Network-aware compute and memory allocation in optically composable data centers with deep reinforcement learning and graph neural networks.
Zacharaya ShabkaGeorgios ZervasPublished in: JOCN (2022)
Keyphrases
- data center
- neural network
- reinforcement learning
- cloud computing
- traffic engineering
- disaster recovery
- energy efficiency
- power consumption
- artificial neural networks
- energy aware
- wireless sensor networks
- network structure
- high density
- virtual machine
- learning algorithm
- complex networks
- network traffic
- data mining
- carbon dioxide
- commercial web search engines
- multi tenant
- internet services
- function approximators
- database
- soft computing
- computer networks
- cost effective
- fault diagnosis
- optimal policy
- peer to peer
- fuzzy logic
- data streams
- real time