English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Edge computing hosts applications close to the end users and enableslow-latency real-time applications. Modern applications inturn have adopted themicroservices architecture which composes applications as loosely coupledsmaller components, or services. This complements edge computing infrastructurethat are often resource constrained and may not handle monolithic applications.Instead, edge servers can independently deploy application service components,although at the cost of communication overheads. Consistently meetingapplication service level objectives while also optimizing applicationdeployment (placement and migration of services) cost and communicationoverheads in mobile edge cloud environment is non-trivial. In this paper wepropose and evaluate three dynamic placement strategies, two heuristic (greedyapproximation based on set cover, and integer programming based optimization)and one learning-based algorithm. Their goal is to satisfy the applicationconstraints, minimize infrastructure deployment cost, while ensuringavailability of services to all clients and User Equipment (UE) in the networkcoverage area. The algorithms can be extended to any network topology andmicroservice based edge computing applications. For the experiments, we use thedrone swarm navigation as a representative application for edge computing usecases. Since access to real-world physical testbed for such application isdifficult, we demonstrate the efficacy of our algorithms as a simulation. Wealso contrast these algorithms with respect to placement quality, utilizationof clusters, and level of determinism. Our evaluation not only shows that thelearning-based algorithm provides solutions of better quality; it also providesinteresting conclusions regarding when the (more traditional) heuristicalgorithms are actually better suited.

Heuristic and Reinforcement Learning Algorithms for Dynamic Service Placement on Mobile Edge Cloud