Abstract

Nowadays, P2P applications are commonly used in the Internet being an important paradigm for the development of distinct services. However, the dissemination of P2P applications also entails some important challenges that should be carefully addressed. In particular, some of the important coexistence problems existing between P2P applications and Internet Service Providers (ISPs) are mainly motivated by the inherent P2P dynamics which cause traffic to scatter across the network links in an unforeseeable way.\r \r In this context, this work proposes a collaborative framework of a BitTorrent like system. Using the proposed framework and based on the exchange of valuable information between the application and network levels, some novel techniques are proposed allowing to estimate and control the traffic impact that the P2P system will have on the links of the underlying network infrastructure. Both the framework and the presented techniques were tested resorting to simulation. The results clearly corroborate the viability and effectiveness of the formulated methods. Document type: Part of book or chapter of book

Abstract

Nowadays, P2P applications proliferate in the Internet with distinct utilization contexts, being also an attractive model for the deployment of advanced Internet services. However, there are several undesirable effects that are caused by such applications, raising coexistence problems with Internet Service Providers (ISPs). In this context, using as case study BitTorrent like applications, this work explores a collaborative framework allowing that advanced efforts could be carried on between P2P applications and network level entities. In order to illustrate such framework, several Traffic Engineering (TE) mechanisms are devised in order to align some P2P dynamics with particular objectives pursued by network administrators. The simulation results show that both the proposed framework and corresponding illustrative mechanisms are viable and can effectively foster future research efforts within this field. (undefined) Document type: Part of book or chapter of book

Abstract

Lots of research works have been performed for about ten years around the QoS problem in the Internet, both but separately at the Transport and at the IP levels. Taking into account the emerging traffic engineering-based QoS solutions (Diffserv-oriented), this paper targets the integration of new Transport services and protocols together with these solutions. Starting from performance measurements performed over a national DiffServ platform, contributions exposed here deal with the proposition and the implementation of a session level protocol allowing the application programmers to be masked with the complexity of choosing the underlying new Transport and IP services, still being provided with a per flow QoS. Document type: Part of book or chapter of book

Abstract

© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Nowadays, there is a fast-paced shift from legacy telecommunication systems to novel Software Defined Network (SDN) architectures that can support on-the-fly network reconfiguration, therefore, empowering advanced traffic engineering mechanisms. Despite this momentum, migration to SDN cannot be realized at once especially in high-end cost networks of Internet Service Providers (ISPs). It is expected that ISPs will gradually upgrade their networks to SDN over a period that spans several years. In this paper, we study the SDN upgrading problem in an ISP network: which nodes to upgrade and when. We consider a general model that captures different migration costs and network topologies, and two plausible ISP objectives; first, the maximization of the traffic that traverses at least one SDN node, and second, the maximization of the number of dynamically selectable routing paths enabled by SDN nodes. We leverage the theory of submodular and supermodular functions to devise algorithms with provable approximation ratios for each objective. Using real-world network topologies and traffic matrices, we evaluate the performance of our algorithms and show up to 54% gains over state-of-the-art methods. Moreover, we describe the interplay between the two objectives; maximizing one may cause a factor of 2 loss to the other. EC/H2020/679158/EU/Resolving the Tussle in the Internet: Mapping, Architecture, and Policy Making/ResolutioNe