Loading...
Please wait, while we are loading the content...
Similar Documents
Aalborg Universitet Peer-Assisted Content Distribution with Random Linear Network Coding
| Content Provider | Semantic Scholar |
|---|---|
| Author | Hundeboll, Martin Ledet-Pedersen, Jeppe Sluyterman, Georg Madsen, Tatiana K. |
| Copyright Year | 2013 |
| Abstract | Peer-to-peer networks constitute a widely used, cost-effective and scalable technology to distribute bandwidth-intensive content. However, the majority of todays peer-to-peer systems require complex algorithms to schedule what parts of obtained content to forward to other peers. Network Coding (NC) has been proposed as a method for optimizing this scheduling and previous work supports that a gain in overall throughput may be possible. Networks that apply NC differs from store-and-forward networks by distributing content as a linear combination of received packets. In this paper we propose the structure of the BRONCO peer-to-peer system, which applies random linear network coding. To support simulation results in related studies, we focus on experimental evaluation of performance. Our protocol is implemented using coding in the binary Galois field, which is computationally efficient compared to coding in higher order fields. The overlay network is easy to establish and nodes communicate using a simple protocol. We show that BRONCO outperforms regular HTTP transfers and is, even with a simple protocol, comparable with BitTorrent. Furthermore, we evaluate the performance of different coding parameters and suggest a suitable trade-off between CPU utilization and network overhead. Within the limitations of the used test environment, we have shown that NC is usable in peer-assisted content distribution and we suggest further improvements to reduce redundancy overhead. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | https://vbn.aau.dk/ws/files/182202006/paper.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |