| 摘要: | 壅塞控制技術一直是網路相關研究的重要議題，尤其在網路的視訊串流的研究上，隨著網路的普及以及使用費用的日趨平價，網路服務已不再局限於大公司、公家機關或是大專院校，更進一步深入家庭。也因此各種基於一般消費者的網路服務接踵推出。而最受矚目的不外是多媒體影音服務。且網路的先天架構較傳統廣播媒體更能夠無遠弗屆的服務使用者，並將使用的費用及限制降至最低。 為了將多媒體服務藉由現在的網路環境播送到家戶，目前所最常用網路通訊協定不得不做進一步的改善，而其重者尤以改善傳輸層的通訊協定。目前網路傳輸層通訊協定是以服務資料傳送為主，旨在保證資料傳輸的正確完整。但相較於資料傳輸，多媒體傳輸更強調即時性。藉由新穎的影音壓縮技術，多媒體傳輸可以容忍少量的封包遺失，但對於影音資料接收的平穩需求卻更為急迫，而影響傳輸平穩的重要因素之一就是所取得的傳送頻寬，以視訊串流為例，當頻寬不足時延遲的封包被丟棄，丟棄的封包除了浪費頻寬更會進一步延遲隨後送出的封包。而針對傳輸平穩的需求，學者們提出目前所最廣泛使用的流量壅塞控制技術TFRC。 TFRC除了平順的傳輸外最大特色便是具有TCP Friendly，TCP Friendly 的特色即是在與傳統資料傳輸協定，如TCP傳輸協定競爭頻寬時並不會產生不公平競爭的現象，也就是當一個TCP與TFRC連線在競爭頻寬時，TFRC會保持著與TCP連線相近的傳輸速率，而不會持續增加傳輸速度而壓迫其他的TCP連線，這種特性是基於TFRC能藉由偵測封包遺失而持續感知網路壅塞，進一步去推估，若存在一個TCP連線與本身競爭相同瓶頸頻寬時，調整本身的傳輸速度同於該被推估的TCP連線之平均傳送速度。但此特性相對也抑制TFRC的傳輸效能，也就是說當利用TFRC傳送多媒體串流服務，TCP Friendly的特性使得傳輸多媒體串流與一般的TCP資料連線競爭頻寬時過於保守，忽略的資料傳輸與多媒體傳輸先天需求的差異卻齊頭式平等，使得透過TFRC傳輸的多媒體串流效能無端減弱。這種問題在無線網路多媒體傳輸更為嚴重。 在無線網路的環境下的封包遺失，除了來自網路壅塞之外更會因為不良的無線網路訊號而導致封包遺失。此時傳統通訊協定，如TCP、TFRC等，會因為壅塞控制的誤判導致傳輸效能嚴重下降。這種現象除了弱化多媒體傳輸品質外更嚴重浪費頻寬。隨著無線網路的普及、傳輸速率的大幅度進展以及使用費用的降低，各種無線網路營運供應商如雨後春筍般出現，為了吸引使用者增加其收益，莫不以提供無線多媒體服務為其主要訴求。而妥善運用其網路資源成為網路營運商首重考量之一。但是TFRC的保守性與無線網路而造成的效能低落成為無線網路營運上的需要立即克服的重要問題。 為了解決網路壅塞造成的傳輸效能低落，學者提出可用頻寬估測的概念。以現今網路而言所有傳輸資料的長期來看是穩定的，也因此觀測傳輸路徑中瓶頸頻寬的變化足以顯示該傳輸路徑網路壅塞的變化。基於這個觀察我們提出了JitterPath這個可用頻寬估測的方法，相較於其他具代表性的可用頻寬估測方法而言，JitterPath具有端對端、快速且準確的特性。也因此不需要網路節點配合即可準確估測網路可用頻寬。 可用頻寬的概念，除了做為網路測量工具之外，更可以用在提升通訊協定的效率之上。基於JitterPath的基礎，我們提出新傳輸層通訊協定，包含可以提升傳統TCP通訊協於無線網路下的效能的EJTCP以及針對多媒體及無線網路傳輸特性所提出改良TFRC通訊協定的OWDJ-TFRC，為完整的通訊層協定的無線網路多媒體解決方案。 TCP is the most important and widely used transport protocol at present. With the advent of advanced wireless broadband technologies, TCP must be tuned and enhanced from traditional networks made up of purely wired links to wired-cum-wireless networks. As a result of high bit error rate (BER) in wireless links, TCP halves down its congestion window unnecessarily caused by random packet loss event continuously, and the performance is significantly degraded in wireless networks. The problem about differentiating congestion loss and random loss has been investigated recently by a number of schemes. Wireless TCP solutions, such as JTCP (jitter-based TCP) improve TCP performance for wireless networks. However, even if the enhanced solutions make efforts to distinguish packet losses, some unavoidable events may occur to make TCP timeout frequently. Hence, we amend JTCP scheme to design a smooth transmission scheme to increase the correctness of loss distinction and avoid bursty transmission. To have better transport performance, we design enhanced JTCP to provide better performance in sending data traffic under wire-cum-wireless environment. However, JTCP only have good performance in data traffic but multimedia traffic. For example, video streaming. Rate-based congestion control is an important issue for advanced video streaming. The widely adopted rate based congestion control scheme is TFRC. According to TCP-friendly rate estimation mechanism, TFRC can provide smooth perceptual quality in video streaming. However, video streaming needs not only smooth rate control but also higher priority in competing network bandwidth. Compare to data traffic, video streaming has minimum bandwidth requirement issue, however, data traffic only cares about integrity. If video streaming can not acquire network bandwidth in time, outdated video streaming packets will be dropped and network bandwidth wasted. In a word, TFRC is too conservative while it transmits video streaming service. Measurement of end-to-end available bandwidth has received considerable attention due to its potential use in improving QoS. Available bandwidth enables the sending rate to adapt to network conditions, so that packet loss, caused by congestion, can be significantly reduced before error control mechanisms are finally employed. To this end, we propose a probing noise resilient available bandwidth estimation scheme, called JitterPath, which is adaptive to both the fluid and bursty traffic models. Two key factors, one-way delay jitter and accumulated queuing delay, are both exploited to predict the type of queuing region for each packet pair. Then, the bottleneck utilization information included in the joint queuing regions is estimated and used to quantify the captured traffic ratio, which indicates the relationship between the probing rate and available bandwidth. The contributions of our method are as follows: (1) JitterPath can work without being restricted to fluid traffic models; (2) since JitterPath does not directly use the bottleneck link capacity to calculate the available bandwidth, it is feasible for use in a multi-hop environment with a single bottleneck; (3) JitterPath inherently reduces the impact of probing noises under the bursty cross traffic model. Extensive simulations, Internet experiments, and comparisons with other methods were conducted to verify the effectiveness of our method under both single-hop and multi-hop environments. Before deeply discuss available bandwidth, we need to understand the major traffic in the Internet and the problem while it applied in wireless environment. Beside issue of conservation, TFRC will malfunction in wireless environment if packet lost events were introduced by wireless channel loss but network congestion. Some State-of-arts try to utilize delay measurement to distinguish channel loss from observed packet loss events. However, these approaches do not take care the measurement noise came from background traffics. The bursty nature of background traffic breaks relationship between the delay measurement and congestion. To solve this issue, we proposed a new one-way delay jitter based method, OWDJ-TFRC, to achieve above two goals in wired-cum-wireless network. Simulation results also show that our method conducts performance improvement without intrusiveness issue under bursty background traffic in wire-cum-wireless network. |
