A Kubernetes custom scheduler based on reinforcement learning for compute-intensive pods
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914265736151040 |
|---|---|
| author | Zhou, Hanlin Chan, Huah Yong Zhang, Shun Yao Lin, Meie Ni, Jingfei |
| author_facet | Zhou, Hanlin Chan, Huah Yong Zhang, Shun Yao Lin, Meie Ni, Jingfei |
| contents | With the rise of cloud computing and lightweight containers, Docker has emerged as a leading technology for rapid service deployment, with Kubernetes responsible for pod orchestration. However, for compute-intensive workloads-particularly web services executing containerized machine-learning training-the default Kubernetes scheduler does not always achieve optimal placement. To address this, we propose two custom, reinforcement-learning-based schedulers, SDQN and SDQN-n, both built on the Deep Q-Network (DQN) framework. In compute-intensive scenarios, these models outperform the default Kubernetes scheduler as well as Transformer-and LSTM-based alternatives, reducing average CPU utilization per cluster node by 10%, and by over 20% when using SDQN-n. Moreover, our results show that SDQN-n approach of consolidating pods onto fewer nodes further amplifies resource savings and helps advance greener, more energy-efficient data centers.Therefore, pod scheduling must employ different strategies tailored to each scenario in order to achieve better performance.Since the reinforcement-learning components of the SDQN and SDQN-n architectures proposed in this paper can be easily tuned by adjusting their parameters, they can accommodate the requirements of various future scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_13579 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Kubernetes custom scheduler based on reinforcement learning for compute-intensive pods Zhou, Hanlin Chan, Huah Yong Zhang, Shun Yao Lin, Meie Ni, Jingfei Distributed, Parallel, and Cluster Computing With the rise of cloud computing and lightweight containers, Docker has emerged as a leading technology for rapid service deployment, with Kubernetes responsible for pod orchestration. However, for compute-intensive workloads-particularly web services executing containerized machine-learning training-the default Kubernetes scheduler does not always achieve optimal placement. To address this, we propose two custom, reinforcement-learning-based schedulers, SDQN and SDQN-n, both built on the Deep Q-Network (DQN) framework. In compute-intensive scenarios, these models outperform the default Kubernetes scheduler as well as Transformer-and LSTM-based alternatives, reducing average CPU utilization per cluster node by 10%, and by over 20% when using SDQN-n. Moreover, our results show that SDQN-n approach of consolidating pods onto fewer nodes further amplifies resource savings and helps advance greener, more energy-efficient data centers.Therefore, pod scheduling must employ different strategies tailored to each scenario in order to achieve better performance.Since the reinforcement-learning components of the SDQN and SDQN-n architectures proposed in this paper can be easily tuned by adjusting their parameters, they can accommodate the requirements of various future scenarios. |
| title | A Kubernetes custom scheduler based on reinforcement learning for compute-intensive pods |
| topic | Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2601.13579 |