Correlation-based data broadcasting in wireless networks

A key element in many mobile application systems is the realization of efficient data delivery from server to mobile clients. Although broadcast has been proved to be an efficient data dissemination technique, selection of broadcast data is still an active research area. In this paper, we mainly studied the functions of the implicit regularities attached to clients' request data in the selection of broadcast data. Furthermore, we put forward a correlation-based broadcast model, which selects broadcast data items according to data access frequencies as well as their correlations. The primary rationale underneath is the fact that some data are prone to be accessed if certain data are reached. The results from extensive simulation experiments shows that the correlation-based broadcast can significantly improve the mean response time and reduce the number of client requests.