A SERVICE MIGRATION STRATEGY BASED ON MULTIPLE ATTRIBUTE DECISION IN MOBILE EDGE COMPUTING

 

Abstract

Machine migration increases costs while enhancing the user’s experience. How to balance costs and benefits is what we need to focus on. The core issue of the migration strategy is whether, when, and where to migrate. In this paper, we propose an edge computing migration strategy based on multiple attribute decision making to deal with the issue. Furthermore, we demonstrate the effectiveness of the migration strategy by simulation. Keywords-mobile edge computing; multiple attribute decision making; virtual machine migration; mobility With the shortcoming of long network delay and long response time, traditional mobile cloud computing can’t meet the need of delay sensitive business, such as Virtual Reality and Augmented Reality. Mobile edge computing has emerged and provided a way to solve the problems. During the movement of the user, if an optimal data center is detected, the virtual machine migrates from the current data center to the optimal one. It is important to note that virtual.

 

EXISTING SYSTEM:

In recent years, with the rapid development of mobile Internet, mobile data traffic is at an alarming rate of growth. According to the Cisco VNI  report, the total amount of mobile data will grow sevenfold between 2016 and 2021. It is clear that super data volume will increase the network load, especially the core network. In response to growing mobile traffic, mobile operators realized the advantage of decentralization of their core network and begun to design solution based on traffic offloading. As a result, mobile edge computing (MEC) came into being. Mobile edge cloud in MEC deploys calculation, storage, processing and other functions on the side of base station without uploading task to the cloud data center. It has a number of benefits, such as reducing bandwidth consumption, reducing latency by locating resources at nearby users and improving transmission efficiency. Due to the mobility of users, the data center that is providing service may not be the optimal one. In order to keep the quality of experience, virtual machine that containing context information needs to be migrated from one data center to another. In this paper, we design a migration strategy based on MADA (multi-attribute decision making) in MEC. In our approach, the virtual machine can be migrated a multiple servers according to the network status, user location, task attributes and server load. At the same time, we use MATLAB to simulate the network and user’s movement to the greatest extent. The simulation results show that our migration strategy is beneficial. The remainder of this paper is organized as follows: Section II introduces related researches. The migration strategy based on multiple attribute decision making is conducted in Section III Sections IV presents simulation experiments and results discussion. The paper concludes in Section V. .

PROPOSED SYSTEM: 

There are some research work focusing on MEC, such as concepts, scenarios, benefits, and challenges. Introduce the concept of mobile edge computing and the related market drivers, depicting the advanced blueprint of edge calculation. Some real-time computing scenarios and challenges for edge computing discussed in apply fog calculation to medical health monitoring, which helps to reduce latency and improve stability provides a framework of the edge calculation designed to migrate users’ ongoing business from the original data center to another combine fog, SDN and NFV three concepts, showing how to achieve MEC in mobile networks, and how to promote the development of Internet of Things. The author introduces the details of the virtual machine migration technology, providing a heuristic idea of migration to reduce power consumption and achieve load balancing in. The author presented architecture to validate and evaluate fog calculation and demonstrated the likelihood of user telemedicine equipment. In addition, several papers published in recent years describe computational offloading associated with MEC. describe a one-dimensional MDP with a specific cost function based on distance. Wang et al. proposed a new effective solution to speed up the calculation speed. These papers only consider the users location, didn’t consider the load of edge server, bandwidth and other context conditions.

CONCLUSION

In this paper, we propose a mobile edge computing migration strategy based on multiple attribute decision making. The strategy can solve the problem whether, when and where to migrate efficiently. Simulation results show that the mobile edge computing migration strategy can choose the appropriate server, significantly reduce the user’s response time and improve the quality of user’s experience. More simulation will be done in the future, and we will focus on optimizing the migration strategy that can be applied to real networks which are more complex.

REFERENCES: 

[1] Index C V N. Forecast and Methodology, “2015-2020 White Paper[R]. Technical Report,” Cisco, 2016.

[2] Y. C. Hu, M. Patel, D. Sabella, N. Sprecher, and V. Young, “Mobile Edge Computing A key technology towards 5G,” ETSI White Paper, 2015.

[3] A. Ahmed and E. Ahmed, “A survey on mobile edge computing,” ACM SIGCOMM Computer Communication Review, vol. 8, pp. 1- 18, 2016.

[4] Y. Cao, P. Hou, D. Brown, J. Wang, and S. Chen, “Distributed Analytics and Edge Intelligence:Pervasive Health Monitoring at the Era of Fog Computing,” The Workshop on Mobile Big Data ACM, pp. 43-48, 2015.

[5] T. Taleb and A. Ksentini., “Follow Me Cloud: Interworking Federated Clouds and Distributed Mobile Networks,” Communications Magazine IEEE, pp. 12-19, 2013. [6] O. Salman, I. Elhajj, A. Kayssi, and A. Chehab, “Edge computing enabling the Internet of Things,” Internet of Things IEEE, pp. 603-60.

[7] M. Mishra, A. Das, P. Kulkarni, and A. Sahoo, “Dynamic resource management using virtual machine migrations,” Communications Magazine IEEE, pp. 34-40, 2012.

[8] H. Dubey, J. Yang, N. Constant, A. M. Amiri, Q. Yang, and K. Makodiya, “Fog Data: Enhancing Telehealth Big Data Through Fog Computing,” the ASE BigData & SocialInformatics 2015, 2015.

[9] A. Ksentini, T. Taleb and M. Chen, “A Markov Decision Processbased service migration procedure for follow me cloud,” Communications (ICC), pp. 1350-1354, 2014.

[10] S. Wang, R. Urgaonkar, T. He, M. Zafer, and K. Chan, “Mobility- Induced Service Migration in Mobile Micro-clouds,” Military Communications Conference (MILCOM), pp. 835-840, 2014.