Abstract
A model that allows the clients or users to access a collection of resources used for computing such as storage, services provided by peer devices, server and applications which is available to all the mobile users as it presents at the edge of the wireless network is called as mobile edge cloud system. It provides wireless network information and local context awareness along with low latency and bandwidth conservation, so it is much better than traditional central cloud. This paper represents the characteristics, application, model services, architecture and open challenges of mobile edge cloud system; the application is also classified into different criteria. It also gives an idea of MEC for future research direction.
Access provided by Autonomous University of Puebla. Download conference paper PDF
Similar content being viewed by others
Keywords
70.1 Introduction
The knowledge of combining both information technologies and communication helps in creating a network structure that helps to improve the user requirements and develop a large number of options for selecting new internet application. So, one among them is cloud computing. But the model of cloud computing which is based on centralized data centers comes with a number of limitations like:
-
For real-time applications, it is very much difficult and also costly to move all the data from different edge nodes to the center cloud.
-
It difficult to take care of the latency requirements of time-critical application.
-
It difficult to adapt in traffic changes for applications that works on local network and user content using far away data centers.
These limitations as lead to the development of an integrated model called mobile edge cloud system also known as edge cloud. These limitations are often addressed employing a new integrated model called mobile edge clouds (MEC) also called edge cloud. The system consists of base stations, access points, routers, switches and a collection of computation and storage resources which is used by the clients or users in mobile devices for performing a task [1,2,3,4]. Fog computing [5] provides a virtualized platform concept which is placed at the sting of wireless network that provides resources for computing, storage and networking services between the datacenter and different edge nodes. Mobile edge computing [6,7,8,9] is analogous to cloud computing that provides IT and cloud-computing services that is in the range of the radio access network which can be referred as RAN at a close range of mobile users. The mobile edge computing server can be placed at the base stations, radio network controller or at sites with different types of MultiTechology Aps. [10,11,12] proposed various segmentation techniques.
70.2 Characteristics and Applications of MEC
MEC has the subsequent characteristics [5, 6] (Fig. 70.1).
-
(1)
Status awareness for local network: To access channel information and real-time network, MEC is established at the string.
-
(2)
Context awareness for local user: The user location and contents are locally available to the application.
-
(3)
Distributed: The MEC resources, service and application are distributed in nature placed at different locations, and the wireless access networks are arranged in a hierarchy order which are base stations, access points, switches, gateways and also end-point devices.
-
(4)
Multiformity: The MEC nodes are heterogeneous in nature with different processing and storage capabilities with changing network bandwidth and connectivity.
-
(5)
Mobility and undependable access: MEC services needs to be hosted in the mobile devices itself because the services might be accessed through unexpended wireless network or the point of connection to the network might change so mobility support is must.
-
(6)
Ultra-low latency: To support tangible Internet applications which are robotics, virtual, AR and real-time application MEC must be able to perform in low-latency so that the application can overcome delay and end-end latency.
-
(7)
Interaction with mesial cloud: MECs provide local processing of data along with low latency and content awareness, but there are clouds which provides global centralization which as advanced storage and processing capabilities, and it also provide support to the traditional central cloud.
Along with the properties, the applications of MEC are as follows (Fig. 70.2).
-
(1)
Real time application like live gaming can reduce the experience of delay if the process is executed at the sting so that the data does not need to move between the end devices and other data centers.
-
(2)
The application needs to adjust with the local network because there will be situation where the network degenerate or load in the traffic increases. One of the solutions is reducing the video data rate which is suitable for the required bandwidth.
-
(3)
The application which are local in nature process and compute the information on smaller dataset locally and maintains location privacy of the user by not sharing with any kinds of network. The application involves insertion, sharing, crowd sensing of local data or content.
-
(4)
Huge amount of data like large data analysis, surveillance monitoring is processed and aggregated at the sting in order to reduce the bandwidth and cloud storage of the mesial cloud.
MEC can provide three levels of services to its customers:
-
Infrastructure as a service (IaaS)
-
Software as a service (SaaS)
-
Platform as a service (PaaS).
