دانلود رایگان مقاله کنترل بهینه ازدحام چندمسیره در شبکه اطلاعات محور

Abstract

In this paper we consider the problem of joint congestion control and request forwarding in Information-Centric Networks, namely the named-data networking architecture (NDN). The network architecture we consider is based on information retrieval natively pull-based, driven by user requests, point-to-multipoint and intrinsically coupled with in-network caching. We formalize the problem as global optimization with non-linear objectives and linear constraints with the twofold objective of maximizing user throughput and minimizing overall network cost. We solve it via decomposition and derive a family of optimal congestion control strategies at the receiver and of distributed algorithms for dynamic request forwarding at network nodes. An experimental evaluation of our proposal is carried out in different network scenarios using realistic workloads, to assess the performance of our design and to highlight the benefits of an ICN approach. The experimentation is carried out using the NDN software router implementation on a large grid infrastructure deployed to enable experimental research.

9. Conclusions

Previous work on ICN mostly magnifies one specific aspect of the paradigm at a time, like in-network caching or adaptive forwarding, while devoting less attention to the novel communication model as a whole. Overall end-user experience and networkwide resource utilization are often left out of the picture. Also, one may argue that the limited benefits of a single building block taken apart, like in-network caching, can be approached by off-the shelf solutions, so missing the bigger potential of the ICN idea head-totoe. In this paper, we tackle the problem of a joint multipath congestion control and request forwarding in ICN and design scalable, fully distributed and inter-working mechanisms for efficient pointto-multipoint content delivery. More precisely, we formulate and solve a global optimization problem with the twofold objective of maximizing end-user throughput, while minimizing network cost. Our framework explicitly accounts for the interplay between multipath flow control, in-path caching and in-network request scheduling. As a result, we derive: (i) a family of receiver-driven multipath controllers, leveraging a unique congestion window and per-route delay monitoring. (ii) A set of optimal dynamic request forwarding strategies based on the number of pending requests which is the base for the design of a fully distributed algorithm run at ICN nodes. Note that, beyond ICN, the problem of multipath congestion control with a priori unknown and variable sources (due to in-path caching) has never been considered before.