Collaborative Multi-Agent Reinforcement Learning Approach for Elastic Cloud Resource Scaling

TL;DR

This paper introduces a multi-agent reinforcement learning approach for elastic cloud resource scaling, improving responsiveness, resource utilization, and system robustness in dynamic cloud environments.

Contribution

It presents a novel collaborative multi-agent framework with a lightweight prediction model and centralized training for effective cloud resource scaling.

Findings

Outperforms existing methods in resource utilization and SLA compliance

Enhances responsiveness and scheduling latency in cloud environments

Demonstrates strong adaptability and robustness in experiments

Abstract

This paper addresses the challenges of rapid resource variation and highly uncertain task loads in cloud computing environments. It proposes an optimization method for elastic cloud resource scaling based on a multi-agent system. The method deploys multiple autonomous agents to perceive resource states in parallel and make local decisions. While maintaining the distributed nature of the system, it introduces a collaborative value function to achieve global coordination. This improves the responsiveness of resource scheduling and enhances overall system performance. To strengthen system foresight, a lightweight state prediction model is designed. It assists agents in identifying future workload trends and optimizes the selection of scaling actions. For policy training, the method adopts a centralized training and decentralized execution reinforcement learning framework. This enables agents to learn effectively and coordinate strategies under conditions of incomplete information. The paper also constructs typical cloud scenarios, including multi-tenancy and burst traffic, to evaluate the proposed method. The evaluation focuses on resource isolation, service quality assurance, and robustness. Experimental results show that the proposed multi-agent scaling strategy outperforms existing methods in resource utilization, SLA violation control, and scheduling latency. The results demonstrate strong adaptability and intelligent regulation. This provides an efficient and reliable new approach to solving the problem of elastic resource scaling in complex cloud platforms.