mlsanityData to 14 Oct 2026

Feasibility-Aware Security-Constrained Unit Commitment via Hybrid Soft Actor-Critic with Quantum-Sampled Features

arXiv 2606.26345 ↗First posted 24 Jun 2026eess.SY cs.SYcited by 0

On the map: Deep reinforcement learning methods → Quantum reinforcement learning

Abstract (arXiv)

Security-constrained unit commitment (SCUC) couples binary commitment, economic dispatch, reserves, and network security over a multiperiod horizon, which makes an exact solution expensive at realistic system sizes. This paper proposes a three-layer hybrid framework in which a Bernoulli hybrid soft actor-critic (HSAC) policy proposes hourly commitments, a quantum-sampled auxiliary channel augments the state, and a native SCUC mixed-integer linear program recovers dispatch and security variables after only a limited subset of commitment binaries is enforced. The method is therefore solver-compatible rather than an end-to-end replacement for exact optimization. We formalize the SCUC-to-reinforcement-learning interface, derive the temporal coverage induced by the fixed cap, and conduct representative experiments on the 14-, 57-, and 118-bus cases. The results show stable, low-cost recovery in the 14-bus case; a very low screen-rejection rate in the 57-bus case, consistent with learned feasibility generalization under fixed intertemporal SCUC constraints; and a clear coverage bottleneck in the 118-bus case once the enforcement cap no longer spans a complete commitment period. The 118-bus case runtime traces nevertheless remain tightly clustered for accepted episodes, indicating that the policy still captures a repeatable recovery pattern across most episodes. The study, therefore, identifies the dominant limitation of the current implementation as the amount of useful commitment information that reaches the recovery model under an exploratory Bernoulli actor and a small enforcement cap, and shows how that limitation governs scalability.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Quantum reinforcement learning, one of 15 directions in Deep reinforcement learning methods. Builds on 13 of its 35 references that are in the map. First posted on arXiv 24 Jun 2026.

Builds on

13 of 35 references.

References · 13

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2018Supervised learning with quantum enhanced feature spacescited by 665
  4. 2019Learning to Solve Large-Scale Security-Constrained Unit Commitment Problemscited by 40
  5. 2022JuMP 1.0: Recent improvements to a modeling language for mathematical optimizationcited by 37
  6. 2021Is learning for the unit commitment problem a low-hanging fruit?cited by 5
  7. 2022An Optimization Method-Assisted Ensemble Deep Reinforcement Learning Algorithm to Solve Unit Commitment Problemscited by 3
  8. 2025Qubit-Efficient Quantum Annealing for Stochastic Unit Commitmentcited by 2
  9. 2025Leveraging Quantum Computing for Accelerated Classical Algorithms in Power Systems Optimizationcited by 2
  10. 2025A New Hybrid Quantum-Classical Algorithm for Solving the Unit Commitment Problemcited by 2
  11. 2025D2-UC: A Distributed-Distributed Quantum-Classical Framework for Unit Commitmentcited by 2
  12. 2026A Survey on Applications of Quantum Computing for Unit Commitmentcited by 2
1 more
  1. 2026Structure-Aware Commitment Reduction for Network-Constrained Unit Commitment with Solver-Preserving Guaranteescited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Feasibility-Aware Security-Constrained Unit Commitment via Hybrid Soft Actor-Critic with Quantum-Sampled Features
  2. 2024Quantum Reinforcement Learning-Based Two-Stage Unit Commitment Framework for Enhanced Power Systems Robustness
  3. 2025Real-Time Defense Against Coordinated Cyber-Physical Attacks: A Robust Constrained Reinforcement Learning Approach
  4. 2026Differentiable Policy Transport over Multi-Layer Network Feasibility Geometry
  5. 2025Quantum-Embedded Dynamic Security Control using Hybrid Deep Reinforcement Learning
  6. 2026Multi-Objective Deep Reinforcement Learning for Secure and Stable Power System Operation
  7. 2025Logic-informed reinforcement learning for cross-domain optimization of large-scale cyber-physical systems
  8. 2025Quantum-Enhanced Reinforcement Learning for Power Grid Security Assessment