Elsevier

Computer Networks

Volume 122, 20 July 2017, Pages 138-152
Computer Networks

Multiple context based service scheduling for balancing cost and benefits of mobile users and cloud datacenter supplier in mobile cloud

https://doi.org/10.1016/j.comnet.2017.04.039Get rights and content

Abstract

This paper makes the use of cloud architecture as computational power for mobile device application. The multiple context based service scheduling scheme for balancing the cost and the benefits of mobile users and cloud datacenter supplier in mobile cloud is proposed, which can adapt to the system context without compromising mobile device user's QoS. The multiple context based mobile cloud service scheduling is formulated as a utility optimization problem, which is expressed as the summation of utilities of mobile cloud users. The proposed model aims to satisfy huge number of mobile requests, improve mobile user's QoS experiences and reduce system overheads. The proposed problem consists of cloud resources allocation optimization subproblem and mobile user QoS optimization subproblem. The multiple context based service scheduling algorithm is proposed to efficiently and adaptively schedule resource according to the context information. The proposed algorithm is validated through a series of experiments. The proposed algorithm can provide better QoS satisfaction for mobile device user, improve cloud resource utilization and reduce the cost.

Introduction

While the mobile device battery is more efficient than before, mobile applications are demanding more processing power and more computation capacity to all tasks in a reasonable time [1]. The cloud assisted approach is suitable for complex mobile applications because the cloud datacenter could help mobile device to complete the tasks on time. The mobile applications are processed on the cloud datacenter, while the mobile device is only for input and output. To deliver the results quickly, some mobile applications may need to be run on multiple servers concurrently. The mobile device performs simple computation, the cloud datacenter will perform the more complex computation associated with mobile applications. The powerful cloud provider can efficiently process intelligent applications for mobile devices.

For a mobile device with limited capability, gathering the contextual information, reasoning and processing contexts are time consuming. Also, the battery power required to process the information may be limited. With respect to mobile computing, the mobile cloud service provisioning scheme must deal with inherent mobility issues, such as device, network, dynamic environment and even user heterogeneity. Context information brings new opportunities for efficient and effective mobile cloud service scheduling for mobile devices [2]. Relevant to mobile device user's context information, the mobile cloud service scheduling system aims at providing the user with the most relevant services. The intelligent mobile application can change behavior based on the current context of the mobile device and cloud system. The mobile cloud contexts may include any information that can be used to describe the mobile device user, network, and cloud system environment. The mobile cloud context information (e.g. mobile user, wireless networks, cloud provider) can improve mobile application's QoS.

It is difficult to jointly ensure acceptable QoS for mobile device user and optimize cloud resource utilization in mobile cloud. In the paper, the characteristics of the mobile device, wireless network and cloud environment are adopted as the context parameters. The proposed multiple context based service scheduling model aims to efficiently apply available cloud resources to enhance mobile applications by effectively exploiting system context information. The proposed model takes into account the mobile user context information, the status of wireless network and cloud system.

The contributions of this paper are as follows.

  • (1)

    This paper makes the use of cloud architecture as computational power for mobile device application. The multiple context based service scheduling scheme for balancing the cost and the benefits of mobile users and cloud datacenter supplier in mobile cloud is proposed, which can adapt to the system context without compromising mobile device user's QoS.

  • (2)

    The multiple context based mobile cloud service scheduling is formulated as a utility optimization problem, which is expressed as the summation of utilities of mobile cloud users. The proposed model aims to satisfy huge number of mobile requests, improve mobile user's QoS experiences and reduce system overheads. The proposed problem consists of cloud resources allocation optimization subproblem and mobile user QoS optimization subproblem.

  • (3)

    The multiple context based service scheduling algorithm is proposed to efficiently and adaptively schedule resource according to the context information. The proposed algorithm is validated through a series of experiments. The proposed algorithm can provide better QoS satisfaction for mobile device user, improve cloud resource utilization and reduce the cost.

The organization of the rest of the paper is as follows. Section 2 presents the related works. Section 3 describes multiple context based service scheduling for balancing costs and benefits of mobile users and cloud datacenter supplier in mobile cloud. Section 4 presents multiple context based service scheduling algorithm in mobile cloud. Section 5 presents system design of multiple context based service scheduling. The experiments results are presented in Section 6. Section 7 concludes the paper.

