Event-related optimization for a class of resource location with admission control

A class of resource location service for distributed VoD system, which combines one-hop k-random walk and global centralized indexing service, is studied. First, in order to minimizing the cost of communication and guaranteeing the response time performance, a Markov model is proposed to describe the queue phenomenon, admission control and the process of location. In this model, control is related with not only states but also events, which introduce more information as the control basis. Then, an optimization algorithm that combines policy gradient estimation and stochastic approximation is proposed. This algorithm can deal with constraints and depend on no system parameter. Finally, an illustrative simulation is performed to demonstrate the effectiveness of model and algorithm.