Towards an Optimized Distributed Message Queue System for AIoT Edge Computing: A Reinforcement Learning Approach.
Zaipeng XieCheng JiLifeng XuMingyao XiaHongli CaoPublished in: Sensors (2023)
Keyphrases
- reinforcement learning
- multi agent
- distributed systems
- distributed environment
- cooperative
- function approximation
- edge information
- markov decision processes
- queue length
- lightweight
- markov chain
- edge detection
- special case
- optimal policy
- machine learning
- computer networks
- fault tolerant
- state space
- distributed data
- action selection
- temporal difference
- reinforcement learning algorithms
- queueing theory
- hazard rate