Scheduling mix-flow in SD-DCN based on Deep Reinforcement Learning with Private Link.
Jinjie LuWaixi LiuYinghao ZhuSen LingZhitao ChenJiaqi ZengPublished in: MSN (2020)
Keyphrases
- reinforcement learning
- scheduling problem
- origin destination
- scheduling algorithm
- function approximation
- reinforcement learning algorithms
- privacy preserving
- resource constraints
- flow patterns
- state space
- markov decision processes
- real time database systems
- round robin
- learning process
- multi agent
- machine learning
- flow field
- learning algorithm
- flexible manufacturing systems
- temporal difference
- model free
- social networks
- resource allocation
- optimal policy
- optical flow
- action selection
- link structure
- deep learning
- dynamic programming
- np hard
- transition model