高速多媒體網路中提供多重服務品質之智慧型訊務控制器

Abstract

近年來，網際網路的人口急速增加。網際網路上的應用從數據資料到語音及影像，各種應用所需要之服務品質要求也不同。非同步傳輸模式(ATM)具有整合各種通訊服務的能力，故被採用為高速網路整合各種應用服務的關鍵技術。因為訊務的多樣性及所要求的服務品質不同，ATM 需要一個精巧且即時的訊務控制器來確保所有線上用戶的服務品質，並且希望能進一步提高整體網路的使用效益。 智慧型控制機制在這幾年來被廣泛應用在許多訊務控制相關的問題上。根據研究顯示，智慧型控制機制比傳統的方法有更好的表現。因此我們採用智慧型控制技術去實現高速網路上所需的訊務控制器。 在此篇論文中，我們提出了一個不但能保障封包漏失率(cell loss ratio)，也能使封包延遲變異(cell delay variation)降低的智慧型訊務控制器，其中包括了呼叫允諾控制器與壅塞控制器。除此之外，我們也藉由即時線上學習的機制來增加此訊務控制器在應用環境改變時的調適能力。我們所提出的智慧型訊務控制器可提供較多種類的服務品質保障，並且對不同應用環境也有較高的調適力，所以不僅對於所有目前已存在的應用，甚至是將來可能會出現的未知應用，都能在服務品質上獲得保障。

In recent years, the number of Internet people grows rapidly. Internet applications are ranging from non-real time data services to real-time audio and video service, which need different quality of service (QoS) requirements. Asynchronous transfer mode (ATM) has been proposed as one of the techniques to integrate diverse application services for high speed networks. Because of diverse traffic sources and associated QoSs, an ATM network requires a sophisticated and real-time traffic controller to guarantee QoSs for existing calls and to achieve high system utilization. Recently, intelligent techniques (e.g. neural network, fuzzy logic) have been widely applied to deal with traffic control related problems in ATM networks. Research results showed that intelligent techniques had better performance than conventional schemes. In this thesis, we propose an intelligent traffic controller (ITC) with multiple QoSs including cell loss ratio (CLR) and cell delay variation (CDV). The ITC mainly consists of connection admission control (CAC) and congestion control (CC). In addition, we propose an on-line learning scheme to improve robustness of the ITC. Due to providing multiple QoSs and robustness, the ITC can support all existing network applications as well as those with yet unknown characteristic that would emerge in future.