iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911425608286208 |
|---|---|
| author | Hu, Yi-Xiang Wang, Yuke Wu, Feng Huang, Zirui Zeng, Shuli Li, Xiang-Yang |
| author_facet | Hu, Yi-Xiang Wang, Yuke Wu, Feng Huang, Zirui Zeng, Shuli Li, Xiang-Yang |
| contents | Scheduling precedence-constrained tasks under shared renewable resources is central to modern computing platforms. The Resource Investment Problem (RIP) models this setting by minimizing the cost of provisioned renewable resources under precedence and timing constraints. Exact mixed-integer programming and constraint programming become impractically slow on large instances, and dynamic updates require schedule revisions under tight latency budgets. We present iScheduler, a reinforcement-learning-driven iterative scheduling framework that formulates RIP solving as a Markov decision process over decomposed subproblems and constructs schedules through sequential process selection. The framework accelerates optimization and supports reconfiguration by reusing unchanged process schedules and rescheduling only affected processes. We also release L-RIPLIB, an industrial-scale benchmark derived from cloud-platform workloads with 1,000 instances of 2,500-10,000 tasks. Experiments show that iScheduler attains competitive resource costs while reducing time to feasibility by up to 43$\times$ against strong commercial baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_06064 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems Hu, Yi-Xiang Wang, Yuke Wu, Feng Huang, Zirui Zeng, Shuli Li, Xiang-Yang Distributed, Parallel, and Cluster Computing Artificial Intelligence Scheduling precedence-constrained tasks under shared renewable resources is central to modern computing platforms. The Resource Investment Problem (RIP) models this setting by minimizing the cost of provisioned renewable resources under precedence and timing constraints. Exact mixed-integer programming and constraint programming become impractically slow on large instances, and dynamic updates require schedule revisions under tight latency budgets. We present iScheduler, a reinforcement-learning-driven iterative scheduling framework that formulates RIP solving as a Markov decision process over decomposed subproblems and constructs schedules through sequential process selection. The framework accelerates optimization and supports reconfiguration by reusing unchanged process schedules and rescheduling only affected processes. We also release L-RIPLIB, an industrial-scale benchmark derived from cloud-platform workloads with 1,000 instances of 2,500-10,000 tasks. Experiments show that iScheduler attains competitive resource costs while reducing time to feasibility by up to 43$\times$ against strong commercial baselines. |
| title | iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems |
| topic | Distributed, Parallel, and Cluster Computing Artificial Intelligence |
| url | https://arxiv.org/abs/2602.06064 |