Service-oriented heterogeneous resource sharing for optimizing service latency in mobile cloud

Authors:
Takayuki Nishio;Ryoichi Shinkuma;Tatsuro Takahashi;Narayan B. Mandayam
Affiliations:
Kyoto University, Kyoto, Japan;Kyoto University, Kyoto, Japan;Kyoto University, Kyoto, Japan;Rutgers University, North Brunswick, NJ, USA
Venue:
Proceedings of the first international workshop on Mobile cloud computing & networking
Year:
2013

Citing 9
Cited 0

Design and Testing of a Generalized Reduced Gradient Code for Nonlinear Programming

ACM Transactions on Mathematical Software (TOMS)
SPEC CPU2000: Measuring CPU Performance in the New Millennium

Computer
Convex Optimization

Convex Optimization
Energy consumption in mobile phones: a measurement study and implications for network applications

Proceedings of the 9th ACM SIGCOMM conference on Internet measurement conference
Cloud Computing for Mobile Users: Can Offloading Computation Save Energy?

Computer
A Survey of Research on Mobile Cloud Computing

ICIS '11 Proceedings of the 2011 10th IEEE/ACIS International Conference on Computer and Information Science
Power consumption breakdown on a modern laptop

PACS'04 Proceedings of the 4th international conference on Power-Aware Computer Systems
Fog computing and its role in the internet of things

Proceedings of the first edition of the MCC workshop on Mobile cloud computing
Scalability of a mobile cloud management system

Proceedings of the first edition of the MCC workshop on Mobile cloud computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Fog computing is expected to be an enabler of mobile cloud computing, which extends the cloud computing paradigm to the edge of the network. In the mobile cloud, not only central data centers but also pervasive mobile devices share their heterogeneous resources (e. g. CPUs, bandwidth, content) and support services. The mobile cloud based on such resource sharing is expected to be a powerful platform for mobile cloud applications and services. In this paper, we propose an architecture and mathematical framework for heterogeneous resource sharing based on the key idea of service-oriented utility functions. Since heterogeneous resources are often measured/quantified in disparate scales/units (e.g. power, bandwidth, latency), we present a unified framework where all these quantities are equivalently mapped to "time" resources. We formulate optimization problems for maximizing (i) the sum of the utility functions, and (ii) the product of the utility functions, and solve them via convex optimization approaches. Our numerical results show that service-oriented heterogeneous resource sharing reduces service latencies effectively and achieves high energy efficiency, making it attractive for use in the mobile cloud.