M-DRL: Deep Reinforcement Learning Based Coflow Traffic Scheduler with MLFQ Threshold Adaption.
Tianba ChenWei LiYuKang SunYunchun LiPublished in: NPC (2020)
Keyphrases
- reinforcement learning
- resource utilization
- function approximation
- network traffic
- real time
- multi agent
- state space
- optimal policy
- markov decision processes
- learning problems
- model free
- traffic flow
- adaptive threshold
- scheduling algorithm
- road network
- response time
- transition model
- machine learning
- threshold selection
- traffic engineering
- internet traffic
- learning algorithm
- electric vehicles
- intelligent transportation systems
- congestion control
- traffic control
- action space
- markov decision process
- optimal control
- resource manager
- packet scheduling