An active queue management method for real-time streaming
A technology of active queue management and real-time streaming, which is applied in the field of communication networks and can solve problems such as lack of robustness and sensitive parameters
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0036] Such as figure 2 and image 3 As shown, the simulation experiment of the present invention is carried out under the UMTS environment provided by EURANE in NS2. N servers are located in the wired network, and respectively establish data connections with N wireless terminals UE, and R1 and R2 form the wired network. BS / AP means base station / wireless access point, the wireless link bandwidth is 2Mbps, and the average byte error rate is set to 3.5×10-5. Since N UEs share the wireless bandwidth, the wireless link becomes a bandwidth bottleneck. Therefore, in the experiment, the active queue management algorithm is deployed at the BS / AP, and the rest of the network nodes use Drop-Tail routers. The experiment obtains different degrees of delay performance requirements and system loads by setting different preset retention delays D0 and the number of connections N. The smaller D0 means the higher the delay performance requirements, and the larger N means the heavier the syst...
Embodiment 2
[0044] Such as figure 1 As shown, the present invention proposes a kind of active queue management method that is applied to real-time stream transmission, and this method comprises the steps:
[0045] Step 1: Use queuing theory to study the queuing system with rate adjustment, and obtain the relationship between system parameters and performance. The specific steps are:
[0046] i. Expand the queuing system with rate adjustment, the buffer output rate μ value is no longer limited to 1 (that is, it can be any integer value), the sending end adjusts the packet sending intensity according to the feedback queue length, and the system time is discretized.
[0047] ii. Use the time-discrete first-order Markov chain to theoretically analyze the performance parameters of the system. It mainly analyzes the performance of the queuing system in terms of average queue length, queue length change, overflow probability and underflow probability.
[0048] iii. Realized the influence of th...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


