Qing-Shan Jia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Qing-Shan Jia has a total of 142 co-authors. Here are the top co-authors by number of shared publications:
- Xiaohong Guan
Xi'an Jiaotong University, Xi'an, China
22 shared publications Xiaohong Guan
Center for Intelligent and Networked Systems, Beijing National Research Center for Information Science and Technology, Department of Automation, Tsinghua University, Beijing, China
9 shared publications- Qianchuan Zhao
Tsinghua University
5 shared publications - Gongming Wang
Department of Information, Beijing University of Technology, Beijing, China
4 shared publications - Junfei Qiao
Beijing University of Technology
4 shared publications - Karl Henrik Johansson
KTH Royal Institute of Technology
4 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 41 (6) , 4306-4318
Historical-Data-Free and System-Independent Training: A Neural Network-Assisted Improved Lagrangian Relaxation Method for Large-Scale Security-Constrained Unit Commitment
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 41 (6) , 4306-4318
Historical-Data-Free and System-Independent Training: A Neural Network-Assisted Improved Lagrangian Relaxation Method for Large-Scale Security-Constrained Unit Commitment
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 17 (6) , 5448-5459
A Unified Virtual Battery Modeling Framework for Flexibility Characterization of Building HVAC Systems
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 17 (6) , 5448-5459
A Unified Virtual Battery Modeling Framework for Flexibility Characterization of Building HVAC Systems
- 3 September 2026
- Published by Elsevier in Building and Environment
- Vol. 305
Experimental study on surveillance video-based indoor occupancy measurement for occupant-centric control
- 3 September 2026
- Published by Elsevier in Building and Environment
- Vol. 305
Experimental study on surveillance video-based indoor occupancy measurement for occupant-centric control
- 23 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. PP (08858950) , 1-14
A Multi-timescale Learn-to-Optimize Method for Unit Commitment with Renewable Power
The high penetration of volatile renewable power has created an urgent need for fast methods to solve large scale security-constrained unit commitment (SCUC) problems. In this paper, we propose a multi-timescale learn-to-optimize (MT L2O) method to efficiently solve large-scale stochastic SCUC. The coarse timescale serves as a learning-based presolving stage. At this scale, we propose a group-based multi-resolution formulation where machine learning (ML) techniques are used to predict integer variables and fix those with high confidence for finer timescales. Therefore, problems at finer timescales are reduced in size and can be solved more efficiently. Compared to existing works, when learning at the coarse scale, binary status constraints spanning multiple time periods become inactive. This not only significantly reduces data dimensionality but also eliminates the need for feasibility recovery measures targeting these constraints. At finer timescales, we develop constraint reduction methods for two types of constraints based on the on/off status determined at coarser timescales. Numerical experiments on IEEE 118-bus system, IEEE 300-bus system, and a 3266-bus system based on a practical provincial grid in China demonstrate that our methods obtain near-optimal solutions with an average performance gap not exceeding 0.4% and achieve speedups of 3.03 to 34.46 times compared to the commercial solver Gurobi.
- 23 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. PP (08858950) , 1-14
A Multi-timescale Learn-to-Optimize Method for Unit Commitment with Renewable Power
The high penetration of volatile renewable power has created an urgent need for fast methods to solve large scale security-constrained unit commitment (SCUC) problems. In this paper, we propose a multi-timescale learn-to-optimize (MT L2O) method to efficiently solve large-scale stochastic SCUC. The coarse timescale serves as a learning-based presolving stage. At this scale, we propose a group-based multi-resolution formulation where machine learning (ML) techniques are used to predict integer variables and fix those with high confidence for finer timescales. Therefore, problems at finer timescales are reduced in size and can be solved more efficiently. Compared to existing works, when learning at the coarse scale, binary status constraints spanning multiple time periods become inactive. This not only significantly reduces data dimensionality but also eliminates the need for feasibility recovery measures targeting these constraints. At finer timescales, we develop constraint reduction methods for two types of constraints based on the on/off status determined at coarser timescales. Numerical experiments on IEEE 118-bus system, IEEE 300-bus system, and a 3266-bus system based on a practical provincial grid in China demonstrate that our methods obtain near-optimal solutions with an average performance gap not exceeding 0.4% and achieve speedups of 3.03 to 34.46 times compared to the commercial solver Gurobi.