Section snippets

Related works

To extend the mobile devices' capabilities for supporting compute-intensive applications, mobile cloud computing was introduced to leverage cloud resources, allowing mobile devices to utilize powerful cloud datacenter servers to process compute-intensive tasks. Michael J. OSullivan et al. [3] presented the Context Aware Mobile Cloud Services (CAMCS) middleware that can improve mobile cloud user experience. That is achieved by the Cloud Personal Assistant (CPA), which completes user assigned

Multiple context based service scheduling for balancing costs and benefits of mobile users and cloud datacenter supplier in mobile cloud

In this section, the multiple context based service scheduling and provisioning for balancing the costs and the benefits of mobile users and cloud datacenter supplier in mobile cloud is proposed. The proposed model aims to efficiently apply available cloud resources to enhance mobile applications by effectively exploiting system context information. Firstly, the model description is given. Secondly, mathematical formulation and solution are presented. Thirdly, data privacy and security control

Multiple context based service scheduling algorithm in mobile cloud

The multiple context based service scheduling algorithm (CMSSA) includes two parts: mobile device optimization sub-algorithm and cloud provider optimization sub-algorithm, which is executed by the cloud supplier and the mobile device. The pseudocode of multiple contexts based service scheduling algorithm in mobile cloud (CMSSA) is described below.

Algorithm Multiple Contexts based Service Scheduling Algorithm in Mobile Cloud (CMSSA)

Sub-Algorithm 1 (zjcpu, zjram, zjstorage, zmbandwidth)
Input: zjc

System components in multiple context based mobile service scheduling model

The multiple context based service scheduling and provisioning model in mobile cloud is presented in Fig. 4, which consists of mobile user, cloud proxy, cloud monitor, cloud scheduler and the context manager. The cloud proxy is the center of the mobile cloud system, which receives the requests from mobile users and allocates them to the scheduler. A cloud proxy handles all incoming requests from mobile users and ensures that each request has enough time to be processed before it times out.

Experiments and analysis

In this section, the proposed multiple contexts based mobile cloud service scheduling and provisioning algorithm is validated by a series of experiments.

Conclusions

This paper makes the use of cloud architecture as computational power for mobile device application. The multiple context based service scheduling scheme for balancing the cost and the benefits of mobile users and cloud datacenter supplier in mobile cloud is proposed, which can adapt to the system context without compromising mobile device user's QoS. The multiple context based mobile cloud service scheduling is formulated as a utility optimization problem, which is expressed as the summation

Acknowledgements

The authors thank the editors and the anonymous reviewers for their helpful comments and suggestions. The work was supported by the National Natural Science Foundation (NSF) under grants (No.61672397, No.61472294, No.61601336), Program for the High-end Talents of Hubei Province. Any opinions, findings, and conclusions are those of the authors and do not necessarily reflect the views of the above agencies.

Chunlin Li is a Professor of School of Computer Science and Technology in Wuhan University of Technology. She received the ME in Computer Science from Wuhan University of Technology in 2000, and PhD in Computer Software and Theory from Huazhong University of Science and Technology in 2003. Her research interests include cloud computing and distributed computing.

References (39)

  • P.M. Ragini et al.

    An efficient model for privacy and security in mobile cloud computing

  • G. Zhuo et al.

    Privacy-preserving verifiable data aggregation and analysis for cloud-assisted mobile crowdsourcing

  • M. Shojafar et al.

    Adaptive energy-efficient QoS-aware scheduling algorithm for TCP/IP mobile cloud

  • I. Bisio et al.

    Context‐awareness over transient cloud in D2D networks: energy performance analysis and evaluation

    Trans. Emerging Telecommun. Technol.

    (2015)
  • N.Z. Naqvi et al.

    To cloud or not to cloud: a context-aware deployment perspective of augmented reality mobile applications

  • K. Gai et al.

    Energy-aware optimal task assignment for mobile heterogeneous embedded systems in cloud computing

  • W. Hummer et al.

    Context-aware personalization for smart mobile cloud services

  • A. Benali et al.

    Cloud environment assignment: a context-aware and dynamic software product lines-based approach

  • S.N.Z. Naqvi et al.

    Dynamic deployment and reconfiguration of intelligent applications in mobile cloud computing with context-driven probabilistic models

  • Cited by (10)

    View all citing articles on Scopus

    Chunlin Li is a Professor of School of Computer Science and Technology in Wuhan University of Technology. She received the ME in Computer Science from Wuhan University of Technology in 2000, and PhD in Computer Software and Theory from Huazhong University of Science and Technology in 2003. Her research interests include cloud computing and distributed computing.

    Xin Yan is a vice Professor of Management at Wuhan University of Technology. He received his M.S. in Mechanical Engineering from Hubei University of Technology in 1997 and his Ph.D. in Computer Science and Technology from Wuhan University of Technology in 2006. His research interests include computer network and communication.

    Yang Zhang is currently an Assistant Professor in the School of Computer Science and Technology, Wuhan University of Technology. He received the Ph.D. degree from the School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore, in 2015. He obtained his B.Eng. and M.Eng. degrees from Beihang University (BUAA), Beijing, China, in 2008 and 2011, respectively.

    Youlong Luo is a vice Professor of Management at Wuhan University of Technology. He received his M.S. in Telecommunication and System from Wuhan University of Technology in 2003 and his Ph.D. in Finance from Wuhan University of Technology in 2012. His research interests include cloud computing and electronic commerce.

    View full text