Abstract

Recent years have seen considerable interest in mobile cloud computing and edge cloud computing. This paper presents a mobile Intercloud system for supporting mobile cloud computing in general and edge cloud computing in particular. In essence, a mobile user with a mobile terminal can set up a virtual mobile terminal with applications and data in a central/home cloud. The virtual mobile terminal can facilitate task and computation offloading and other functions. Moreover, when a mobile terminal joins an edge cloud, the virtual mobile terminal (including required applications and data) can be migrated to enhance system efficiency and the user experience (e.g., shorter access delays). An experimental prototype has been developed for evaluating certain basic object transfer functions. To support the application transfer function, we formulate both finite- and infinite-horizon Markov decision models to determine decision policies (i.e., should an application be transferred to an edge cloud). The transfer decision depends on various factors, including transfer cost, duration associated with the edge cloud, usage probability, and usage cost in the central cloud and edge cloud. Based on the models, we obtain closed-form solutions for the decision policies, which can be expressed in meaningful formulas to provide useful insights for edge cloud computing in general. To evaluate the mobile Intercloud system for edge cloud computing, we conducted extensive evaluations, including experimental evaluation for testing the basic functions and protocols, analytical evaluation for studying the analytical models, and simulation evaluation for analyzing performance in a multiuser and multicloud environment in particular. The experimental, simulation, and analytical results provide useful insights into the design and development of the mobile Intercloud system for edge cloud computing as well as decision policies for application transfer.

Highlights

  • Cloud computing enables computing resources such as storage and services to be shared dynamically and flexibly over the Internet [1, 2]

  • We present the simulation results to evaluate the performance of the finite-horizon Markov decision process (FHMDP) and infinite-horizon Markov decision process (IHMDP)

  • In addition to task or computation offloading, virtual mobile terminals as well as data/files and applications can be transferred among clouds to better support physical mobile terminals

Read more

Summary

Introduction

Cloud computing enables computing resources such as storage and services to be shared dynamically and flexibly over the Internet [1, 2]. (i) We present a mobile Intercloud system and the associated protocols for supporting edge cloud computing It facilitates the transfer of data and applications between heterogeneous clouds so that mobile users can use the resources more effectively and efficiently (ii) We formulate a Markov decision-based model/problem to analyze an application migration problem for edge cloud computing (i.e., should an application be migrated to an edge cloud taking into consideration various factors). Both finite-horizon and infinite-horizon models are investigated.

Related Work
System and Protocol
Migrate through intercloud gateway if required
Decision Models for Application Transfer
Upload application
Performance Analysis
Result
Edge cloud 1
Simulation Evaluation
Findings
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call