Process Batch Offloading Method for Mobile-Cloud Computing Platform

Process Batch Offloading Method for Mobile-Cloud Computing Platform

Pawan Kumar Thakur (Department of Information Technology, Panjab University, Chandigarh, India) and Amandeep Verma (Department of Information Technology, Panjab University, Chandigarh, India)
Copyright: © 2015 |Pages: 13
DOI: 10.4018/JCIT.2015070101


Mobile cloud applications transfers the computational power and data storage outside the mobile device and into the mobile cloud, getting mobile computing and mobile applications to not handheld devices users but a wider choice of mobile subscribers. Process offloading is the technique in which some part of the application is transferred into the mobile cloud for execution. Many applications like GPS, face recognition, video editing etc. consumes more battery of the mobile devices. By offloading the power hunger part to the cloud is one of the approach to elongate the battery lifetime of mobile devices. The major goal of the proposed model is to combine the similar processes into single batch and offload the batch into cloud rather than offloading a single process into cloud. A MPCEPGM (Multilevel Process Cost Evaluation with Process Group Merging) algorithm is proposed for application partitioning and offloading to the cloud. MPCEPGM will predict the overall execution cost of the whole batch or process tree as single entity. This will help the mobile offloading procedure to organize the processes according to their delivery time. Proposed model is energy efficient to deliver the data effectively to the mobile cloud. The performance of the proposed system is assessed on the basis of total execution time and communication cost using Matlab simulations.
Article Preview

1. Introduction

Cloud computing deals with the distribution of computing resources over the internet. Cloud computing offers a bulk of resources like networks, computer processing power, data storage space, specialized corporate as well as the user application. Cloud computing is a technique which provide convenient and on demand network access (Satyanarayanan, 2010). It also provide bulk of computing resources in addition to minimum management services used for interaction.

Cloud Computing (CC) supports suitable, network access on-demand to a collective pool of configurable computing resources (such as services, applications, servers, storage and networks) that can be easily used with minimal effort or interaction required by the management and service providers. Mainly Three basic fundamental structure of cloud computing namely cloud service Platform as a Service (PaaS), Infrastructure as a Service (IaaS) and Software as a Service (SaaS) (

Figure 1 illustrates the four tiers of the cloud architecture. In the layered architecture, top tier is the cloud applications (User Layer) that provides all the cloud applications to the end users. These applications are provided by the bottom SaaS layer on pay-per-use basis. The next tier is the cloud programming (SaaS layer) that includes the software frameworks and creates user interfaces that are cost-effective. The next tier is the cloud middleware (PaaS Layer) that implements all the platform services. It provides run-time environments for executing user applications. The bottom tier is the cloud resources (IaaS Layer) that provide the physical resources to power the data-centers.

Figure 1.

Cloud computing stack [2]


Mobile cloud computing is defined as a combination of Mobile internet, mobile computing and cloud computing technologies. Mobile Computing Technology (MCT) (Hunt and Scott et al., 1998) can be used to transfer data and to share resources of computer and cellphones. It gives an accurate and real time information to a client at any time, at any place. Mobile Internet Technology (MIT) is the mixture of internet and mobile communication. It plays an important role to provide network services and real time network resources to a client. Mobile Cloud Computing (MCC) includes mobile computing, cloud computing, virtualizations and networking. MCC gives us challenges and new possibilities in energy saving by supply of computing resources, mobile resources and network resources to increase resource utilization, virtualization and sharing so that reduction in cost can be achieved.

Data offloading is a technique used to offload the data from the network to the cloud. This helps in reducing the traffic on the communication channels in the network. The data being sent onto the network from the smart mobile device is offloaded to the cloud. It enhances the performance of the smart mobile devices. Data offloading allows the mobile users to execute smart mobile applications that require strong processors, long battery lifetime and memory by offloading the data for storage and data for processing on the cloud. Resource intensive data from the mobile application is offloaded to the cloud; it uses the cloud resources. Thus the mobile resources are not exhausted.

Two techniques of computation offloading (i.e. Mobile Code Offloading). These techniques are Coarse Grained offloading and Fine grained offloading (Kovachev et al., 2012). Coarse Grained offloading: in this approach full application or program is offloaded into the cloud for execution rather than offloading some of the partitioned code. This approach declines the load of a constraint of this approach is that the full application migration may result in additional communication overhead. Fine grained offloading: in this approach programmers modify the code so that it can handle partitioning and state migration. In this approach, only the power hungry part of the application is offloaded into the cloud. By doing this large amount of energy can be saved. Decoder acts as demanding part. Hence we can offload only the CPU demanding part and there is no need to offload monitor intensive part.

Complete Article List

Search this Journal:
Open Access Articles
Volume 22: 4 Issues (2020): 2 Released, 2 Forthcoming
Volume 21: 4 Issues (2019)
Volume 20: 4 Issues (2018)
Volume 19: 4 Issues (2017)
Volume 18: 4 Issues (2016)
Volume 17: 4 Issues (2015)
Volume 16: 4 Issues (2014)
Volume 15: 4 Issues (2013)
Volume 14: 4 Issues (2012)
Volume 13: 4 Issues (2011)
Volume 12: 4 Issues (2010)
Volume 11: 4 Issues (2009)
Volume 10: 4 Issues (2008)
Volume 9: 4 Issues (2007)
Volume 8: 4 Issues (2006)
Volume 7: 4 Issues (2005)
Volume 6: 1 Issue (2004)
Volume 5: 1 Issue (2003)
Volume 4: 1 Issue (2002)
Volume 3: 1 Issue (2001)
Volume 2: 1 Issue (2000)
Volume 1: 1 Issue (1999)
View Complete Journal Contents Listing