4.7 Article

Edge Cloud Selection: The Essential Step for Network Service Marketplaces

Journal

IEEE COMMUNICATIONS MAGAZINE
Volume 59, Issue 10, Pages 28-33

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/MCOM.211.2001056

Keywords

-

Funding

  1. MESON (Optimized Edge Slice Orchestration) project
  2. European Union
  3. Operational Program Competitiveness, Entrepreneurship and Innovation [T1EDK-02947]

Ask authors/readers for more resources

This article presents a distributed service discovery framework for network service marketplaces in edge computing, which allows the discovery of NSs among edge clouds through a cache-based protocol and uses a multi-criteria ranking mechanism to identify the most suitable edge cloud.
The evolution of 5G network service ecosystems raises the need for the discovery of services among multiple (edge) clouds with potentially heterogeneous resources and features. Besides 5G service deployment, such a service discovery architecture could provide the means for cross-service communication (CSC), that is, the consumption of a network service (NS) by another NS, empowering the service capabilities of the latter. This article presents a distributed service discovery framework for network service marketplaces (NSMs) in edge computing. We exemplify the operation of a new distributed service discovery mechanism that relies on a cache-based protocol for the discovery of NSs among edge clouds. We also present a multi-criteria ranking mechanism, which identifies the most suitable edge cloud according to the client's functional, performance, and cost requirements. Our evaluation results indicate that the proposed service discovery mechanism (SDM) yields service discovery effectiveness on par with other approaches, while drastically reducing the communication overhead.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available