Efficient Broadcast Schedulers of Hierarchical Data Dissemination Systems

Abstract

With the increasing popularity of portable wireless devices and the need to access data anytime and anywhere, mechanisms to efficiently and effectively transmit information to wireless clients are of significant interest. Several research studies address broadcast scheduling algorithms for centralized systems. However, broadcast scheduling in hierarchical data dissemination systems are largely ignored. In these systems a primary server accepts updates that are broadcasted to secondary servers and then to wireless clients. This paper focuses on broadcast scheduling at the primary server side. First, we show that a straightforward broadcast scheduler that ignores clients' access patterns can provide participating clients with outdated information more than 80% of the time. Then, we propose three broadcast scheduling algorithms. The proposed algorithms primarily differ in how data broadcasts are guided at the primary and secondary servers. We present guidance mechanisms that are based on real and predicted clients' access patterns. We experimentally evaluate the proposed scheduling algorithms using simulation while running an extensive set of experiments. The performance study illustrates that the third proposed algorithm, which depends on predictive scheduling at both the primary and the secondary servers, provides the best performance in terms of the response time of the clients' requests and the reception of outdated information.