Saltarin de Arco, Jonnahtan Eduardo (2017). Network Coding Enabled Named Data Networking Architectures. (Thesis). Universität Bern, Bern
|
Text
Thesis_SaltarinDeArco.pdf - Thesis Available under License Creative Commons: Attribution-Noncommercial-No Derivative Works (CC-BY-NC-ND 4.0). Download (1MB) | Preview |
Abstract
The volume of data traffic in the Internet has increased drastically in the last years, mostly due to data intensive applications like video streaming, file sharing, etc.. This motivates the development of new communication methods that can deal with the growing volume of data traffic. To this aim, Named Data Networking (NDN) has been proposed as a future Internet architecture that changes how the Internet works, from the exchange of content between particular nodes of the network, to retrieval of particular content in the network. The NDN architecture enables ubiquitous in-network caching and naturally supports dynamic selection of content sources, characteristics that fit well with the communication needs of data intensive applications. However, the performance of data intensive applications is degraded by the limited throughput seen by applications, which can be caused by (i) limited bandwidth, (ii) network bottlenecks and (iii) packet losses. In this thesis, we argue that introducing network coding into the NDN architecture improves the performance of NDN-based data intensive applications by alleviating the three issues presented above. In particular, network coding (i) enables efficient multipath data retrieval in NDN, which allows nodes to aggregate all the bandwidth available through their multiple interfaces; (ii) allows information from multiple sources to be combined at the intermediate routers, which alleviates the impact of network bottlenecks; and (iii) enables clients to efficiently handle packet losses. This thesis first provides an architecture that enables network coding in NDN for data intensive applications. Then, a study demonstrates and quantifies the benefits that network coding brings to video streaming over NDN, a particular data intensive application. To study the benefits that network coding brings in a more realistic NDN scenario, this thesis finally provides a caching strategy that is used when the in-network caches have limited capacity. Overall, the evaluation results show that the use of network coding permits to exploit more efficiently available network resources, which leads to reduced data traffic load on the sources, increased cache-hit rate at the in-network caches and faster content retrieval at the clients. In particular, for video streaming applications, network coding enables clients to watch higher quality videos compared to using traditional NDN, while it also reduces the video servers' load. Moreover, the proposed caching strategy for network coding enabled NDN maintains the benefits that network coding brings to NDN even when the caches have limited storage space.
| Item Type: | Thesis |
|---|---|
| Dissertation Type: | Single |
| Date of Defense: | 2017 |
| Subjects: | 000 Computer science, knowledge & systems 500 Science > 510 Mathematics |
| Institute / Center: | 08 Faculty of Science > Institute of Computer Science (INF) > Communication and Distributed Systems (CDS) 08 Faculty of Science > Institute of Computer Science (INF) |
| Depositing User: | Admin importFromBoris |
| Date Deposited: | 25 Jan 2019 12:57 |
| Last Modified: | 25 Jan 2019 12:57 |
| URI: | https://boristheses.unibe.ch/id/eprint/826 |
Actions (login required)
 |
View Item |