Internet traffic analysis: A case study from two major European operators

Abstract

International audienceNetwork and service operators nowadays use probes located in their networks in order to improve their knowledge on traffic evolution. The limited set of managed services like IPTV enable the use of well controlled rules for network dimensioning but this is not the case for public Internet originated traffic. Due to the growing success of services delivered by Internet players, a close attention given to customers' usage is mandatory to make accurate forecasts in order to avoid future network congestion. The present paper proposes a detailed analysis based on real Internet traffic captured on fixed (xDSL, FTTH) and mobile networks of Orange France and Telefónica operators. Internet traffic profile (traffic evolution over the time) for fixed and mobile networks is described. The paper discusses the relation between access technologies and traffic profiles. Additionally, it clarifies how both fixed and mobile residential customers access Internet services. This provides insight on the applications generating the major part of the traffic (i.e. video streaming, peer-to-peer, file downloading, etc.) and on the proportion of traffic generated by the "heavy users"

On Optimal Proactive Caching for Mobile Networks With Demand Uncertainties

“…Large timescale data networks are known to exhibit statistically fluctuating, periodic demand patterns, typically on a daily basis [4], [6], [11]. Accordingly, we assume that each day is divided into time-slots whereby a user can generate one request per slot according to the statistics of , and only require the following mild ergodicity characteristics: 2 We note that the results and insights obtained in this paper apply to the more general case of being user-dependent, and some special cases of time dependency.…”

“…It is well documented by the FCC that the wireless spectrum consistently incurs periods of underutilization on a daily basis [2], [3], which is attributed to the users' behavioral patterns as most users idle together in the off-peak times. This study is also strengthened by the wireless spectrum measurements carried out by RRDTool [4], [5], the wireless spectrum tracking client, and the recent data traces collected by major European operators in [6]. Thus, the demand on wireless spectrum varies between a peak level at which service providers incur excessive costs to provide reliable delivery of data content, and an off-peak level at which the precious resource is left underutilized.…”

“…Despite the predominance of reactive solutions in mobile data services, it is also well known that data users possess consistent (therefore statistically predictable) interests and activity patterns (e.g., [6] and [18]- [20]). This has motivated a few recent works [21], [22] to develop proactive scheduling strategies to smooth out the network traffic over time, reduce the service costs, and essentially preserve the users' activity patterns undisturbed.…”

Effective Internet Traffic Management by Reducing Congestion in TCP Cubic through Proactive Approach

“…So the Internet Traffic is a density of data which travels on the Internet Connection. Internet exchanges numerous information in the form of a huge number of:- [5]. These two multimedia websites is generating more than half of total internet traffic.…”

A Scalable Parallel Architecture Based on Many-Core Processors for Generating HTTP Traffic

“…Unfortunately, such a tool is not easily available, and is usually of much smaller scale than needed. Recent research suggests that the Web still occupies 15%∼18% of the traffic [1]. Therefore, generating high-performance and a representative Web traffic generator is crucial for evaluating the emerging network architecture under different network conditions.…”