- 16 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23 (15455955) , 8263-8275
A Bayesian Optimization Method for Design Space Exploration of Processors With Efficient Evaluation Budget Allocation
Design space exploration (DSE), which aims to optimize the parameter configurations for the processor with a limited evaluation budget, is an important but challenging problem. Processor performance for a given parameter configuration can only be obtained through expensive evaluations. A key characteristic of processor DSE is that the optimization objective is the benchmark score, which is typically computed as a weighted combination of multiple sub-benchmark scores. Each sub-benchmark score can only be obtained through a costly evaluation. Bayesian optimization (BO) is widely used for DSE through an iterative process, where a surrogate model is constructed and updated to guide the selection of parameter configurations in each iteration. However, during the optimization process, it is not always necessary to evaluate all subbenchmarks for every recommended parameter configuration. In some cases, evaluating only a subset of sub-benchmarks can still provide significant improvements to the surrogate model. This paper proposes a BO-based algorithm that effectively utilizes the evaluation budget for efficient optimization. In each iteration, the evaluation budget is divided into two parts: exploitation and exploration. For the exploitation part, we propose a diversity-aware horse racing selection rule and use ordinal optimization to identify configurations with a high likelihood of being optimal. They are evaluated on all sub-benchmarks to obtain the total scores. For the exploration part, we propose a conditional entropy-based greedy algorithm to allocate the evaluation budget across parameter configurations and their corresponding sub-benchmarks, which can effectively improve the surrogate model. We conduct a comprehensive numerical experiment to validate the effectiveness of both components of our algorithm. Furthermore, experiments on three real-world DSE problems demonstrate that our algorithm outperforms state-of-the-art Bayesian optimization methods.
- 16 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23 (15455955) , 8263-8275
A Bayesian Optimization Method for Design Space Exploration of Processors With Efficient Evaluation Budget Allocation
Design space exploration (DSE), which aims to optimize the parameter configurations for the processor with a limited evaluation budget, is an important but challenging problem. Processor performance for a given parameter configuration can only be obtained through expensive evaluations. A key characteristic of processor DSE is that the optimization objective is the benchmark score, which is typically computed as a weighted combination of multiple sub-benchmark scores. Each sub-benchmark score can only be obtained through a costly evaluation. Bayesian optimization (BO) is widely used for DSE through an iterative process, where a surrogate model is constructed and updated to guide the selection of parameter configurations in each iteration. However, during the optimization process, it is not always necessary to evaluate all subbenchmarks for every recommended parameter configuration. In some cases, evaluating only a subset of sub-benchmarks can still provide significant improvements to the surrogate model. This paper proposes a BO-based algorithm that effectively utilizes the evaluation budget for efficient optimization. In each iteration, the evaluation budget is divided into two parts: exploitation and exploration. For the exploitation part, we propose a diversity-aware horse racing selection rule and use ordinal optimization to identify configurations with a high likelihood of being optimal. They are evaluated on all sub-benchmarks to obtain the total scores. For the exploration part, we propose a conditional entropy-based greedy algorithm to allocate the evaluation budget across parameter configurations and their corresponding sub-benchmarks, which can effectively improve the surrogate model. We conduct a comprehensive numerical experiment to validate the effectiveness of both components of our algorithm. Furthermore, experiments on three real-world DSE problems demonstrate that our algorithm outperforms state-of-the-art Bayesian optimization methods.
- Open Access
- 30 January 2026
- Published by Springer Nature in Discrete Event Dynamic Systems
- Vol. 36 (1)
Machine learning-enhanced vector ordinal optimization for multi-objective stochastic unit commitment
- 30 January 2026
- Published by Springer Nature in Discrete Event Dynamic Systems
- Vol. 36 (1)
Open AccessMachine learning-enhanced vector ordinal optimization for multi-objective stochastic unit commitment
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23, 14725-14741
Multi-Agent Reinforcement Learning via Agent-Specific Preference
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23, 14725-14741
Multi-Agent Reinforcement Learning via Agent-Specific Preference
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23 (15455955) , 3916-3933
Consensus-Based Distributed Reinforcement Learning With Primal–Dual Update for Networked Microgrids On-Line Coordination
This paper develops a distributed reinforcement learning (RL) method to coordinate cooperative microgrids (MGs). The high uncertainty of power loads and renewable energy sources motivate the operator to perform real-time dispatch. On the one hand, the existing online methods usually utilize approximate models that result in intractable constraint violation. A common method is to relax it as a chance constraint, while it is still hard to ensure its satisfaction in practice. On the other hand, some MGs may hope to preserve the private information on their local costs and states. To address these problems, we make the following contributions. First, the coordination problem is reformulated as a constrained multi-agent Markov decision process. Second, the distributed RL algorithm with a theoretical convergence guarantee is developed. Third, to further preserve the local private information and improve the performance, this algorithm is modified by adding a local feature extraction module for each agent. This module could also be regarded as an encryption module for the local state information. Fourth, numerical experiments are carried out to validate the effectiveness of the modified algorithm.
