Predictive flow control for TCP-friendly end-to-end real-time video on the Internet

Sun, Yeali S.; Tsou, Fu-Ming; Chen, Meng Chang

doi:10.1016/s0140-3664(02)00002-6

Cited by 3 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The recursive-least-squares (RLS) algorithm is an adaptive filter algorithm that is simple and computationally efficient. The RLS algorithm has been widely used in control and communications applications, such as MPEG traffic prediction, handoff resources prediction, RTT prediction, and packet loss probability prediction ( [7], [8]). Because network traffic is highly dynamic, it is desirable to have an algorithm that can adapt quickly.…”

Section: Bandwidth Predictionmentioning

confidence: 99%

Dynamic bandwidth reservation scheme in 802.11 and 802.16 interworking networks

Tung

Sun

Chen

2011

2011 IEEE Wireless Communications and Networking Conference

Self Cite

View full text Add to dashboard Cite

One of the most popular applications of IEEE 802.16 network is to serve as a backhaul service for IEEE 802.11 networks. However, the traffic of an IEEE 802.16 connection aggregated from IEEE 802.11 networks fluctuates. Thus, efficient bandwidth reservation at the subscriber station (SS) is an importance issue. This study proposes a simple and flexible bandwidth reservation scheme at the SS, called multi-stage selfcorrection bandwidth reservation (MSBR), to make effective use of the bandwidth without violating the QoS requirements for real-time traffic under the proposed cost model. The MSBR scheme introduces the concept of Decision Period for bandwidth reservation to reduce the control message overheads. The proposed method also adopts the RLS algorithm to predict the traffic arrival and applies the MSBR method to capture the traffic dynamics for bandwidth reservation. Simulation results demonstrate that the proposed MSBR scheme utilizes the bandwidth efficiently without violating the QoS requirements of real-time services.

show abstract

Section: Bandwidth Predictionmentioning

confidence: 99%