DDRM: An SLO-aware Deep Dynamic Resource Management Framework for Microservices

Loosely coupled microservice architectures have been widely adopted in cloud-native applications due to their inherent advantages in modularity, development agility, and scalability. However, the resulting complex and dynamic service topologies introduce intricate inter-service dependencies, which o...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings / IEEE International Conference on Cluster Computing pp. 1 - 12
Main Authors: Tang, Liangping, Wang, Jin, Wang, Wanyou, Shi, Gaotao, Li, Zhijun
Format: Conference Proceeding
Language:English
Published: IEEE 02.09.2025
Subjects:
Adaptation models
Cloud computing
Collaboration
Deep learning
deep learning for systems
Dynamic scheduling
Microservice architectures
microservices
resource efficiency
resource man-agement
Resource management
Scalability
Stability analysis
Thermal stability
ISSN:2168-9253
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Loosely coupled microservice architectures have been widely adopted in cloud-native applications due to their inherent advantages in modularity, development agility, and scalability. However, the resulting complex and dynamic service topologies introduce intricate inter-service dependencies, which often lead to backpressure effects and queuing delays. These phenomena significantly challenge traditional monolithic and rule-based resource management approaches, which struggle to capture the non-linear performance characteristics and long-term effects of resource allocation decisions in such environments. To address these challenges, we propose DDRM, a two-stage predictor-decider collaborative framework for dynamic resource management in microservice systems. DDRM integrates deep learning to model inter-service interactions and predict the probability of Service Level Objective (SLO) violations, and employs reinforcement learning to optimize resource allocation decisions by maximizing long-term cumulative rewards while meeting SLO targets. Extensive evaluations demonstrate that DDRM outperforms state-of-the-art baselines by up to 29.8 %, while exhibiting strong stability and adaptability under highly varying workloads.
ISSN:2168-9253
DOI:10.1109/CLUSTER59342.2025.11186472