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23 (15455955) , 3916-3933
Consensus-Based Distributed Reinforcement Learning With Primal–Dual Update for Networked Microgrids On-Line Coordination
This paper develops a distributed reinforcement learning (RL) method to coordinate cooperative microgrids (MGs). The high uncertainty of power loads and renewable energy sources motivate the operator to perform real-time dispatch. On the one hand, the existing online methods usually utilize approximate models that result in intractable constraint violation. A common method is to relax it as a chance constraint, while it is still hard to ensure its satisfaction in practice. On the other hand, some MGs may hope to preserve the private information on their local costs and states. To address these problems, we make the following contributions. First, the coordination problem is reformulated as a constrained multi-agent Markov decision process. Second, the distributed RL algorithm with a theoretical convergence guarantee is developed. Third, to further preserve the local private information and improve the performance, this algorithm is modified by adding a local feature extraction module for each agent. This module could also be regarded as an encryption module for the local state information. Fourth, numerical experiments are carried out to validate the effectiveness of the modified algorithm.
- Open Access
STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning
Preference-based reinforcement learning (PbRL) bypasses complex reward engineering by learning rewards directly from human preferences, enabling better alignment with human intentions. However, its effectiveness in multi-stage tasks, where agents sequentially perform sub-tasks (e.g., navigation, grasping), is limited by stage misalignment: Comparing segments from mismatched stages, such as movement versus manipulation, results in uninformative feedback, thus hindering policy learning. In this paper, we validate the stage misalignment issue through theoretical analysis and empirical experiments. To address this issue, we propose STage-AlIgned Reward learning (STAIR), which first learns a stage approximation based on temporal distance, then prioritizes comparisons within the same stage. Temporal distance is learned via contrastive learning, which groups temporally close states into coherent stages, without predefined task knowledge, and adapts dynamically to policy changes. Extensive experiments demonstrate STAIR's superiority in multi-stage tasks and competitive performance in single-stage tasks. Furthermore, human studies show that stages approximated by STAIR are consistent with human cognition, confirming its effectiveness in mitigating stage misalignment.
Open AccessSTAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning
Preference-based reinforcement learning (PbRL) bypasses complex reward engineering by learning rewards directly from human preferences, enabling better alignment with human intentions. However, its effectiveness in multi-stage tasks, where agents sequentially perform sub-tasks (e.g., navigation, grasping), is limited by stage misalignment: Comparing segments from mismatched stages, such as movement versus manipulation, results in uninformative feedback, thus hindering policy learning. In this paper, we validate the stage misalignment issue through theoretical analysis and empirical experiments. To address this issue, we propose STage-AlIgned Reward learning (STAIR), which first learns a stage approximation based on temporal distance, then prioritizes comparisons within the same stage. Temporal distance is learned via contrastive learning, which groups temporally close states into coherent stages, without predefined task knowledge, and adapts dynamically to policy changes. Extensive experiments demonstrate STAIR's superiority in multi-stage tasks and competitive performance in single-stage tasks. Furthermore, human studies show that stages approximated by STAIR are consistent with human cognition, confirming its effectiveness in mitigating stage misalignment.
- Open Access
- 27 September 2025
- Published by Elsevier in Results in Control and Optimization
- Vol. 21
An accelerated black-box sample paths feasibility probability estimation method for control policies of autonomous vehicles
- 27 September 2025
- Published by Elsevier in Results in Control and Optimization
- Vol. 21
Open AccessAn accelerated black-box sample paths feasibility probability estimation method for control policies of autonomous vehicles