Mobile Data Networks Research Articles

A Systematic Review on Machine Learning and Deep Learning Models for Electronic Information Security in Mobile Networks.

Today’s advancements in wireless communication technologies have resulted in a tremendous volume of data being generated. Most of our information is part of a widespread network that connects various devices across the globe. The capabilities of electronic devices are also increasing day by day, which leads to more generation and sharing of information. Similarly, as mobile network topologies become more diverse and complicated, the incidence of security breaches has increased. It has hampered the uptake of smart mobile apps and services, which has been accentuated by the large variety of platforms that provide data, storage, computation, and application services to end-users. It becomes necessary in such scenarios to protect data and check its use and misuse. According to the research, an artificial intelligence-based security model should assure the secrecy, integrity, and authenticity of the system, its equipment, and the protocols that control the network, independent of its generation, in order to deal with such a complicated network. The open difficulties that mobile networks still face, such as unauthorised network scanning, fraud links, and so on, have been thoroughly examined. Numerous ML and DL techniques that can be utilised to create a secure environment, as well as various cyber security threats, are discussed. We address the necessity to develop new approaches to provide high security of electronic data in mobile networks because the possibilities for increasing mobile network security are inexhaustible.

Privacy retrieval method of big data in mobile network based on edge computing

In order to better achieve the goal of big data privacy retrieval and ensure user data security, a mobile network big data privacy retrieval method based on edge computing is proposed. Combined with the principle of edge computing, identify the privacy characteristics of mobile network big data, build a feature database for data management, optimize the privacy data security encryption algorithm, and simplify the privacy retrieval process of mobile network big data. Finally, experiments show that the mobile network big data privacy retrieval method based on edge computing has high security and effectiveness in the process of practical application, and fully meets the research requirements.

Performance Evaluation of a SCM-OFDM Radio over Fiber System for the Mobile Fronthaul

The exponential growth in mobile data traffic caused by the upsurge of Internet users has led to a high demand of capacity on the mobile data networks. High capacity and high data rate requirements created an emergence of Radio over Fiber (RoF) technology which is a possible key in the provision of high bandwidth and cost-effective fronthaul solutions. This paper presents an evaluation on the integration of Subcarrier Multiplexing (SCM) with RoF and Orthogonal Frequency Division Multiplexing (OFDM) technologies to enhance the system capacities. A 4-channel SCM-OFDM architecture combined with RoF technology is examined across three different modulation schemes (i.e., 256-QAM, 64-QAM and 16-QAM) for transmission distances from 10 km to 120 km for two data rates i.e., (5 and 10) Gbps. The performance of the architectures is measured by Bit-error rate (BER), Quality-factor (Q-factor), Signal-to-Noise Ratio (SNR), Error Vector Magnitude (EVM), Eye-Opening Penalty (EOP), received power and of transmitted signals. The simulation results indicates that the SCM-OFDM model at a 10 Gbps data rate gives a better performance under the 256-QAM modulation scheme. Furthermore the performance of all the SCM-OFDM systems is more superior operating at a 10 Gbps data rate when compared to the 5 Gbps data rate.

Monitoring COVID-19-Induced Gender Differences in Teleworking Rates Using Mobile Network Data

The COVID-19 pandemic has created a sudden need for a wider uptake of home-based telework as means of sustaining the production. Generally, teleworking arrangements impact directly worker’s efficiency and motivation. The direction of this impact, however, depends on the balance between positive effects of teleworking (e.g. increased flexibility and autonomy) and its downsides (e.g. blurring boundaries between private and work life). Moreover, these effects of teleworking can be amplified in case of vulnerable groups of workers, such as women. The first step in understanding the implications of teleworking on women is to have timely information on the extent of teleworking by age and gender. In the absence of timely official statistics, in this paper we propose a method for nowcasting the teleworking trends by age and gender for 20 Italian regions using mobile network operators (MNO) data. The method is developed and validated using MNO data together with the Italian quarterly Labour Force Survey. Our results confirm that the MNO data have the potential to be used as a tool for monitoring gender and age differences in teleworking patterns. This tool becomes even more important today as it could support the adequate gender mainstreaming in the ‘Next Generation EU’ recovery plan and help to manage related social impacts of COVID-19 through policymaking.

