Data caching issues in an information retrieval system
ACM Transactions on Database Systems (TODS)
Scheduling algorithms for modern disk drives
SIGMETRICS '94 Proceedings of the 1994 ACM SIGMETRICS conference on Measurement and modeling of computer systems
Balancing push and pull for data broadcast
SIGMOD '97 Proceedings of the 1997 ACM SIGMOD international conference on Management of data
Joint broadcast scheduling and user's cache management for efficient information delivery
MobiCom '98 Proceedings of the 4th annual ACM/IEEE international conference on Mobile computing and networking
Scheduling on-demand broadcasts: new metrics and algorithms
MobiCom '98 Proceedings of the 4th annual ACM/IEEE international conference on Mobile computing and networking
An optimality proof of the LRU-K page replacement algorithm
Journal of the ACM (JACM)
Adaptive Data Broadcast in Hybrid Networks
VLDB '97 Proceedings of the 23rd International Conference on Very Large Data Bases
Broadcast Scheduling for Information Distribution
INFOCOM '97 Proceedings of the INFOCOM '97. Sixteenth Annual Joint Conference of the IEEE Computer and Communications Societies. Driving the Information Revolution
Impact of Applying Aggregate Query Processing in Mobile Commerce
International Journal of Business Data Communications and Networking
Hi-index | 0.00 |
Broadcast scheduling algorithms have received a lot of attention recently, since they are important for supporting mobile/ubiquitous computing. However, a comprehensive system's perspective towards the development of high performance broadcast servers is very much lacking. With this paper we attempt to fill this gap. We contribute four novel scheduling algorithms that ensure the proper interplay between broadcast and disk scheduling in order to attain high performance. We study comprehensively the performance of the broadcast server, as it consists of the broadcast scheduling and the disk scheduling, algorithms. Our results show that the contributed algorithms outperform the algorithms, which currently define the state of the art. Furthermore, one of our algorithms is shown to enjoy considerably higher performance, under all values of the problem and system parameters (such as the skew of access distributions, the system load, the data object sizes, cache-and disk-intensive workloads, etc.). An important conclusion of this study is that broadcast scheduling algorithms have only a small effect on the overall broadcast system performance, a fact that necessitates the refocusing of related research.