Showing papers on "Transmission delay published in 1986"

Transmission Range Control in Multihop Packet Radio Networks

Abstract: This paper presents a model for analyzing the performance of transmission strategies in a multihop packet radio network where each station has adjustable transmission radius. A larger transmission radius will increase the probability of finding a receiver in the desired direction and contribute bigger progress if the transmission is successful, but it also has a higher probability of collision with other transmissions. The converse is true for shorter transmission range. We illustrate our model by comparing three transmission strategies. Our results show that the network can achieve better performance by suitably controlling the transmission range. One of the transmission strategies, namely transmitting to the nearest forward neighbor by using adjustable transmission power, has desirable features in a high terminal density environment.

Packet Trains--Measurements and a New Model for Computer Network Traffic

Abstract: Traffic measurements on a ring local area computer network at the Massachusetts Institute of Technology are presented. The analysis of the arrival pattern shows that the arrival processes are neither Poisson nor compound Poisson. An alternative model called "packet train" is proposed. In the train model, the traffic on the network consists of a number of packet streams between various pairs of nodes on the network. Each node-pair stream (or node-pair process, as we call them) consists of a number of trains. Each train consists of a number of packets (or cars) going in either direction (from node A to B or from node B to A). The intercar gap is large (compared to packet transmission time) and random. The intertrain time is even larger. The Poisson and the compound Poisson arrivals are shown to be special cases of the train arrival model. Another important observation is that the packet arrivals exhibit a "source locality." If a packet is seen on the network going from A to B, the probability of the next packet going from A to B or from B to A is very high. Implications of the train arrivals and of source locality on the design of bridges, gateways, and reservation protocols are discussed. A numbet of open problems requiring development of analysis techniques for systems with train arrival processes are also described.

Waveform substitution techniques for recovering missing speech segments in packet voice communications

Abstract: Packet communication systems cannot, in general, guarantee accurate and prompt delivery of every packet. The effect of network congestion and transmission impairments on data packets is extended delay; in voice communications these problems lead to lost packets. When some speech packets are not available, the simplest response of a receiving terminal is to substitute silence for the missing speech. Here, we explore techniques for replacing missing speech with wave-form segments from correctly received packets in order to increase the maximum tolerable missing packet rate. After presenting a simple formula for predicting the probability of waveform substitution failure as a function of packet duration and packet loss rate, we introduce two techniques for selecting substitution waveforms. One method is based on pattern matching and the other technique explicitly estimates voicing and pitch. Both approaches achieve substantial improvements in speech quality relative to silence substitution. After waveform substitution, a significant component of the perceived distortion is due to discontinuities at packet boundaries. To reduce this distortion, we introduce a simple smoothing procedure.

Frequency-hop transmission for satellite packet switching and terrestrial packet radio networks

Abstract: The performance of frequency-hop transmission in a packet communication network is analyzed. Satellite multiple-access broadcast channels for packet switching and terrestrial packet radio networks are the primary examples of the type of network considered. An analysis of the effects of multiple-access interference in frequency-hop radio networks is presented. New measures of "local" performance are defined and evaluated for networks of this type, and new concepts that are important in the design of these networks are introduced. In particular, error probabilities and local throughput are evaluated for a frequency-hop radio network which incorporates the standard slotted and unslotted ALOHA channel-access protocols, asynchronous frequency hopping, and Reed-Solomon error-control coding. The performance of frequency-hop multiple access with error-control coding is compared with the performance of conventional ALOHA random access using narrow-band radios.

Broadcast packet switching network

Abstract: A high performance packet switching network that can be used to provide voice data and video communication on a large scale is disclosed. The packet switching network has a broadcast capability which makes it suitable for applications including commercial television distribution and conferencing. The basic switching capability of the network is provided by a switching module which is capable of producing a desired number of copies of a broadcast packet and routing the copied packets to desired destinations. A plurality of switching modules may be interconnected to form a packet switch. Interconnection circuitry is provided so that the number of interconnected switch modules may be varied with a minimum of recabling.