Self-play learning strategies for resource assignment in Open-RAN networks

Open Radio Access Network (ORAN) is being developed with an aim to democratise access and lower the cost of future mobile data networks, supporting network services with various QoS requirements, such as massive IoT and URLLC. In ORAN, network functionality is dis-aggregated into remote units (RUs), distributed units (DUs) and central units (CUs), which allows flexible software on Commercial-Off-The-Shelf (COTS) deployments. Furthermore, the mapping of variable RU requirements to local mobile edge computing centres for future centralised processing would significantly reduce the power consumption in cellular networks. In this paper, we study the RU–DU resource assignment problem in an ORAN system, modelled as a 2D bin packing problem. A deep reinforcement learning-based self-play approach is proposed to achieve efficient RU–DU resource management, with AlphaGo Zero inspired neural Monte-Carlo Tree Search (MCTS). Experiments on representative 2D bin packing environment and real sites data show that the self-play learning strategy achieves intelligent RU–DU resource assignment for different network conditions. Comparing with baseline methods, including a heuristic virtual resource allocation algorithm, the Lego heuristic algorithm and the MCTS methods, the proposed approach achieves a performance gain between 5.70% to 12.95% in terms of resource utilisation efficiency.

ERICSSON MOBILITY REPORT (REVIEW. PART I)

Resilient networks are the foundation for continued digitalization of societies and industries. Continuous network modernization and coverage build-out has led to several hundred million people becoming new mobile broadband subscribers every year. 5G is scaling faster than any previous mobile generation and we expect 5G subscriptions to reach 1 billion by the end of 2022. In several regions, deployment of 5G standalone networks is also picking up pace, as communications service providers prepare for innovation to address the business opportunities beyond enhanced mobile broadband. A solid digital network infrastructure underpins enterprises’ digital transformation plans, and their new capabilities can be turned into new customer services. As exemplified in this edition, service providers are looking to expand out of pure connectivity into service enablement platforms. Global mobile network data traffic has doubled in the last two years, driven by continuing growth in smartphone usage, mobile broadband and now the digitalization of societies and industries. But traffic is not the only thing that grows. The ongoing war in Europe, as well as increased geopolitical tension in the world, leads to a range of global threats – economic as well as social – that must be navigated. And in our field of networking, the threat landscape calls for constant diligence in keeping ahead with security. You can read more about security in this edition. Managing the continued strong traffic growth while reducing energy consumption is also a top priority. Older technologies are being replaced by continuous build-out of 4G and 5G networks, substantially improving network performance and energy efficiency with each generation. 5G technologies play a key role in modernization, providing multiples of capacity while becoming more energy efficient. Innovative network technologies enable service providers to introduce new services that in turn support societies and enterprises to reduce their carbon emission footprint. In this edition, we share some examples of how 4G and 5G technologies make it possible to unleash the power of IoT connectivity to enhance both enterprises’ business performance and sustainability.

Graphene two terminal detector as THz mixer

The growing requirements for mobile communication networks (data transfer rates over 100 Gbps) makes it necessary to use carrier signal with a frequency of at least 100 GHz. This requires the development of cheap and broadband sub-terahertz (sub-THz) detectors. Here we report on our recent efforts toward the development of a heterodyne sub-THz detector based on a single layer graphene two-terminal device integrated with a bowtie antenna on a sapphire substrate. Our detector operates at frequency of 140 GHz, which corresponds to the maximum transmission of THz radiation in the Earth’s atmosphere. The heterodyne detection is achieved by quasi-optical coupling of signals from two sub-THz radiation sources to the same detector. The measured frequency bandwidth is 5.8 GHz.

