用强化学习加速大规模资源调度，效率提升43倍
iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
- 将资源调度问题转化为分步决策的强化学习模型
- 在1000个超大规模任务实例上实现43倍更快求解
- 适合需要快速重调度的云平台资源管理场景
在共享可再生资源下调度具有优先级约束的任务是现代计算平台的关键问题，通常建模为最小化资源投入成本的资源投资问题（RIP），并受优先级和时间约束。然而，对于大规模RIP实例，精确的混合整数规划和约束规划方法变得不切实际，且动态更新需在严苛延迟预算下进行调度重构。为此，我们提出iScheduler，一个基于强化学习的迭代调度框架，用于大规模RIP求解。具体而言，该框架将RIP求解建模为分解子问题上的马尔可夫决策过程，并通过顺序选择工艺流程构建调度。此方法加速优化并支持重构：复用未受影响的工艺调度，仅重调度受影响部分。为评估该框架，我们发布了L-RIPLIB，一个源自云平台工作负载的工业级基准，包含1000个实例，每个实例含2500至10000个任务。实验表明，iScheduler在保持竞争性资源成本的同时，将达可行解的时间缩短高达43倍，优于领先的求解器基基线。
原文摘要 · Abstract (English)
Scheduling precedence-constrained tasks under shared renewable resources is critical to modern computing platforms. It is often modeled as the Resource Investment Problem (RIP) by minimizing the cost of provisioned renewable resources under precedence and timing constraints. Unfortunately, exact mixed-integer programming and constraint programming become impractically slow on large RIP instances, and dynamic updates require schedule revisions under tight latency budgets. To address this, we present iScheduler, a reinforcement-learning-driven iterative scheduling framework for large RIP. Specifically, it formulates RIP solving as a Markov decision process over decomposed subproblems and constructs schedules through sequential process selection. By doing this, the framework accelerates optimization and supports reconfiguration by reusing unchanged process schedules and rescheduling only affected processes. To evaluate this framework, we release L-RIPLIB, an industrial-scale benchmark derived from cloud-platform workloads with 1,000 instances of 2,500-10,000 tasks. Our experiments show that iScheduler attains competitive resource costs while reducing time to feasibility by up to 43$\times$ against leading solver-backed baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。