Delay-sensitive user scheduling and power control in heterogeneous networks

Delay-sensitive traffic services, such as live streaming video, voice over IP and multimedia teleconferencing, requires low end-to-end delay in order to maintain its interactive and streaming nature. In recent years, the popularity of delay-sensitive applications has been rapidly growing. In this study, the authors consider the delay-sensitive user scheduling and power control design for heterogeneous networks (HetNets). They model the problem as an infinite-horizon average cost Markov decision process MDP. Based on the dynamics of channel state information (CSI) and queue state information (QSI), they focus on finding an adaptive user scheduling and power control policy to minimise the average delay of network subjected to the power constraints of heterogeneous base stations. In order to reduce the computational complexity and facilitate the distributive implementation, the authors derive a distributive stochastic learning algorithm which only requires local CSI and local QSI to determine the optimal user scheduling and power control policy. The simulation results confirm that significant delay performance gain can be achieved compared with various baseline schemes.