In mobile wireless systems, the data on air can be accessed by a large number of mobile clients. The organization of data on wireless channels, which aims to reduce the access time of clients, is a key problem in data broadcast systems. Existing algorithms for periodic data broadcasts generally make assumptions that the clients' queries are already known and/or the distribution of access frequencies of these queries can be obtained in advance. However, the assumptions are not realistic in real life. In this paper, we study the scheduling problem of periodic XML data broadcast and demonstrate that when scheduling XML data in this context, these assumptions are unnecessary. Then taking the structural similarity between XML documents into account, a novel cluster-based scheduling algorithm for periodic XML data broadcast is also proposed. Finally, we study the performance of our scheduling algorithm through a set of experiments. The results show that our scheduling algorithm can significantly improve access efficiency.udud
展开▼
