OCSM: an optimized channel split method—towards real-time and on-demand data broadcast scheduling

Abstract

In recent years, it has been witnessed a boom in the development of mobile networks and a great increase in the computing ability of mobile devices. The rapid booming in client requests lead to some new challenges for real-time on-demand data broadcasting: (1) the dynamic diversity of the data characteristics; (2) the dynamic diversity of real-time clients’ demand greatly increase the volume of hot-spot data (the most access data); and (3) the clients’ demands for high service quality. To date, the current research has focused on the fixed-channel models (i.e. the bandwidth and number of channels are unchangeable) and algorithms. To adapt to the characteristics of the real-time requests, an optimized channel split method (OCSM) is proposed for automatic channel split and data allocation in this paper. The experiments undertaken in this study included two aspects: (1) determining the different strategies under different data sizes and deadlines; and (2) verifying the validity of the automatic channel split and data allocation through a series of experiments with the general performance matrics. The results show that the proposed method outperforms some of the state-of-the-art scheduling algorithms.