Social Computing for Mobile Big Data in Wireless Networks

📝 Abstract

Mobile big data contains vast statistical features in various dimensions, including spatial, temporal, and the underlying social domain. Understanding and exploiting the features of mobile data from a social network perspective will be extremely beneficial to wireless networks, from planning, operation, and maintenance to optimization and marketing. In this paper, we categorize and analyze the big data collected from real wireless cellular networks. Then, we study the social characteristics of mobile big data and highlight several research directions for mobile big data in the social computing areas.

💡 Analysis

Mobile big data contains vast statistical features in various dimensions, including spatial, temporal, and the underlying social domain. Understanding and exploiting the features of mobile data from a social network perspective will be extremely beneficial to wireless networks, from planning, operation, and maintenance to optimization and marketing. In this paper, we categorize and analyze the big data collected from real wireless cellular networks. Then, we study the social characteristics of mobile big data and highlight several research directions for mobile big data in the social computing areas.

📄 Content

1 / 8

Social Computing for Mobile Big Data in Wireless Networks1

Xing Zhang12, Zhenglei Yi1, Zhi Yan3, Geyong Min4, Wenbo Wang12, Sabita Maharjan5, Yan Zhang5

1 Beijing Advanced Innovation Center for Future Internet Technology, Beijing University of Technology, Beijing, China 2 Key Laboratory of Universal Wireless Communication, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing, 100876, China, Email: zhangx@ieee.org 3 School of Electrical and Information Engineering, Hunan University, Changsha, China. 4 College of Engineering, Mathematics and Physical Sciences, University of Exeter, U.K. 5 Simula Research Laboratory, Fornebu 1364, Norway

Abstract: Mobile big data contains vast statistical features in various dimensions, including spatial, temporal, and the underlying social domain. Understanding and exploiting the features of mobile data from a social network perspective will be extremely beneficial to wireless networks, from planning, operation, and maintenance to optimization and marketing. In this paper, we categorize and analyze the big data collected from real wireless cellular networks. Then, we study the social characteristics of mobile big data and highlight several research directions for mobile big data in the social computing areas.

1. Introduction Data services’ exponential growth, and the constantly expanding wireless and mobile applications that use them, have ushered in an era of big data. Since 2014, the number of connected mobile devices has been more than the world’s population. The surge of mobile traffic in recent years is mainly attributed to the rapid proliferation of mobile social applications including multimedia, running on mobile devices such as smartphones, mobile tablets, and other smart mobile devices. By 2020, more than three- fifths of all devices connected to the mobile networks will be “smart” devices. With a compound annual growth rate (CAGR) of 53% global mobile data traffic will increase nearly eightfold between 2015 and 2020 [1]. This mobile big data poses many new challenges to conventional data analytics because of its large dimensionality, heterogeneity, and complex features therein, e.g., Volume, Variety, Velocity, Value and Veracity [2]. Dealing with big data is a key challenge for many wireless networking applications such as O&M, planning and optimization, and marketing. In this paper, to help address this problem, we provide a

1 This paper is an extended version of our previously published paper in Computer Magazine: Xing Zhang, Zhenglei Yi, Zhi Yan, Geyong Min, Wenbo Wang, Ahmed Elmokashfi, Sabita Maharjan, Yan Zhang, “Social Computing for Mobile Big Data”, Computer, vol.49, no. 9, pp. 86-90, Sept. 2016, doi:10.1109/MC.2016.267 2 / 8

classification structure for mobile big data and highlight several research directions from the perspective of social computing using a significant volume of real data collected from mobile networks. 2. Big Data in Mobile Cellular Networks The concept of ‘Big Data’ means not only a large volume of data but also other features that differentiate it from the concepts of `huge amount data’. The big data definition given in [2] includes the 5V properties: Volume, Variety, Velocity, Value and Veracity. It’s a new generation of technologies and architectures designed to economically extract value from very large volume of a wide variety of data by enabling high velocity capture, discovery, and analysis. It contains massive volume of both structured and unstructured data that is difficult to process using traditional database and software techniques. In addition to the five ‘Vs’ properties, due to the complexity of mobile cellular networks, big data in mobile cellular networks also exhibits several other unique characteristics, which lead to unprecedented challenges as well as opportunities . For instance, to understand behaviors and requirements of mobile users, which in turn allow the intelligent decision making for real-time decision making in various applications. In this section, we will introduce the data categories in mobile cellular networks and their unique characteristics. 2.1 Data Categories in Mobile Cellular Networks The vast amount of mobile data is collected and extracted from several key network interfaces, in both Radio Access Network (RAN) and Core Network (CN), as shown in Figure 1. These data can be roughly classified into four categories that include flow record data, network performance data, mobile terminal data, and additional data information, as shown in Table 1. Internet BSC RNC SGSN GGSN SGW PGW MME BTS NodeB eNodeB 2G 4G 3G S1-U SGi S5/S8 S1-MME Gn Gi Iu-Ps S11 Monitor & Collector Terminal Radio Access Network (RAN) Core Network (CN) Gb

3 / 8

Figure 1. Mobile Cellular Network Architecture and the data collecting points

Tabl

This content is AI-processed based on ArXiv data.