High-speed packet-switched communications system with end-to-end flow control and retransmission

Abstract: Disclosed is a packet switched communications system wherein a plurality of switching nodes serves a plurality of terminals through transmission links. Each of the terminals transmits a packet of data-link layer control protocol including a network-layer control protocol to an associated one of the switching nodes. Each of the switching nodes is responsive to the network control protocol of the packet for routing it to one of the transmission links defined by the network layer control protocol of the packet. The switching node includes a plurality of line controllers associated respectively to the transmission links. Each line controller appends a physical address of the packet at the defined transmission link to the packet and updates its network-layer control protocol with a logical address of the packet at the defined transmission link and sends it to the line controller associated with the defined transmission link by way of a switching network.

Waveform substitution techniques for recovering missing speech segments in packet voice communications

Abstract: Packet communication systems cannot, in general, guarantee accurate and prompt delivery of every packet. The effect of network congestion and transmission impairments on data packets is extended delay; in voice communications these problems lead to lost packets. This paper describes techniques for replacing missing speech with waveform segments from correctly received packets in order to increase the maximum tolerable missing packet rate. After presenting a simple formula for predicting the probability of waveform substitution failure as a function of packet duration and packet loss rate, we introduce two techniques for selecting substitution waveforms. One method is based on pattern matching and the other technique explicitly estimates voicing and pitch. Both approaches achieve substantial improvements in speech quality relative to silence substitution.

Protocol for handling transmission errors over asynchronous communication lines

Abstract: A system or scheme for automatic detection of and recovery from transmission errors in the asynchronous communication mode at the data link level with complete transparency at the higher levels is disclosed wherein the transmissions are in the form of a sequence of data packets, and an improved combination of end-of-text (ETX) bytes along with checksums is used in each data packet to detect errors The ETX character is dynamically selected for each packet after the data comprising the packet has been assembled This character is coded differently from the remaining character codes in its respective packet and is made the second byte thereof following the start-of-text byte (STX) The third byte in each packet is made the complement of the preceding ETX byte, the latter of which is also made the last byte in the packet Thus, the second and last bytes in each packet are identical, and different from all the other bytes, and the third byte is their complement Other bytes in each packet include: one byte indicating the location of the packet in a set in a given transmission sequence; a byte distinguishing the packet's set from other transmission sequences; two bytes indicative of the number of data bytes in the packet; one byte operating as a control character indicating the functional nature of the packet; data bytes; and, two checksum bytes which precede the last ETX byte Among the advantages of transmissions using packets containing the foregoing improved combination of bytes, is the fact that all transmission errors will be detected and upon detection of an error in a packet, the transmitter is immediately notified and retransmission is carried out only from the erroneous packet rather than from the beginning of the entire sequence as in the prior art

Reliable synchronous inter-node communication in a self-routing network

Abstract: A communication method and packet switching network (101) in which self-routing packets are communicated among stages of switching nodes via inter-stage links (204-215) whereon data of the packets is transmitted in one direction (210) and the packet clocking signals are transmitted in the other direction (211). Upon having the capability to accept a packet from one of the interstage links, a switch node transmits the packet clock signals to the upstream stage connect to that link indicating the present capacity to accept a packet. Furthermore, each switch node after receiving the end of a packet from an upstream stage waits for a predefined duration of time before commencing the transmission of the packet clocking signals. That delay allows the transmitting switch node i the upstream stage to determine that the link and downstream node are functioning correctly since continued transmission of the packet clock signals indicates that the packet had not been received or that downstream node had incorrectly responded to receipt of the packet. If a malfunction is detected, an error indication is transmitted to the computer controlling the switching network.

