KMPS : a reinforcement learning scheduler for Kubernetes edge-cloud systems

Tools

Huang, Congyue and Tan, Wei and Ou, Miaohua and Yang, Erfu and Li, Yun (2026) KMPS : a reinforcement learning scheduler for Kubernetes edge-cloud systems. IEEE Internet of Things Journal. ISSN 2372-2541 (https://doi.org/10.1109/jiot.2026.3658608)

[thumbnail of Huang-etal-IEEE-IOTJ-2026-KMPS-a-reinforcement-learning-scheduler-for-Kubernetes-edge-cloud-systems]
Preview
 Text. Filename: Huang-etal-IEEE-IOTJ-2026-KMPS-a-reinforcement-learning-scheduler-for-Kubernetes-edge-cloud-systems.pdf
Accepted Author Manuscript
License: Creative Commons Attribution 4.0 logo
Download (2MB)| Preview

Abstract

Kubernetes (K8s) provides the foundation for integrating distributed edge-cloud resources. However, existing frameworks struggle to address the challenges of cross-cluster coordination and dynamic resource changes, limiting throughput. We propose KMPS, a deep reinforcement learning-based scheduling framework to enhance long-term throughput. KMPS integrates a multi-agent proximal policy optimization algorithm for autonomous edge access point scheduling, combined with gRPC cross-cluster scheduling and invalid target filtering; utilizes graph neural networks to embed system state information, decomposing high-dimensional service orchestration actions through multiple separate policy networks; and constructs a three-time-scale coordination mechanism (0.25s, 2s, 25s) to coordinate scheduling and orchestration, with K8s compatibility. Experiments on real workloads verify that KMPS operates stably under dynamic loads, sudden emergency tasks, and multi-cluster scenarios. Compared to baselines, the proposed framework achieves an over 5.3% increase in long-term throughput and a 60% reduction in cross-cluster scheduling latency.

ORCID iDs

Huang, Congyue, Tan, Wei, Ou, Miaohua, Yang, Erfu ORCID logoORCID: https://orcid.org/0000-0003-1813-5950 and Li, Yun;
CORE (COnnecting REpositories)