RLDRM: Closed Loop Dynamic Cache Allocation with Deep Reinforcement Learning for Network Function Virtualization.
Bin LiYipeng WangRen WangCharlie TaiRavi R. IyerZhu ZhouAndrew HerdrichTong ZhangAmeer Haj-AliIon StoicaKrste AsanovicPublished in: NetSoft (2020)
Keyphrases
- closed loop
- reinforcement learning
- open loop
- control system
- fault detection and isolation
- control scheme
- feedback control
- parameter identification
- control law
- asymptotic stability
- network structure
- communication networks
- dynamic environments
- tracking error
- force control
- pid controller
- optimal control
- future internet
- function approximation
- flight test
- feedback controller
- fuzzy logic