Saved in:
Bibliographic Details
Main Authors: Prodanov, Jovan, Bertalanič, Blaž, Fortuna, Carolina, Chou, Shih-Kai, Jurič, Matjaž Branko, Sanchez-Iborra, Ramon, Hribar, Jernej
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.07671
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911149691240448
author Prodanov, Jovan
Bertalanič, Blaž
Fortuna, Carolina
Chou, Shih-Kai
Jurič, Matjaž Branko
Sanchez-Iborra, Ramon
Hribar, Jernej
author_facet Prodanov, Jovan
Bertalanič, Blaž
Fortuna, Carolina
Chou, Shih-Kai
Jurič, Matjaž Branko
Sanchez-Iborra, Ramon
Hribar, Jernej
contents Modern edge-cloud systems face challenges in efficiently scaling resources to handle dynamic and unpredictable workloads. Traditional scaling approaches typically rely on static thresholds and predefined rules, which are often inadequate for optimizing resource utilization and maintaining performance in distributed and dynamic environments. This inefficiency hinders the adaptability and performance required in edge-cloud infrastructures, which can only be achieved through the newly proposed in-place scaling. To address this problem, we propose the Multi-Agent Reinforcement Learning-based In-place Scaling Engine (MARLISE) that enables seamless, dynamic, reactive control with in-place resource scaling. We develop our solution using two Deep Reinforcement Learning algorithms: Deep Q-Network (DQN), and Proximal Policy Optimization (PPO). We analyze each version of the proposed MARLISE solution using dynamic workloads, demonstrating their ability to ensure low response times of microservices and scalability. Our results show that MARLISE-based approaches outperform heuristic method in managing resource elasticity while maintaining microservice response times and achieving higher resource efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2507_07671
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-agent Reinforcement Learning-based In-place Scaling Engine for Edge-cloud Systems
Prodanov, Jovan
Bertalanič, Blaž
Fortuna, Carolina
Chou, Shih-Kai
Jurič, Matjaž Branko
Sanchez-Iborra, Ramon
Hribar, Jernej
Distributed, Parallel, and Cluster Computing
Modern edge-cloud systems face challenges in efficiently scaling resources to handle dynamic and unpredictable workloads. Traditional scaling approaches typically rely on static thresholds and predefined rules, which are often inadequate for optimizing resource utilization and maintaining performance in distributed and dynamic environments. This inefficiency hinders the adaptability and performance required in edge-cloud infrastructures, which can only be achieved through the newly proposed in-place scaling. To address this problem, we propose the Multi-Agent Reinforcement Learning-based In-place Scaling Engine (MARLISE) that enables seamless, dynamic, reactive control with in-place resource scaling. We develop our solution using two Deep Reinforcement Learning algorithms: Deep Q-Network (DQN), and Proximal Policy Optimization (PPO). We analyze each version of the proposed MARLISE solution using dynamic workloads, demonstrating their ability to ensure low response times of microservices and scalability. Our results show that MARLISE-based approaches outperform heuristic method in managing resource elasticity while maintaining microservice response times and achieving higher resource efficiency.
title Multi-agent Reinforcement Learning-based In-place Scaling Engine for Edge-cloud Systems
topic Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2507.07671