Content Delivery Network

With the pretty prompt growth in Internet content, future Internet is emerging as the main usage shifting from traditional host-to-host model to content dissemination model, e.g. video makes up more than half of Internet traffic. ISPs, content providers and other third parties have widely deployed content delivery networks (CDNs) to support digital content distribution. Though CDN is an ad-hoc solution to the content dissemination problem, there are still big challenges, such as complicated control plane. By contrast, as a wholly new designed network architecture, named data networking (NDN) incorporates content delivery function in its network layer, its stateful routing and forwarding plane can effectively detect and adapt to the dynamic and ever-changing Internet. In this paper, we try to explore the similarities and differences between CDN and NDN. Hence, we evaluate the distribution efficiency, network security and protocol overhead between CDN and NDN. Especially in the implementation phase, we conduct their testbeds separately with the same topology to derive their performance of content delivery. Finally, summarizing our main results, we gather that: 1) NDN has its own advantage on lots of aspects, including security, scalability and quality of service (QoS); 2) NDN make full use of surrounding resources and is more adaptive to the dynamic and ever-changing Internet; 3) though CDN is a commercial and mature architecture, in some scenarios, NDN can perform better than CDN under the same topology and caching storage. In a word, NDN is practical to play an even greater role in the evolution of the Internet based on the massive distribution and retrieval in the future.

A Content Delivery Network (CDN) is a distributed network of servers (that provide web content) and file storage devices deployed in various geographical locations such that when requests are being made by users, these requests are redirected via GEO-DNS to the closest content repository to the user for response. This work proposes an adaptive request routing algorithm to choose the replica server using network
proximity and a combination of Quality of Service metrics. The metrics include: bandwidth, availability of server, and latency. This is because the original intention of CDNs is for surrogate servers to respond to request from clients that are closer in proximity. This is not always the best option because the closest surrogate may either be overloaded (making it unavailable) or the connection may be poor. Thus, proximity with a mixture of metric are combined to choose the best surrogate to respond to request. In contrast to most works in existing literature, this study employs three metrics and five membership functions (Very high, High, Medium, Low and Very low) based on the rules guiding fuzzy logic to give an accurate measure for each of the three metrics used in order to determine without errors when to grant or deny a request from the users. This makes it an improvement on existing works that used some other metrics and only three membership functions (High, Medium and Low), this research uses two additional membership functions which help to give a more precise measure of the variables in question and hence improves the efficiency of the request delivery, thus giving users of the network more robust information as regards the quality of web content service delivery.

Real-time content delivery services have recently achieved high popularity in Internet, both for professional communities and also for entertainment. In contrast with some complex architectures like Content Delivery Networks, or Content Oriented Networks, this paper considers a light architecture, working on top of the current networking IP multi-domain infrastructures. It enhances the real-time (video) content delivery, by exploiting the cases where the content object exists on several servers. The system performs an initial content server selection (based on multi-criteria) considering the servers' load status and network conditions. Then it performs in-session media dynamic flow rate adaptation. Additionally, if necessary, a server handover is triggered. All above functionalities are assembled in a unified solution. This paper is a preliminary work, to identify the main requirements and then to develop the design for a family of implementations. Different design decisions variants are analyzed and explored, proving the solution flexibility. Currently the proposed system is under implementation in the framework of a European project.

The success of novel bandwidth-consuming multimedia
services such as Video-on-Demand (VoD) is leading to
a tremendous growth of the Internet traffic. Content caching
can help to mitigate such uncontrolled growth by storing video content closer to the users in core, metro and access network nodes. So far, metro and especially access networks supporting mobile and fixed users have evolved independently, leveraging logically (and often also physically) separate infrastructures; this means that mobile users cannot access caches placed in the fixed access network (and vice-versa), even if they are geographically close to them, and energy consumption implications of such undesired effect must be investigated. We define an optimization problem modeling an energy-efficient placement of caches in core, metro and fixed/mobile access nodes of the network. Then, we show how the evolution towards a Fixed-Mobile Converged metro/access network, where fixed and mobile users can share caches, can reduce the energy consumed for VoD content delivery.