Deep Reinforcement Learning Enhanced Greedy Optimization for Online Scheduling of Batched Tasks in Cloud HPC Systems

Yuanhao Yang, Hong Shen

Research output: Contribution to journalArticlepeer-review

12 Citations (Scopus)

Abstract

In a large cloud data center HPC system, a critical problem is how to allocate the submitted tasks to heterogeneous servers that will achieve the goal of maximizing the system's gain defined as the value of completed tasks minus system operation costs. We consider this problem in the online setting that tasks arrive in batches and propose a novel deep reinforcement learning (DRL) enhanced greedy optimization algorithm of two-stage scheduling interacting task sequencing and task allocation. For task sequencing, we deploy a DRL module to predict the best allocation sequence for each arriving batch of tasks based on the knowledge (allocation strategies) learnt from previous batches. For task allocation, we propose a greedy strategy that allocates tasks to servers one by one online following the allocation sequence to maximize the total gain increase. We show that our greedy strategy has a performance guarantee of competitive ratio $\frac{1}{1+\kappa }$11+κ to the optimal offline solution, which improves the existing result for the same problem, where $\kappa$κ is upper bounded by the maximum cost-to-gain ratio of each task. While our DRL module enhances the greedy algorithm by providing the likely-optimal allocation sequence for each batch of arriving tasks, our greedy strategy bounds DRL's prediction error within a proven worst-case performance guarantee for any allocation sequence. It enables a better solution quality than that obtainable from both DRL and greedy optimization alone. Extensive experiment evaluation results in both simulation and real application environments demonstrate the effectiveness and efficiency of our proposed algorithm. Compared with the state-of-the-art baselines, our algorithm increases the system gain by about 10% to 30%. Our algorithm provides an interesting example of combining machine learning (ML) and greedy optimization techniques to improve ML-based solutions with a worst-case performance guarantee for solving hard optimization problems.

Original languageEnglish
Pages (from-to)3003-3014
Number of pages12
JournalIEEE Transactions on Parallel and Distributed Systems
Volume33
Issue number11
DOIs
Publication statusPublished - 1 Nov 2022
Externally publishedYes

Keywords

  • Task scheduling
  • approximation algorithm
  • deep reinforcement learning
  • greedy optimization

Fingerprint

Dive into the research topics of 'Deep Reinforcement Learning Enhanced Greedy Optimization for Online Scheduling of Batched Tasks in Cloud HPC Systems'. Together they form a unique fingerprint.

Cite this