Delay circuit for a monolithic integrated circuit and method for adjusting delay of same

Abstract: A delay circuit that can be implemented in a monolithic integrated circuit includes a plurality of capacitor/laser-fusible link series pairs. Delay of a binary output signal of the circuit with respect to an input transition is directly proportional to the amount of capacitance connected into the circuit. Because the laser-fusible links can selectively be opened with a laser, the amount of capacitance connected into the circuit can incrementally be reduced; thus, the delay of the circuit is reducibly adjustable to a desired value. By including a plurality of conductive element/laser-fusible link series pairs in the delay circuit, the delay of the circuit is also increasingly adjustable. A method for economically adjusting the delay of each of many like delay circuits embodied in a semiconductor wafer includes measuring a sample of the delays of the delay circuits, calculating an average delay, determining the difference between a desired delay and the average delay to determine an incremental amount of delay to eliminate or to add, determining from predetermined data which fusible links should be opened, and using a laser beam to open the appropriate links.

Composite data transmission system

Abstract: A composite data transmission system wherein packet switching stations adapted to transmit data of the kind for which transfer delay and periodicity do not matter and operated to detect collisions between packets in the light of alterations in the DC voltage level of packet signals and circuit switching stations adapted to transmit data of the kind requiring periodic transmission are connected to one and the same transmission line, which composite data transmission system is characterized by causing DC voltage signals of a fixed magnitude to flow with prescribed periods through the transmission line thereby enabling the packet switching stations to recognize collisions and permitting the circuit switching stations to exchange communication during the existence of the packet switching stations' recognition of collisions and permitting the packet switching stations to exchange communication during the absence of the DC voltage signals' flow.

Synchronized multiple access apparatus and method for a local area network

Abstract: The present access protocol for contention networks results in synchronous network operation. Each node determines the next transmission instant by counting from the beginning of the most recently received packet of information a time equal to that packet's labeled length minus the previously measured round trip propagation delay seen by the node. Subsequent instants will occur at intervals equal to the maximum propagation delay allowed on the network. Each time a subsequent packet is received, synchronization is rederived based on the packet. If no packets are received within predetermined slots, the network is considered to be in asynchronous mode, with transmissions allowed at any time following the next slot. The disclosed packet synchronized multiple access (PSMA) protocol improves the performance measures by which local area networks are evaluated.

System for controllably eliminating bits from packet information field based on indicator in header and amount of data in packet buffer

Abstract: Buffer memory overflow control is realized by controlling the amount of packet data being inputted to the buffer memory in response to the amount of packet data stored in the buffer memory. Depending on the type of coding being employed and the amount of data stored in the buffer memory, one or more groups of bits are controllably dropped from the packet information field being inputted into the buffer memory.

Packet switching system

Abstract: A packet switching system mainly consists of a packet transmission controller, connected to a line group, for performing transmission control of a data packet, and a packet switching unit for receiving the data packet from the packet transmission controller to perform switching processing. The packet switching unit includes a packet separator for separating the data packet into a header part and a data part, a packet header processor for updating the separated header part, a packet data buffer for storing the separated data part, and a packet combiner for combining the output from the packet data buffer and the output from the packet header processor and supplying a combined packet to the packet transmission controller.

A packet switching network with multiple packet destinations

Abstract: A communication method and packet switching network in which self-routing packets are communicated to a single-destination port of the switching network, a plurality of grouped destination ports or to two distinct destination ports after the modification by the switching network of the self-contained routing information within the packets. The packet switching network has a plurality of stages with each stage comprising a plurality of switch nodes, and the communicated packets can be of the single-destination, broadcast, or multiple-destination types of packets. The routing information within the packet comprises pairs of data bits with each pair associated with a stage of the switching network and with the value of the pair of bits determines the type of packet for the corresponding stage. Each switching node has two input and two output terminals, and a switch node in a particular stage is responsive to a single-destination packet received on an input terminal to communicate the packet to the output terminal designated by the value of the pair of bits for that stage. A switch node is responsive to a broadcast type packet to communicate the packet to both output terminals.

