid to real-time coordination between an aggregator and an operator. In this paper, we consider solving an online optimization in a closed-loop system and present a design of real-time aggregate flexibility feedback, termed the maximum entropy feedback (MEF). In addition to deriving analytic properties of the MEF, combining learning and control, we show that it can be approximated using reinforcement learning and used as a penalty term in a novel control algorithm – the penalized predictive control (PPC), which modifies vanilla model predictive control (MPC). The benefits of our scheme are (1). Efficient Communication. An operator running PPC does not need to know the exact states and constraints of the loads, but only the MEF. (2). Fast Computation. The PPC often has much less number of variables than an MPC formulation. (3). Lower Costs. We show that under certain regularity assumptions, the PPC is optimal. We illustrate the efficacy of the PPC using a dataset from an adaptive electric vehicle charging network and show that PPC outperforms classical MPC.

2020

1. TPS

   Decentralized provision of renewable predictions within a virtual power plant

   Chen, Yue,  Li, Tongxin, Zhao, Changhong, and Wei, Wei

   IEEE Transactions on Power Systems 2020
2. TSIPN

   Learning graphs from linear measurements: Fundamental trade-offs and applications

   Li, Tongxin, Werner, Lucien, and Low, Steven H

   IEEE Transactions on Signal and Information Processing over Networks 2020
3. SIGEnergy

   Real-time flexibility feedback for closed-loop aggregator and system operator coordination

   Li, Tongxin, Low, Steven H, and Wierman, Adam

   In Proceedings of the ACM International Conference on Future Energy Systems 2020
4. PSCC

   Classification of electric vehicle charging time series with selective clustering

   Sun, Chenxi,  Li, Tongxin, Low, Steven H, and Li, Victor OK

   Electric Power Systems Research 2020
5. SIGMETRICS

   Competitive algorithms for the online multiple knapsack problem with application to electric vehicle charging

   Sun, Bo, Zeynali, Ali,  Li, Tongxin, Hajiesmaili, Mohammad, Wierman, Adam, and Tsang, Danny HK

   Proceedings of the ACM on Measurement and Analysis of Computing Systems 2020
6. SIGEnergy

   ORC: An Online Competitive Algorithm for Recommendation and Charging Schedule in Electric Vehicle Charging Network

   Sun, Bo,  Li, Tongxin, Low, Steven H, and Tsang, Danny HK

   In Proceedings of the Eleventh ACM International Conference on Future Energy Systems 2020

2019

1. SIGEnergy

   ACN-Data: Analysis and applications of an open EV charging dataset

   Lee, Zachary J,  Li, Tongxin, and Low, Steven H

   In Proceedings of the Tenth ACM International Conference on Future Energy Systems 2019
2. CDC

   Learning Graph Parameters from Linear Measurements: Fundamental Trade-offs and Application to Electric Grids

   Li, Tongxin, Werner, Lucien, and Low, Steven H

   In 2019 IEEE 58th Conference on Decision and Control (CDC) 2019