Wireless Networks for Mobile Edge Computing: Spatial Modeling and Latency Analysis

Next-generation wireless networks will provide users ubiquitous low-latency computing services using devices at the network edge, called mobile edge computing (MEC). The key operation of MEC is to offload computation intensive tasks from users. Since each edge device comprises an access point (AP) a...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on wireless communications 2018-08, Vol.17 (8), p.5225-5240
Main Authors: Ko, Seung-Woo, Han, Kaifeng, Huang, Kaibin
Format: Article
Language:English
Subjects:
Bandwidths
computation offloading
Computational modeling
Constraint modelling
Density
Edge computing
Electronic devices
Geometry
Mobile computing
Mobile edge computing
multiple access
Network latency
parallel computing
Parallel processing
Parameters
Provisioning
queueing
Queues
Queuing theory
Radio
radio access networks
Scaling laws
Servers
Stability
stochastic geometry
Stochastic processes
Task analysis
Wireless communication
Wireless networks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Next-generation wireless networks will provide users ubiquitous low-latency computing services using devices at the network edge, called mobile edge computing (MEC). The key operation of MEC is to offload computation intensive tasks from users. Since each edge device comprises an access point (AP) and a computer server (CS), an MEC network can be decomposed as a radio access network cascaded with a CS network. Based on the architecture, we investigate network-constrained latency performance, namely communication latency and computation latency, under the constraints of radio-access connectivity and CS stability. To this end, a spatial random network is modeled featuring random node distribution, parallel computing, non-orthogonal multiple access, and random computation-task generation. Given the model and the said network constraints, we derive the scaling laws of communication latency and computation latency with respect to network-load parameters (density of mobiles and their task-generation rates) and network-resource parameters (bandwidth, density of APs/CSs, and CS computation rate). Essentially, the analysis involves the interplay of the theories of stochastic geometry, queueing, and parallel computing. Combining the derived scaling laws quantifies the tradeoffs between the latencies, network connectivity, and network stability. The results provide useful guidelines for MEC-network provisioning and planning by avoiding either of the cascaded radio access network or CS network being a performance bottleneck.
ISSN:1536-1276
1558-2248
DOI:10.1109/TWC.2018.2840120