Computing on Base Station Behavior Using Erlang Measurement and Call Detail Record

Abstract

As the impressive development of wireless devices and growth of mobile users, telecommunication operators are thirsty for understanding the characteristics of mobile network behavior. Based on the big data generated in the telecommunication networks, telecommunication operators are able to obtain substantial insights by using big data analysis and computing techniques. This paper introduces the important aspects in this topic, including data set information, data analysis techniques and two case studies. We categorize the data set in the telecommunication networks into two types, user-oriented and network-oriented, and discuss the potential application. Then several important data analysis techniques are summarized and reviewed, from temporal and spatial analysis to data mining and statistical test. Finally, we present two case studies, using erlang measurement and call detail record, respectively, to understand the base station behavior. Interestingly, the 'Night Burst' phenomenon of college students is revealed by comparing the base stations location and real-world map, and we conclude that it is not proper to model the voice call arrivals as Poisson process.

Leveraging Intelligence from Network CDR Data for Interference Aware Energy Consumption Minimization

“…Contrary to prior studies, this paper provides a fundamentally different approach, i.e., a proactive approach, that builds on the lines of Big Data empowered Self Organizing Network (BSON) vision presented for 5G in [37] leveraging CDRs to simultaneously minimize energy consumption and ICI in emerging ultra-dense networks. Several studies have demonstrated the usefulness of using real-world CDRs data in the mobile network analysis and planning in comparison to analytical approaches [38], [39]. The authors in [38] have performed a spatio-temporal analysis of CDRs data collected from various base stations in China.…”

“…Several studies have demonstrated the usefulness of using real-world CDRs data in the mobile network analysis and planning in comparison to analytical approaches [38], [39]. The authors in [38] have performed a spatio-temporal analysis of CDRs data collected from various base stations in China. It has been concluded that call arrival patterns vary over time and locations and Poisson distribution model over 1 hour interval is inaccurate and it has been pointed out that advance machine learning algorithms can help model the phenomena more precisely.…”

Semantic Analysis of Literary Vocabulary Based on Microsystem and Computer Aided Deep Research

“…e number of layers of the network is deep, the number of feature maps extracted from each layer is large, and the scale and semantic information are different. erefore, it is necessary to carry out effective feature reorganization on the feature maps extracted from each layer of the backbone network, and it is of certain significance to use the global semantic information of the image [23]. Suppose the convolution kernel size is as follows:…”

Survey of wireless big data

“…As for traffic analysis, Zhang et al [33] first categorized the data set in the telecommunication networks into user-oriented and network-oriented. Thereafter it presents the two case studies in the temporal dimension and spatial dimension.…”