Details
| Original language | English |
|---|---|
| Title of host publication | 2023 IEEE 31st International Conference on Network Protocols |
| Subtitle of host publication | ICNP |
| Publisher | IEEE Computer Society |
| Number of pages | 6 |
| ISBN (electronic) | 9798350303223 |
| ISBN (print) | 979-8-3503-0323-0 |
| Publication status | Published - 2023 |
| Event | 31st IEEE International Conference on Network Protocols, ICNP 2023 - Reykjavik, Iceland Duration: 10 Oct 2023 → 13 Oct 2023 |
Publication series
| Name | Proceedings - International Conference on Network Protocols, ICNP |
|---|---|
| ISSN (Print) | 1092-1648 |
Abstract
In this paper, we present RLKube, a Reinforcement Learning (RL)-based custom Kubernetes (K8s) scheduler plugin for optimized task scheduling. RLKube objectives are maximizing resource utilization and Pod throughput as well as improving energy efficiency in a K8s cluster. We used Double Deep Q-Network (DDQN) with Prioritized Experience Replay (PER) and utilized different reward functions to train the RL agent. Also, we have developed corresponding policies for each objective. We have evaluated the effectiveness of RLKube using various datasets simulating a diverse set of realistic load patterns. The results show that RLKube outperforms the default K8s scheduling policies in terms of throughput and energy usage, highlighting its potential for Improving task scheduling in K8s clusters.
Keywords
- Energy Consumption, Kubernetes, Optimization, Scheduling
ASJC Scopus subject areas
- Computer Science(all)
- Computer Networks and Communications
- Computer Science(all)
- Software
Sustainable Development Goals
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2023 IEEE 31st International Conference on Network Protocols: ICNP. IEEE Computer Society, 2023. (Proceedings - International Conference on Network Protocols, ICNP).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - An RL-Based Model for Optimized Kubernetes Scheduling
AU - Rothman, John
AU - Chamanara, Javad
PY - 2023
Y1 - 2023
N2 - In this paper, we present RLKube, a Reinforcement Learning (RL)-based custom Kubernetes (K8s) scheduler plugin for optimized task scheduling. RLKube objectives are maximizing resource utilization and Pod throughput as well as improving energy efficiency in a K8s cluster. We used Double Deep Q-Network (DDQN) with Prioritized Experience Replay (PER) and utilized different reward functions to train the RL agent. Also, we have developed corresponding policies for each objective. We have evaluated the effectiveness of RLKube using various datasets simulating a diverse set of realistic load patterns. The results show that RLKube outperforms the default K8s scheduling policies in terms of throughput and energy usage, highlighting its potential for Improving task scheduling in K8s clusters.
AB - In this paper, we present RLKube, a Reinforcement Learning (RL)-based custom Kubernetes (K8s) scheduler plugin for optimized task scheduling. RLKube objectives are maximizing resource utilization and Pod throughput as well as improving energy efficiency in a K8s cluster. We used Double Deep Q-Network (DDQN) with Prioritized Experience Replay (PER) and utilized different reward functions to train the RL agent. Also, we have developed corresponding policies for each objective. We have evaluated the effectiveness of RLKube using various datasets simulating a diverse set of realistic load patterns. The results show that RLKube outperforms the default K8s scheduling policies in terms of throughput and energy usage, highlighting its potential for Improving task scheduling in K8s clusters.
KW - Energy Consumption
KW - Kubernetes
KW - Optimization
KW - Scheduling
UR - http://www.scopus.com/inward/record.url?scp=85182517484&partnerID=8YFLogxK
U2 - 10.1109/ICNP59255.2023.10355623
DO - 10.1109/ICNP59255.2023.10355623
M3 - Conference contribution
AN - SCOPUS:85182517484
SN - 979-8-3503-0323-0
T3 - Proceedings - International Conference on Network Protocols, ICNP
BT - 2023 IEEE 31st International Conference on Network Protocols
PB - IEEE Computer Society
T2 - 31st IEEE International Conference on Network Protocols, ICNP 2023
Y2 - 10 October 2023 through 13 October 2023
ER -