Fowler+Leland_JSAC_91 - -1- Local Area Network Trafc...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
-1- Local Area Network Traffic Characteristics, with Implications for Broadband Network Congestion Management Henry J. Fowler Will E. Leland Bellcore Bellcore 331 Newman Springs Road 445 South Street Red Bank, NJ 07701 Morristown, NJ 07962 Abstract This paper examines the phenomenon of congestion in order to better understand the congestion management techniques that will be needed in high-speed, cell-based networks. The first step of this study is to use high time-resolution local area network (LAN) traffic data to explore the nature of LAN traffic variability. Then, we use the data for a trace-driven simulation of a connectionless service that provides LAN interconnection. The simulation allows us to characterize what congestion might look like in a high-speed, cell-based network. The most striking aspect of the LAN data is the extreme traffic variability on time scales ranging from milliseconds to months. Conventional traffic models do not capture this behavior, which has a profound impact on the nature of traffic congestion. When our realistic data is applied to simple models of LAN interconnection, we observe that: g During congested periods, congestion persists and losses can be significant. g Congestion losses cannot be avoided by modest increases in buffer capacity. g The consequences of misengineering can be serious. g Fortunately, most congested periods are preceded by signs of impending danger. 1. Introduction Technological advances and customer demands are rapidly ushering in public high-speed packet switched networks. The target network for high-speed, high-bandwidth communication is the Broadband Integrated Services Digital Network (BISDN). [1] BISDN ultimately will offer a wide range of new services exhibiting many varied traffic characteristics that complicate congestion management. To address these concerns, one must first understand the nature of congestion itself. This paper examines some forms of congestion that may arise in BISDN. Considerable effort has been, and continues to be, devoted to understanding the congestion management needs of BISDN. Some efforts focused on particular aspects of the problem, such as algorithms for discarding Asynchronous Transfer Mode (ATM) cells. [2] [3] Others examined performance issues, such as the effects of non-random cell arrivals on switch design. [4] Still other efforts have been devoted to developing an overall structure for studying congestion management in BISDNs. [5] [6] While defining congestion management approaches is extremely important work, the nature of the congestion to be managed remains almost completely unknown. It is difficult to forecast how congestion will arise in a BISDN, because we do not yet know which services will be offered and which will contribute a significant portion of the BISDN traffic. In addition, the traffic characteristics of many new services, such as video, are poorly known. While we cannot describe the congestion behavior of all possible future services, this paper characterizes the congestion behavior that may be induced by
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 09/13/2009 for the course EE 6345 taught by Professor Cantrell during the Spring '09 term at University of Texas at Dallas, Richardson.

Page1 / 20

Fowler+Leland_JSAC_91 - -1- Local Area Network Trafc...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online