An Empirical Study of the Multiscale Predictability of Network Traffic
HPDC '04 Proceedings of the 13th IEEE International Symposium on High Performance Distributed Computing
Computer Networks: The International Journal of Computer and Telecommunications Networking
Limits to consistent on-line forecasting for ergodic time series
IEEE Transactions on Information Theory
Predictive dynamic bandwidth allocation for efficient transport of real-time VBR video over ATM
IEEE Journal on Selected Areas in Communications
Hi-index | 0.00 |
We consider the design of Demand Assigned Multiple Access (DAMA) algorithms that efficiently utilize limited RF uplink resources for packet switched military satellite communication networks. In previous work, we designed DAMA algorithms that optimized link layer efficiency and throughput while controlling delay and jitter. In this work we assess the ability of our DAMA algorithm to meet Service Level Agreements (SLA) between the Network Management System and the terminals. We evaluate the ability of four DAMA algorithms to provide terminals Committed Information Rates (CIR) under various system loading conditions. The designs have increasing levels of confidence in the accuracy of the predicted demand. Results show that although traffic demand cannot be predicted precisely, current demand provides insight into future demands and that this information can be used to more efficiently provide CIR guarantees to terminals.