Admission control for P2P-based Media Delivery Network

With wider application of P2P-based Media Delivery Network (P2P-based MDN), much work has been done to improve the system´ performance and efficiency in the process of media contents sharing. In this paper, we first propose a specific partially observable Markov Decision Process (POMDP) model for admission control of P2P-based MDN. Based on this model, we provide the observation-based randomized policy to conduct admission control and optimize the policy by applying policy-gradient algorithm. Observation-based policy can promote the system´s performance in real time aspect and policy optimizing can increase the accuracy of controller´s judgments based on partial information. Admission strategy in the paper can save the cost in operating the system for media service providers. Bandwidth allocation policy is designed to reduce service delay and provide high-quality service. The comparison results of system´s performances under different policies indicate that, partial service can utilize the system´s resource in a better way.