A Scheme of Resource Allocation for Heterogeneous Services in Peer-to-peer Networks using Particle Swarm Optimization

摘要

This paper considers reasonable resource allocation for heterogeneous services in peer-to-peer (P2P) networks, and presents a utility maximization model for bandwidth allocation of service providers. We firstly consider elastic services with concave utility functions and find that the optimal bandwidth allocation exists. Then we focus on heterogeneous services, where inelastic services with sigmoidal utility functions are coexisting with elastic services. The resource allocation model for heterogenous services is an intrinsically difficult problem of nonconvex optimization, resulting in difficulty of traditional gradient-based algorithm to obtain the optimum. In order to overcome it, we apply Particle Swarm Optimization (PSO) to revolve the model, propose a heuristic algorithm for resource allocation, and verify the results with simulation results.