Packet loss

About: Packet loss is a research topic. Over the lifetime, 21235 publications have been published within this topic receiving 302453 citations.

Transport and display mechanisms for multimedia conferencing across packet-switched networks

Abstract: A transport protocol that supports real-time communication of audio/video frames across campus-area packet switched networks is presented. It is a “best effort” protocol that attempts to ameliorate the effect of jitter, load variation, and packet loss, to provide low latency, synchronized audio and video communications. This goal is realized through four transport and display mechanisms, and a real-time implementation of these mechanisms that integrates operating system services (e.g., scheduling and resource allocation, and device management) with network communication services (e.g., transport protocols), and with application code (e.g., display routines). The four mechanisms are: a facility for varying the synchronization between audio and video to achieve continuous audio in the face of jitter, a network congestion monitoring mechanism that is used to control audio/video latency, a queuing mechanism at the sender that is used to maximize frame throughput without unnecessarily increasing latency, and a forward error correction mechanism for transmitting audio frames multiple times to ameliorate the effects of packet loss in the network. The effectiveness of these techniques is demonstrated by measuring the performance of the protocol when transmitting audio and video across congested networks.

Non-intrusive monitoring of quality levels for voice communications over a packet-based network

Abstract: Provided is a method and apparatus for objectively and non-intrusively measuring voice quality on live calls without disrupting the call session or the network. A communication system includes plural communities each including a switch that controls access to a packet-based data network for call sessions. Each of the communities is coupled to the data network by respective packet-based trunks. Quality of service (QoS) monitoring devices are coupled to the respective packet-based trunks to monitor quality levels of routes between any two given communities. Each QoS monitoring device receives packets containing streaming data (which may be actual packets or test packets). From the received packets, the QoS monitoring device can derive QoS parameters, particularly for audio and speech signals on live calls without disrupting the call session.

Method and system for transferring data in a communications network using redundant communication paths

Abstract: A communication node of the present invention automatically transmits original and duplicate packets over different paths in a communications network to improve delivery reliability of the packet and to decrease packet delivery time. A packet is typically marked for reliable transmission by the application layer of a source node, while a routing agent module within the node IP layer processes the marked packets. The marked packets are transmitted over redundant (e.g., primary and secondary) network paths from the source node to the destination node. The primary path is usually the shortest path between the source and destination nodes, while the secondary path is selected to avoid overlap with the primary path. The application or transport layer of the destination node filters or removes plural copies of received packets.

Method and apparatus for packet network congestion avoidance and control

Abstract: There is provided a method for congestion control and avoidance in computer networks, which method includes the steps of sensing network congestion (including both sensing and predicting possible future network congestion) and allowing a network node to transmit at least one basic data segment and thereafter to transmit additional data, the quantity of said additional data being a function of the basic data segment, wherein the size of the basic data segment is deteremined at least in part by the sensed network congestion. Prediction of possible future network congestion is possible, for example, by learning from a history of network load and/or by detecting an increase in the number of users or other indications. When possible future network congestion is predicted, the application of the methods and apparatus of the invention is operative to prevent the development of future congestion altogether or at least to limit the evolving severity level that such future congestion would have otherwise reached. Controlling the transmission rate of network nodes is an important technique to help prevent future congestion altogether and/or to limit the severity of such congestion. There is also provided an apparatus for congestion control and avoidance in computer networks.

Globally optimal uneven error-protected packetization of scalable code streams

Abstract: In this paper, we present a family of new algorithms for rate-fidelity optimal packetization of scalable source bit streams with uneven error protection. In the most general setting where no assumption is made on the probability function of packet loss or on the rate-fidelity function of the scalable code stream, one of our algorithms can find the globally optimal solution to the problem in O(N/sup 2/L/sup 2/) time, compared to a previously obtained O(N/sup 3/L/sup 2/) complexity, where N is the number of packets and L is the packet payload size. If the rate-fidelity function of the input is convex, the time complexity can be reduced to O(NL/sup 2/) for a class of erasure channels, including channels for which the probability function of losing n packets is monotonically decreasing in n and independent erasure channels with packet erasure rate no larger than N/2(N + 1). Furthermore, our O(NL/sup 2/) algorithm for the convex case can be modified to rind an approximation solution for the general case. All of our algorithms do away with the expediency of fractional bit allocation, a limitation of some existing algorithms.