Ethernet continues to be one of the most popular LAN technologies. Due to the low price and robustness resulting from its wide acceptance and deployment, there has been an attempt to build Ethernet-based real-time control networks for manufacturing automation. However, it is di cult to build a realtime control network using the standard UDP or TCP/IP and Ethernet, because the Ethernet MAC protocol, the 1-persistent CSMA/CD protocol, has unpredictable delay c haracteristics. When both real-time (RT) and non-real-time packets are transported over an ordinary Ethernet LAN, RT packets from a node may experience a large delay due to (i) contention with non-RT packets in the originating node and (ii) collision with RT and non-RT p a c kets from the other nodes. To resolve this problem, we designed, implemented, and evaluated adaptive tra c smoothing. Speci cally, a tra c smoother is installed between the UDP or TCP/IP layer and the Ethernet MAC l a yer, and works as an interface between them. The tra c smoother rst gives RT p a c kets priority o ver non-RT ones in order to eliminate contention within each local node. Second, it smooths a non-RT stream so as to reduce collision with RT packets from the other nodes. This tra c smoothing can dramatically decrease the packet-collision ratio on the network. The tra c smoother, installed at each node, regulates the node's outgoing non-RT stream to maintain a certain tra c-generation rate. In order to provide a reasonable non-RT throughput, the tra c-generation rate is allowed to adapt itself to the underlying network load condition. This tra c smoother requires only a minimal change in the OS kernel without any modi cation to the current standard of Ethernet MAC protocol or the TCP or UDP/IP stack.We h a ve implemented the tra c smoother on both the Linux and the Windows NT platforms, demonstrating signi cant reduction of the RT p a c ket deadline-miss ratio when both RT and non-RT packets are transported over the same Ethernet. More precisely, installation of the proposed tra c smoother on every node is shown to reduce the RT message deadline-miss ratio by t wo orders of magnitude under a heavily-loaded condition, while lowering the non-RT throughput only by h a l f .
AbstractÐUnlike deterministic real-time communication in which excessive resources may be required for ªabsoluteº performance guarantees, statistical real-time communication seeks to achieve both probabilistic performance guarantees and efficient resource sharing. This paper presents a framework for statistical real-time communication in ATM networks, providing delay-guaranteed transport of MPEG-coded video traffic with a statistically-guaranteed cell-loss ratio. Delay-guaranteed communication is achieved with a modified version of Traffic-Controlled Rate-Monotonic Priority Scheduling (TCRM). A set of statistical real-time channels that share similar traffic characteristics are multiplexed into a common macrochannel. Those statistical real-time channels which are multiplexed together share the resources of a macrochannel, and individual statistical real-time channels are given timeliness and probabilistic cellloss guarantees. A macrochannel is serviced by the modified TCRM which improves link utilization and makes channel management simpler. Based on the analysis of an wahaIax queueing system, we propose a procedure for determining the transmission capacity of a macrochannel necessary to statistically guarantee a cell-loss ratio bound. Our extensive trace-driven simulation has shown the superiority of the proposed framework to the other approaches. The overall cell-loss ratios for multihop statistical real-time channels are shown to be smaller than the predetermined bounds, thus verifying our analytical results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.