4.12 Multi-Cloud Offloading in Mobile Cloud Computing Environment
4.12.1 Performance Analysis of Multi-Cloud Offloading Schemes
The non-cooperative transmission when the amount of data (d) is small can still be bet- ter energy efficient than multiple input, single output. However, when d is larger, energy consumption is high, as shown in Figure 4.16. The graph underneath shows that when the amount of data sent to the server is small, the energy requirement is less. It indicates that the system is more energy efficient. But as the amount of data is increased, the energy requirement is also increased simultaneously.
Server 1 A2 offloaded offloadedA3 Result of A3 received Result of A1 received A1 A2 A3 Server Mobile device Server 2 Server k Server (k+1) Server n
A1 offloaded Result of A2 received
FIGURE 4.15
Self-reliant multi-cloud offloading systems.
0 0.0 0.2 0.4 0.6 0.8 1.0 1.2 1.4 1.6 1.8 2.0 20 40 60 80 100 Amount of data To tal ener gy FIGURE 4.16
4.13 Conclusion
Offloading involves power consumption in executing an application and during com- munication with the remote cloud. To better utilize the resource on the cloud, there is a trade-off between transmission energy cost and local execution energy cost. Though many works have made an effort to find the balance point, only a subset of those studies focuses on energy efficiency, while in many cases they merely focus on response time and other resource consumption. A large part of the researches uses modeling and simulation. Some of the models only offload parts of the program to the server, which reduces transmission cost, while at the same time bringing extra partition overhead. Other works have focused on transplanting the entire OS or application runtime to the cloud as this ease the burden on external application programmers.
Questions
1. What does offloading mean? Why is offloading necessary?
2. Show how offloading is beneficial for a large amount of computing. 3. What are the types of offloading? Discuss.
4. What is MACS? Show how it complements the necessity of offloading.
5. List the different methods of cloud path selection. Discuss the issues related to it, if any. 6. What is a MoSoNet? Discuss the algorithms for target selection in a MoSoNet. 7. Discuss the trade-offs in offloading.
8. Discuss the topologies in offloading.
9. What are full and partial offloading? Which one is considered better and why?
10. Explain with different examples when full offloading and partial offloading is to be done. Also provide a case in which offloading will not be beneficial.
References
1. X. Ma, Y. Cui, L. Wang, and I. Stojmenovic, Energy optimizations for mobile terminals via computation offloading, in Second IEEE International Conference on Parallel Distributed and Grid
Computing, Solan, India, pp. 236–241, 2012.
2. K. Kumar, J. Liu, Y. H. Lu, and B. Bhargava, A survey of computation offloading for mobile systems, Mobile Networks and Applications, 18(1), 129–140, 2013.
3. Y. Ge, Y. Zhang, Q. Qiu, and H. Y. Lu, A game theoretic resource allocation for over all energy minimization in mobile cloud computing system, in ACM/IEEE International Symposium on
Low Power Electronics and Design, Redondo Beach, CA, pp. 279–284, July, 2012.
4. L. Jiao, R. Friedman, X. Fu, S. Secci, Z. Smoreda, and H. Tschofenig, Cloud-based computation offloading for mobile devices: State of the art, challenges and opportunities, in IEEE Future
5. K. Kumar and H. Y. Lu, Cloud computing for mobile users: Can offloading computation save energy? Computer, 43(4), 51–56, 2010.
6. H. Wu, Q. Wang, and K. Wolter, Tradeoff between performance improvement and energy sav- ing in mobile cloud offloading systems, in IEEE International Conference on Communications
Workshops, Budapest, Hungary, pp. 728–732, 2013.
7. H. Pan, Cellular and wireless offloading, in Making the Most of Mobile, Telekom Innovation Laboratories, Cambridge, United Kingdom, September 24, 2012.
8. B. Gao, L. He, L. Liu, K. Li, and S. A. Jarvis, From mobiles to clouds: Developing energy-aware offloading strategies for workflows, in 13th International Conference on Grid Computing, Beijing, China, pp. 139–146, September 2012.
9. D. Kovachev, T. Yu, and R. Klamma, Adaptive computation offloading from mobile devices into the cloud, in Tenth International Symposium on Parallel and Distributed Processing with
Applications, Leganes, Spain, pp. 784–791, 2012.
10. H. Wu, Q. Wang, and K. Wolter, Methods of cloud-path selection for offloading in mobile cloud computing systems, in CloudCom, Taipei, Taiwan, pp. 434–448, 2012.
11. B. Han, P. Hui, A. V. Kumar, V. M. Marathe, J. Shao, and A. Srinivasan, Mobile data offloading through opportunistic communications and social participation, IEEE Transactions on Mobile
Computing, 11(5), 821–834, 2012.
12. S. X. Wang, H. Shen, and D. Wetherall, Accelerating the mobile web with selective offloading, in Proceedings of the Second ACM SIGCOMM Workshop on Mobile Cloud Computing, Hong Kong, China, pp. 45–50, August 2013.
13. E. Lagerspetz and S. Tarkoma, Mobile search and the cloud: The benefits of offloading, in IEEE
International Conference on Pervasive Computing and Communications Workshops, Seattle, WA, pp. 117–122, 2011.
14. H. Qi and A. Gani, Research on mobile cloud computing: Review, trend and perspectives, in Second International Conference on Digital Information and Communication Technology and Its
103
5
Green Mobile Cloud Computing
Cloud
Green mobile cloud computing
1. Small cell mobile network +
Cloud computing 2. Computation inside the cloud 4. Longer battery of mobile device 3. Reduction of energy consumption
of mobile device and cloud Mobile network
Data communication
ABSTRACT Green mobile cloud computing is an emerging research area today. Green mobile network means an energy-efficient mobile network that consumes low power. Small cell network provides a green mobile network. By offloading computation inside the cloud, the power consumption by a mobile device can be reduced. But this can cause more power consumption and expense inside the cloud. Thus, there should be a tradeoff between an energy-efficient mobile network and a green cloud environment. In this chap- ter, we discuss several existing approaches for green mobile networks and green cloud computing. Based on comparative studies, we discuss how green mobile cloud computing can be achieved by merging green cellular networks with the cloud environment.
KEY WORDS: macrocell, femtocell, cloud, power, energy.
5.1 Introduction
Energy efficiency is gaining importance for future mobile networks day by day. The increased usage of mobile devices, together with rising energy costs and the need to lessen greenhouse gas emissions, calls for energy-efficient technologies that reduce the overall energy utilization of computation, storage, and communications [1]. A fraction of energy savings in mobile networks could lead to significant financial savings and would protect the environment with the reduced production of the harmful greenhouse gases [1].
Cloud computing (CC) has been widely accepted as the coming generation’s com- puting framework [1]. CC allows its users to make use of the platforms, software, and infrastructures provided by the cloud providers at low cost. With the enormous growth of the usage of mobile applications and the gaining popularity of cloud computing, CC is integrated to the mobile environment, leading to the development of mobile cloud computing (MCC) [2].
MCC has received substantial attention as it is a promising technology that allows the processing and storage of data outside the mobile devices, that is, in the cloud, thus result- ing in considerable energy saving for the devices. It provides virtually endless resources that are obtainable as per the requirement and charged accordingly. This provides eco- nomic advantages both for the cloud providers and the users. MCC is characterized by lower operating cost, high scalability, and better accessibility [3]. The notions of user mobility and wireless access pattern give rise to certain challenges, such as mobility man- agement, quality of service (QoS), energy management, and security and privacy issues, to MCC [2]. The most critical among them is the energy efficiency of mobile devices, which is discussed in this chapter. We also review the literature on the same.