Skip to content
Free planNo credit card requiredStart writing

article · 2005

Multiclass P2P Networks: Static Resource Allocation for Service Differentiation

Florence Clévenot-perronnin, Keith W. Ross

Cited by 0Abstract and details only

Abstract

We propose a multiclass fluid model for BitTorrent-like content distribution systems. The new model can model heterogeneous peers, in which peers have different access bandwidths. The model can also model BitTorrent-like systems which provide differential service (for example, first class and second class service) to the participating peers. The fluid model leads to a non-linear system of differential equations with special structure. For the service differentiation problem, we prove that the system of differential equations admits a unique stable equilibrium, that we compute in closed-form. We also give the average download times for both classes. For the bandwidth diversity problem, we show that the system of differential equations has a stable state that may depend on the initial conditions. We give the average download time of both classes for each reachable steady-state.

Cite this paper

APA 7

Clévenot-perronnin, F., & Ross, K. W. (2005). Multiclass P2P Networks: Static Resource Allocation for Service Differentiation.

MLA 9

Clévenot-perronnin, Florence, and Keith W. Ross. “Multiclass P2P Networks: Static Resource Allocation for Service Differentiation.” 2005.

Chicago

Clévenot-perronnin, Florence, and Keith W. Ross. 2005. “Multiclass P2P Networks: Static Resource Allocation for Service Differentiation.”

Harvard

Clévenot-perronnin, F. and Ross, K.W. (2005) ‘Multiclass P2P Networks: Static Resource Allocation for Service Differentiation’.

BibTeX
@article{clevenotperronnin2005multiclass,
  title = {{Multiclass P2P Networks: Static Resource Allocation for Service Differentiation}},
  author = {Clévenot-perronnin, Florence and Ross, Keith W.},
  year = {2005}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.