The characteristics difference between traditional cloud and MEC is listed in Table 70.1.
For MEC SaaS, mobile users do not need to think about the problems that involves system configuration like application that is within the data center, take on cloud computing. MEC application services can be of any kind of service such as requested or transparent service and these are provided by the service providers, when the data from the client passes through mobile network, i.e., content optimization of radio-aware shown in Fig. 70.3.
Several use cases of MEC platform services are:
(1) To serve applications to mobile end-users, third-party service provider charter a share of the platform. (2) Similar to crowd sensing, MECs allow the mobile end user to release their own application in the platform. (3) In normal cloud architecture, wireless access network contains different levels which contains resources without any planned connection, but in MEC infrastructure, the user can send the code for execution in the platform service automatically.
70.3 Architecture of MEC
Fig. 70.2 illustrates the components like access point (AP), base station (BS), switches, router and aggregation for cell which makes up the MEC server [6] which provides the client to access network data and radio data, resources for computing and storage.
70.3.1 Server
Fig. 70.4 shows the architecture and interfaces of MEC server. The server consists of two parts: one is hosting infrastructure and other is virtualized application platform (VAP). The VAP provides a virtualization manger which provides a sharing environment that is used for deploying and running application that ranges from network operator to third party application and also services to host the different applications such as platforms.
Middleware services like communication, registry and traffic offload function (TOF) are provided by the application platform to the application. The registry stores information about the services that is present in the server that helps to get services to the application at different end points. One more middleware service is radio network information service (RNIS) which provides application to know about its services and also to tell other applications.
The TOF contains policy that routes the client’s data between different applications and also set priority to the traffic.
70.3.2 Specification of Server
The wireless access network is arranged in a hierarchical level and are placed at different locations and each server host different type of application.
Services such as Web services, TCP/IP protocol and other services which contains structure of traditional IP network can be provided by the MEC server [9, 13]. Three of the programming frameworks, i.e., cloudlet, MAUI, and clone cloud and comparison between them is shown in Table 70.2.
70.4 Research Challenges of MEC
The major challenges faced in MEC are (Table 70.3).
70.4.1 Proper Platform with APIs
Network algorithm and control protocol are importantly needed to build a good MEC system, or else it leads to problems in planning. The main problems include: (1) to route quickly and efficiently the traffic to the simplest service case within the network. (2) An adaptive allocation for moving users for allocating function and the required data which will handle user mobility and the required services. (3) To maintain session state while migrating a service from one virtual network to another virtual network without causing any interruption in service.
70.4.2 Management of Resource and Computation Balance
Networks usually contains highly dynamic and complete resources of varies dimension which are placed at geo-spatial points and follows multiple levels of hierarchal network. Further, in unreliable wireless network the changing of mobile device points brings problems in allocation of resources and scheduling algorithm. So, strategies need to be developed to overcome this problem. So, for that, new mechanisms are required to virtualize the complex network and provide resources which are required to the distributed environment.
70.4.3 Interaction with Mobile Devices and Traditional Cloud
The execution of application requires the task to jump from one end mobile node to another, i.e., MEC network nodes and distant central clouds. And it may also involve several stages of computation especially in pipelined fashion where data flow from one stage to another. So, it is important that innovative runtime management schemes needs to be developed for effectively executing the distributed jobs and tasks which as real-time constraints.
70.5 Conclusion
The paper describes about the different MEC systems, their architecture, challenges and models. At first, the paper briefs the characteristics and also explored the applications of MEC based on criteria. Service models are also discussed. Different types of architecture are explained and also the challenges faced by them. As future work, problems faced by MEC in security can be explored and studied.
References
Drolia, U., et al.: The case for mobile edge-clouds. In: 2013 IEEE 10th International Conference on Ubiquitous Intelligence and Computing and 2013 IEEE 10th International Conference on Autonomic and Trusted Computing, Vietri sul Mere, pp. 209–215 (2013). https://doi.org/10.1109/UIC-ATC.2013.94
Liu, H., Smith, K.: Improving the expected quality of experience in cloud-enabled wireless access networks. In: 2015 IEEE 12th International Conference on Mobile Ad Hoc and Sensor Systems, Dallas, TX, pp. 519–524 (2015). https://doi.org/10.1109/MASS.2015.53
Satyanarayanan, M., Bahl, P., Caceres, R., Davies, N.: The case for VM-based cloudlets in mobile computing. IEEE Pervasive Comput. 8(4), 14–23 (2009). https://doi.org/10.1109/MPRV.2009.82
Chen, Y,. Chen, Y., Cao, Q., Yang, X.: PacketCloud: a cloudlet-based open platform for in-network services. IEEE Trans. Parallel Distrib. Syst. 27(4), 1146–1159 (2016). https://doi.org/10.1109/TPDS.2015.2424222
Fog computing aims to reduce processing burden of cloud systems. [Online]. Available: http://www.eweek.com/
Liu, H., Eldarrat, F., Alqahtani, H., Reznik, A., de Foy, X., Zhang, Y.: Mobile edge cloud system: architectures, challenges, and approaches. IEEE Syst. J. 12(3), 2495–2508 (2018). https://doi.org/10.1109/JSYST.2017.2654119
Nunna, S., et al.: Enabling real-time context-aware collaboration through 5G and mobile edge computing. In: 2015 12th International Conference on Information Technology—New Generations, Las Vegas, NV, pp. 601–605 (2015). https://doi.org/10.1109/ITNG.2015.155
Orsini, G., Bade, D., Lamersdorf, W.: Computing at the mobile edge: designing elastic android applications for computation offloading. In: 2015 8th IFIP Wireless and Mobile Networking Conference (WMNC), Munich, pp. 112–119 (2015). https://doi.org/10.1109/WMNC.2015.10
Takahashi, N., Tanaka, H., Kawamura, R.: Analysis of process assignment in multi-tier mobile cloud computing and application to edge accelerated web browsing. In: 2015 3rd IEEE International Conference on Mobile Cloud Computing, Services, and Engineering, San Francisco, CA, pp. 233–234 (2015). https://doi.org/10.1109/MobileCloud.2015.23
Dixit, S., Pai, V.G., Rodrigues, V.C., Agnani, K., Priyan, S.R.V.: 3D reconstruction of 2D X-ray images. In: 2019 4th International Conference on Computational Systems and Information Technology for Sustainable Solution (CSITSS), Bengaluru, India, pp. 1–5 (2019). https://doi.org/10.1109/CSITSS47250.2019.9031045
Dixit, S., Ranjitha, S., Suresh, H.N.: Segmentation of handwritten Kannada text document through computation of standard error and weighted bucket algorithm. Int. J. Adv. Comput. Technol. 3(2), 55–62 (2014). ISSN: 2319-7900
Dixit, S., Narayan, S.H., Belur, M.: Kannada text line extraction based on energy minimization and skew correction. In: 2014 IEEE International Advance Computing Conference (IACC), Gurgaon, pp. 62–67 (2014). https://doi.org/10.1109/IAdCC.2014.6779295
Mannweiler, C., Schneider, J., Schotten, H., Klein, A.: Access schemes for mobile cloud computing. In: 2013 IEEE 14th International Conference on Mobile Data Management, Kanas City, Missouri, USA, pp. 387–392 (2010). https://doi.org/10.1109/MDM.2010.79. https://doi.org/10.1109/MDM.2010.79
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Dixit, S., Kathavate, S., Gautham, S.K. (2022). An Overview on Mobile Edge Cloud System. In: Senjyu, T., Mahalle, P., Perumal, T., Joshi, A. (eds) IOT with Smart Systems. Smart Innovation, Systems and Technologies, vol 251. Springer, Singapore. https://doi.org/10.1007/978-981-16-3945-6_71
Download citation
DOI: https://doi.org/10.1007/978-981-16-3945-6_71
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-3944-9
Online ISBN: 978-981-16-3945-6
eBook Packages: EngineeringEngineering (R0)