GPU-based embedded edge server configuration and offloading for a neural network service.
Joohwan KimShan UllahDeok-Hwan KimPublished in: J. Supercomput. (2021)
Keyphrases
- neural network
- single server
- client server architecture
- service times
- queuing model
- service composition
- client server
- poisson arrivals
- web services
- call center
- neural network model
- database
- queueing model
- embedded systems
- service providers
- artificial neural networks
- edge information
- steady state
- internet services
- service quality
- service discovery
- back propagation
- application level
- special case
- collision detection
- times faster
- fuzzy logic
- web server
- graphics hardware
- service requests
- arrival process
- management system
- service oriented
- wireless networks
- heavy traffic
- wireless internet
- edge detection
- network bandwidth
- queueing networks
- queue length
- parallel implementation
- edge detector
- network architecture
- recurrent neural networks