Analyzing the Behavior and Financial Status of Soccer Fans from a Mobile Phone Network Perspective: Euro 2016, a Case Study

In this study, Call Detail Records (CDRs) covering Budapest for the month of June in 2016 were analyzed. During this observation period, the 2016 UEFA European Football Championship took place, which significantly affected the habit of the residents despite the fact that not a single match was played in the city. We evaluated the fans’ behavior in Budapest during and after the Hungarian matches and found that the mobile phone network activity reflected the football fans’ behavior, demonstrating the potential of the use of mobile phone network data in a social sensing system. The Call Detail Records were enriched with mobile phone properties and used to analyze the subscribers’ devices. Applying the device information (Type Allocation Code) obtained from the activity records, the Subscriber Identity Modules (SIM), which do not operate in cell phones, were omitted from mobility analyses, allowing us to focus on the behavior of people. Mobile phone price was proposed and evaluated as a socioeconomic indicator and the correlation between the phone price and the mobility customs was found. We also found that, besides the cell phone price, the subscriber age and subscription type also had effects on users’ mobility. On the other hand, these factors did not seem to affect their interest in football.

Predicting short‐term mobile Internet traffic from Internet activity using recurrent neural networks

SummaryMobile network traffic prediction is an important input into network capacity planning and optimization. Existing approaches may lack the speed and computational complexity to account for bursting, non‐linear patterns, or other important correlations in time series mobile network data. We compare the performance of two deep learning (DL) architectures, long short‐term memory (LSTM) and gated recurrent unit (GRU), and two conventional machine learning (ML) architectures—Random Forest and Decision Tree—for predicting mobile Internet traffic using 2 months of Telecom Italia data for Milan. K‐Means clustering was used a priori to group cells based on Internet activity, and the Grid Search method was used to identify the best configurations for each model. The predictive quality of the models was evaluated using root mean squared error and mean absolute error. Both DL algorithms were effective in modeling Internet activity and seasonality, both within days and across 2 months. We find variations in performance across clusters within the city. Overall, the DL models outperformed the conventional ML models, and the LSTM outperformed the GRU in our experiments.

Urban Recovery from the COVID-19 Pandemic in Beijing, China

This study documented the geography of the recovery of human activity in Beijing, China, after the city successfully brought the COVID-19 pandemic under control at the end of spring 2020. By using mobile phone network data at fine spatial and temporal scales, we compared the levels of human activity in the morning, afternoon, and evening on weekdays and weekends at the microlevel (1 km × 1 km) before and after the pandemic. Both our descriptive and modeling analyses showed more recovery on weekdays than on weekends. The recovery was faster in the areas that were further away from the city center. Residence-oriented areas recovered faster than non-residence-oriented areas, particularly in the early stages of recovery. The areas with large-scale parks recovered faster, confirming the importance of parks in urban health. The presence of a university campus was a strong predictor of slow recovery in Beijing. Although people avoided using public transit during the pandemic, the level of transit service did not seem to predict urban recovery after the pandemic was under control.

(ITMP) – Intelligent Traffic Management Prototype using Reinforcement Learning approach for Software Defined Data Center (SDDC)

Software defined network architecture offers scalability and resilience as the significant advantages to data center networks. This increases the fault tolerance ability of traditional data center network architectures. Massive amounts of mobile network data as well as e-commerce application data requests are the key sources for data centers which recurrently desire attention. Researchers are yet to design a suitable prototype with functional intelligence to support traffic optimization techniques in SDDC. In this research work, we are proposing an intelligent traffic management prototype for software defined data center by means of reinforcement learning approach through the integration of the functionalities such as controller positioning, traffic load balancing, routing and energy efficiency. These are the key areas where traffic optimization becomes essential to improve network performance. The proposed prototype provides a complete framework for enterprises to deploy applications in an efficient manner. We model the prototype to handle dynamic network data applications such as information retrieval, communication and banking applications. We focus in this article on how communication happens among the data center nodes as an inter-data center communication process upon receiving requests from the applications considered. To further enhance the novelty and efficiency of our research work, we adopt multiple reinforcement learning agents to lever load balancing and routing functionalities. Moreover, to assess and ensure the optimized network performance, we evaluate the energy consumption of the network achieved through our proposed prototype.

