Resource allocation strategies in hybrid delay/blocking wireless systems

This paper presents an analysis of strategies for allocating resources to data users in a hybrid blocking/delay queueing system, applicable for modelling a wide range of wireless networks. Real-time voice traffic operates under a blocked calls cleared regime while non-real-time data is delayable. These traffic types compete on a first come first served basis for a fixed number of servers. Voice traffic uses a single server and data uses multiple servers while operating under a combination of server reduction and server sharing. Reduction allows the allocation of multiple servers to a data call to be adapted to the available spare servers, while sharing allows further adaptation by bringing multiple enqueued data calls into service. All combinations of these schemes are studied. Voice and data calls are modelled as Poisson arrivals with exponential holding times, and the resulting Markov process is analysed using a stochastic simulation of the state space. The results presented demonstrate the trade-offs on the performance of real-time voice and delayable data traffic. In particular, both the "reduction" and "fair sharing" achieve greater system utilisation and smaller data queue delay, using the same basic philosophy - pushing more data calls into the service facility, rather than keeping them in the queue.