mlsanityData to 14 Oct 2026

Symmetry-Preserving Architecture for Multi-NUMA Environments (SPANE): A Deep Reinforcement Learning Approach for Dynamic VM Scheduling

arXiv 2504.14946 ↗First posted 21 Apr 2025cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL for energy, networks and operations

Abstract (arXiv)

As cloud computing continues to evolve, the adoption of multi-NUMA (Non-Uniform Memory Access) architecture by cloud service providers has introduced new challenges in virtual machine (VM) scheduling. To address these challenges and more accurately reflect the complexities faced by modern cloud environments, we introduce the Dynamic VM Allocation problem in Multi-NUMA PM (DVAMP). We formally define both offline and online versions of DVAMP as mixed-integer linear programming problems, providing a rigorous mathematical foundation for analysis. A tight performance bound for greedy online algorithms is derived, offering insights into the worst-case optimality gap as a function of the number of physical machines and VM lifetime variability. To address the challenges posed by DVAMP, we propose SPANE (Symmetry-Preserving Architecture for Multi-NUMA Environments), a novel deep reinforcement learning approach that exploits the problem's inherent symmetries. SPANE produces invariant results under arbitrary permutations of physical machine states, enhancing learning efficiency and solution quality. Extensive experiments conducted on the Huawei-East-1 dataset demonstrate that SPANE outperforms existing baselines, reducing average VM wait time by 45%. Our work contributes to the field of cloud resource management by providing both theoretical insights and practical solutions for VM scheduling in multi-NUMA environments, addressing a critical gap in the literature and offering improved performance for real-world cloud systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 5 of its 29 references that are in the map. First posted on arXiv 21 Apr 2025.

Builds on

5 of 29 references.

References · 5

  1. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,745
  2. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 785
  3. 2020MDP Homomorphic Networks: Group Symmetries in Reinforcement Learningcited by 142
  4. 2021Deep Reinforcement Learning-based Methods for Resource Scheduling in Cloud Computing: A Review and Future Directionscited by 14
  5. 2023Dynamic Vector Bin Packing for Online Resource Allocation in the Cloudcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Deep Reinforcement Learning for Job Scheduling and Resource Management in Cloud Computing: An Algorithm-Level Review
  2. 2024Towards Fair and Firm Real-Time Scheduling in DNN Multi-Tenant Multi-Accelerator Systems via Reinforcement Learning
  3. 2025Towards VM Rescheduling Optimization Through Deep Reinforcement Learning
  4. 2025Scalable Reinforcement Learning for Virtual Machine Scheduling
  5. 2024Deep Reinforcement Learning based Online Scheduling Policy for Deep Neural Network Multi-Tenant Multi-Accelerator Systems
  6. 2025Intelligent Resource Allocation Optimization for Cloud Computing via Machine Learning
  7. 2026Multi-Timescale Latent-Action DRL for Joint Optimization in Edge-Cloud Networks
  8. 2024Cost-Aware Dynamic Cloud Workflow Scheduling using Self-Attention and Evolutionary Reinforcement Learning