Information matching model and multi-angle tracking algorithm for loan loss-linking customers based on the family mobile social-contact big data network

This article focuses on the tracking problem of loan loss-linking customers based on the family mobile social-contact big data network. By defining suspected loan loss-linking customer and family member intimacy, a mobile social-contact big data network of the loan loss-linking customers’ family members is constructed, and similarity of mobile phone usage habits, contact similarity, and contact point similarity in the mobile social-contact big data network are defined and studied accordingly. Then, the similarity matching degrees of mobile phone usage habits, contact locations, and contacts between suspected loan loss-linking customers and loan loss-linking customers are analyzed from the perspective of similarity. This establishes an information matching model of loan loss-linking customers, and proposes the multi-angle tracking algorithm of loan loss-linking customers, allowing information matching and multi-angle tracking for loan loss-linking customers, and applies the model and the algorithm to the loan data of a bank in China. The empirical results show that the proposed model and algorithm can track loan loss-linking customers, and the algorithm exhibits rapid convergence. This study has important significance and practical value for financial institutions to track loan loss-linking customers and recover funds.

Analytics of location-based big data for smart cities: Opportunities, challenges, and future directions

The growing ubiquity of location/activity sensing technologies and location-based services (LBS) has led to a large volume and variety of location-based big data (LocBigData), such as location tracking or sensing data, social media data, and crowdsourced geographic information. The increasing availability of such LocBigData has created unprecedented opportunities for research on urban systems and human environments in general. In this article, we first review the common types of LocBigData: mobile phone network data, GPS data, Location-based social media data, LBS usage/log data, smart card travel data, beacon log data (WiFi or Bluetooth), and camera imagery data. Secondly, we describe the opportunities fueled by LocBigData for the realization of smart cities, mainly via answering questions ranging from “what happened” and “why did it happen” to “what's likely to happen in the future” and “what to do next”. Thirdly, pitfalls of dealing with LocBigData are summarized, such as high volume/velocity/variety; non-random sampling; messy and not clean data; and correlations rather than causal relationships. Finally, we review the state-of-the-art research trends in this field, and conclude the article with a list of open research challenges and a research agenda for LocBigData research to help achieve the vision of smart and sustainable cities.

Cross-phase modulation compensation in multichannel system based on filter bank multicarrier modulation

Futuristic mobile data networks are expected to reach higher data rates per user to accommodate the specifications of emerging services, such as triple play and mobile applications. Researchers are carrying out their works to tackle the drawbacks of traditional orthogonal frequency-division multiplexing by designing new waveforms with high spectral efficiency and low out-of-band emissions. Among many others, filter bank multicarrier (FBMC) is an appealing candidate for beyond 5G that fulfills these constraints. Consequently, it is worth to shed light on the performance of FBMC in multichannel transmission system. The main contribution of our paper is to compensate fiber nonlinearity including self-phase modulation and cross-phase modulation effects using adaptive Volterra equalizer in longhaul FBMC system based on a 6 × 20 Gb / s in wavelength-division multiplexing scheme over 100 km × 30 spans of single-mode fiber (SMF). The impacts of channel spacing, bit rate, and fiber types on system performance are addressed. For a target of bit error rate = 10 − 3, the simulations show that this performance can be reached at −12 dBm of launch power when 5-taps third-order Volterra (TOV) equalizer is used for 12.5 GHz of channel spacing and an improvement of approximately 1 dB is obtained for 7 taps compared with the same equalizer with 3 taps. To further enhance the system performance, standard-SMF is replaced by a new class fiber called pure-silica-core fiber with large effective area, which exhibits a gain of almost 1.3 and 1 dB for 3 and 5 taps, respectively. The complexity burden of the TOV filter is also discussed.

