지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
이용수5
1. Introduction 12. Background 52.1. Kubernetes Pod Autoscaling 52.2. Reinforcement Learning 63. Related Works 83.1. HPA Modeling for Simulation 83.2. Autoscaling Methods 83.3. Reinforcement Learning-based Autoscaling 104. Discrete-time Queueing Model for HPA 144.1. Profiling the Performance of Application 144.2. System Environment Modeling 174.3. Kubernetes HPA Policy Modeling for Baseline 224.4. Model Validation 245. Reinforcement Learning-based HPA 265.1. Scenario 265.2. Reinforcement Learning Design 275.2.1. State 275.2.2. Reward 275.2.3. Action 285.2.4. Policy Update 295.3. Transfer Learning Technique 305.3.1. Offline-Learning Mode : Pre-training 325.3.2. Online-Learning Mode : Transfer Learning 326. Experiments 356.1. Policy Comparison using Simulation 356.1.1. Kubernetes HPA Comparison Simulation 376.1.2. RL-based HPA Comparison Simulation 396.1.3. 3-action, 5-action Comparison Simulation 406.2. Evaluation of Transfer Learning 427. Conclusion 48References 50
0