A multi-agent federated reinforcement learning-based optimization of quality of service in various LoRa network slices.
Eric OssongoMoez EsseghirLeïla Merghem-BoulahiaPublished in: Comput. Commun. (2024)
Keyphrases
- quality of service
- reinforcement learning
- multi agent
- network resources
- network conditions
- bandwidth allocation
- resource utilization
- qos parameters
- qos requirements
- multimedia services
- application level
- bandwidth requirements
- resource reservation
- end to end qos
- resource management
- asynchronous transfer mode
- congestion control
- traffic engineering
- differentiated services
- response time
- transmission rate
- agent technology
- ad hoc networks
- next generation networks
- web services
- multi agent systems
- service provisioning
- real time
- path selection
- qos routing
- admission control
- ip networks
- network management
- cooperative
- service differentiation
- end to end
- computer networks
- network traffic
- qos aware
- ip multimedia subsystem
- network structure
- bandwidth utilization
- end to end quality of service
- intelligent agents
- wireless networks
- call admission control
- mobility management
- end to end delay
- video on demand
- network bandwidth