Cardinality Bundling Under Oligopoly – a Simulation Model

The analysis of the putative effect of proposed mergers of mobile telecommunications operators has reached unprecedented levels of complexity, typically now running into hundreds of pages whereas in 2007 the European Commission was able to approve a 4-to-3 merger in The Netherlands on the basis of 18 pages of analysis. At the heart of this analysis is the structure of the industry, based on the number of firms. This paper takes a new approach in which we explicitly focus on the fact that for mobile operators today, the main product (with the possible exception of the handset subsidy) is data bundles. In the presence of heterogeneous consumer valuations, firms choose bundle sizes and prices. The structural focus of our analysis is the effect of the number and range of bundles offered, in addition to the number of firms, on form profits and consumer surplus. Future work will incorporate the dimension of time as in practice data bundles with various periods of validity are offered in the market. We construct a discrete model in which optimal pricing strategies for firms are determined in a Stackelberg-type competition model. There are finitely many consumers and finitely many firms. Firms determine their quasi-optimal pricing strategy in sequence by using simulation to each select a fixed number of bundles of a single product to offer. Bundles differ in their price and size. There is assumed to be no product differentiation among the firms and consumers have randomized willingness to pay and select their optimal purchase(s) by maximizing their individual consumer surplus. Some customers may choose to purchase nothing at all. First, we select distributions for the firms' choices and for the consumer valuations that allow for outcomes that are typically observed in an oligopoly market like mobile network data. The finite number of consumers can be thought of discrete groups of types of consumers. This is not entirely dissimilar to the user baskets often used (low, moderate and high volume users) in merger analysis. Second, we investigate the effect on consumer and total welfare of a change in the number of firms using our Monte Carlo simulation. Prices and quantities as well as customer valuations are discrete variables and we purposely eschew an attempt to find an analytical solution. The model builds on models where a single firm determines bundling prices and strategies (e.g. Spence, 1980; Schmalensee, 1984; Hitt and Chen, 2005;, Wu et al., 2018; Ye, et al., 2019; Bucarey, et al, 2021), by incorporating competitive interaction (e.g. Mantovani and Vanderkerckhove, 2016). The novelty of our model is the ability to calibrate it to provide insights across a wide range of distributions of customer willingness-to-pay, other consumer preference characteristics and market structures (number of firms). The model is informative for both competition authorities assessing merger proposals, and for firms engaged in cardinality bundle pricing or contemplating market entry. A key finding is that in this model, a reduction of the number of firms from 4 to 3 has no effect on consumer surplus. We also see that when the model runs with 4 firms, it quite often happens that an equilibrium state is reached where one of the firms fails to make any sales at all. This was not observer in the case of 3 firms.

Revealing correlation patterns of individual location activity motifs between workdays and day-offs using massive mobile phone data

Recently, people are increasingly interested in understanding broader and longer-term individual activity-travel behaviors across days or even weeks. However, the relationship of individual daily activity-travel behaviors over multi-days only remains partially revealed, especially between workdays and day-offs. Thus, we develop an effective framework to extract individual daily activity-travel patterns from massive mobile phone network data on basis of location activity motifs (LAMs), which are beneficial to combining the locations, activities, and trips in daily activity-travel behaviors. We then discover that the modified number of LAMs over time conforms well to the classic exploration and preferential return (EPR) model after excluding the influence of the number of trips, which reproduces the human activity-travel behavior characteristics on daily scale and indicates that the complex relationship of LAMs exists between workdays and day-offs. Furthermore, we emphasize three categories of correlation patterns while the relationship of LAMs between workdays and day-offs is instantiated using association rules mining algorithm. Ultimately, the regular individual differences and obvious spatial heterogeneity reveal the formation mechanism of correlation patterns. These empirical results contribute to develop different but related transportation strategies between workdays and day-offs by understanding individual daily activity-travel behaviors.

The influence of location-based games on traditional entertainment products

Digital technologies and in particular the prevalence of mobile devices and high-speed mobile data networks enable new entertainment products such as location-based games (LBGs). Due to their requirement for constant user mobility, LBGs have the potential to affect individuals' consumption patterns of entertainment products and can thus change the nature of business in the context of this emerging technology. The objective of this study is to identify and measure whether LBGs' advent has shifted the consumption of other entertainment products and generate insights which can support practitioners with their strategic business decisions. To this end, we analyze the consumption of the most popular entertainment products (i.e., TV, PC-based online games, and cinema) before and after the release of Pokémon Go. Our results extend prior literature and show that the effect of LBGs—as a new type of entertainment product—is not confined to one product category but can affect multiple product categories of the entertainment industry. In particular, our estimation results indicate that LBGs can attenuate TV and PC online games consumption, but enhance cinema attendance.

An end-to-end statistical process with mobile network data for official statistics

Mobile network data has been proven to provide a rich source of information in multiple statistical domains such as demography, tourism, urban planning, etc. However, the incorporation of this data source to the routinely production of official statistics is taking many efforts since a diversity of highly entangled issues (access, methodology, IT tools, quality, skills) must be solved beforehand. To do this, one-off studies with concrete data sets are not enough and a standard statistical production process must be put in place. We propose a concrete modular process structured into evolvable modules detaching the strongly technological layer underlying this data source from the necessary statistical analysis producing outputs of interest. This architecture follows the principles of the so-called ESS Reference Methodological Framework for Mobile Network Data. Each of these modules deals with a different aspect of this data source. We apply hidden Markov models for the geolocation of mobile devices, use a Bayesian approach on this model to disambiguate devices belonging to the same individual, compute aggregate numbers of individuals detected by a telecommunication network using probability theory, and model hierarchically the integration of auxiliary information from the telco market and official data to produce final estimates of the number of individuals across different territorial regions in the target population. A first simple illustrative proposal has been applied to synthetic data providing preliminary software tools and accuracy indicators monitoring the performance of the process. Currently, this exercise has been applied to the estimation of present population and origin-destination matrices. We present an illustrative example of the execution of these production modules comparing results with the simulated ground truth, thus assessing the performance of each production module.

Analyzing group behavior patterns in a cellular mobile network for 5G use‐cases

SummaryThe massive demand for broadband mobile network services are quite successfully covered already by 3G and 4G cellular mobile systems. The challenges for 5G are more diverse: answering the demands of Ultra‐Reliable Low Latency Communications (URLLC) and massive Machine Type Communications (mMTC) users—besides elevating mobile broadband to the next level. While generic, high‐level targets for KPIs (Key Performance Indicators) are widely communicated, it is not yet well‐understood how the various demands can affect the traffic mixture. Both the radio‐ and the core‐domains of the cellular network have to cope with traffic peaks, and have to obey various QoS (Quality of Service) guarantees. In order to cover these gaps, traffic‐related characteristics (data volume, signaling message types, and traffic peaks) should be determined, and this knowledge should be used during network planning, optimization, and service shaping.This paper aims to provide insights into user behavioral patterns for these three key application areas: enhanced Mobile Broadband (eMBB), URLLC and mMTC. Since traffic volume‐ and burst‐related user behavior is not expected to change suddenly, current targeted data collection on legacy mobile network links would provide a good basic insight for future, 5G usage—at least as traffic patterns. We have collected live pre‐5G mobile network data then analyzed them throughout this paper in order to reveal traffic patterns—and their distinguishing features—for the three key 5G application areas.

Mobility during the COVID-19 Pandemic: A Data-Driven Time-Geographic Analysis of Health-Induced Mobility Changes

The COVID-19 pandemic has profoundly affected the spatial mobility of a major part of the population in many countries. For most people, this was an extremely disruptive shock, resulting in loss of income, social contact and quality of life. However, forced to reduce human physical interaction, most businesses, individuals and households developed new action lines and routines, and were gradually learning to adapt to the new reality. Some of these changes might result in long-term changes in opportunity structures and in spatial preferences for working, employment or residential location choice, and for mobility behavior. In this paper we aim to extend the time-geographic approach to analyzing people’s spatial activities, by focusing on health-related geographical mobility patterns during the pandemic in Sweden. Starting from a micro-approach at individual level and then looking at an aggregate urban scale, we examine the space-time geography during the coronavirus pandemic, using Hägerstrand’s time-geography model. We utilize a massive but (location-wise) fuzzy dataset to analyze aggregate spatiotemporal impacts of the COVID-19 pandemic using a contemporary time-geographical approach. First, we address micro-level behavior in time-space to understand the mechanisms of change and to illustrate that a temporal drastic change in human mobility seems to be plausible. Then we analyze the changes in individuals’ mobility by analyzing their activity spaces in aggregate using mobile phone network data records. Clearly, it is too early for predicting long-term spatial changes, but a clear heterogeneity in spatial behavior can already be detected. It seems plausible that the corona pandemic may have long-lasting effects on employment centers, city roles and spatial mobility patterns.