Routing control method in a packet switching network

Abstract: In a communication network, in which a plurality of switching nodes are connected with each other through a plurality of relay lines and one of the switching nodes acts as a center node for network routing, the center node estimates the state of delay of data for every relay line on the basis of information previously inputted, indicating the communication network configuration, and the state of delay of data reported by each of the switching nodes, and informs each of the switching nodes of said estimated state of delay of data. Each of the switching nodes determines and selects the relay line giving the shortest delay of data for every destination, to which it outputs data, on the basis of the state of delay at the relevant switching node itself and that received from the center node.

CSMA-CD with channel capture

Abstract: This invention relates to an efficient CSMA/CD-based protocol for a local area network using an unidirectional global bus architecture, in which a ready station captures the bus for one packet time only if no other stations to its left transmit along with it. A modified version of the protocol provides a fairer access to the bus. This new scheme is a variable priority structure in which each station has a priority that changes dynamically with the state of the system. This is a contention scheme that behaves like a generalized and very flexible reservation protocol. A performance analysis of both versions of the protocol results in channel efficiency and transmission delay figures that are superior to those of the leading bus protocols.

High speed packet switching arrangement

Abstract: A circuit arrangement is provided for switching serial data packets through a network destined for one of a plurality of possible outgoing lines. Minimal delay is achieved by shifting the data through a shift register having length equivalent to the destination address of the incoming serial data packet. The shift register addresses a memory which in turns controls a switch network so that the incoming packet is switched with minimal delay to an appropriate outbound line. By utilizing random access memory to translate from destination address to switch position, the system may be altered to correct for changes in the overall network caused by network failures or expansion network or to allow dynamic load balancing by directing data through the switch to a control computer which in turn rewrites the memory.

Packet switching system.

Abstract: A packet switching system for achieving high-speed packet switching on data lines having the X.25 protocol of the C.C.I.T.T. It includes a plurality of data line apparatuses (DLC: 10, 11, and 1N), a call connection control information transfer bus commonly connected to the plurality of data line apparatuses (CB: 2), a specialized data transfer bus for data packets (DB: 4), a packet buffer state information transfer bus for transmitting and receiving call state information (SB: 6), and a call connection controlling processor connected to the call connection control information transfer bus (CP: 3). Each of the data line apparatuses has a receive packet storing circuit (DTRQ: 102) provided with a receive packet buffer of the first-in random out (FIRO) memory, and a transmit packet storing circuit (DTSQ: 105) provided with a transmit packet buffer of the FIRO memory.

Packet information field data format

Abstract: A packet information field format is disclosed which facilitates packet buffer memory overflow control Generation of the information field is such that like bits from samples representing a corresponding communication channel from a plurality of frames are grouped together In a specific embodiment, the bits from the communication channel samples are arranged in groups including the most significant bits to the least significant bits The packet header also includes a field which can have an indication therein of whether bits can be dropped from the packet and an indication of whether bits have already been dropped from the packet Consequently, dropping of bits from the packet is readily achieved by first dropping the group including the least significant bits, then dropping the group including the next to least significant bits, if necessary, and so on until it is determined that the entire packet should be dropped, if necessary

Real-time end of packet signal generator

Abstract: Provided is a circuit for signalling the real-time end of a local area network packet as the packet is being pulled off a transmission medium and stored in memory. Storage of the packet is performed by a local area network coprocessor. The circuit monitors for the simultaneous occurrence of three conditions: the coprocessor is in a write-to-memory cycle; it is writing to the address of status word pertaining to a packet; and the most significant bit of the status word is being set. If all three conditions are true, the circuit asserts the real-time end-of-­packet signal.

Traffic Analysis of a Token Ring PBX

Abstract: A new approximation is described for the calculation of the transmission delay distribution experienced by voice subscribers connected to a token ring PBX. Together with simulation, the new technique is used to explore the dependence of delays to transmission on ring latency, voice packet length, and number of active subscribers for a 20 Mbit/s ring. Transmission delays are found to be relatively insensitive to the exact values of ring latency and voice packet length for the systems studied. The overall time between the generation and replay of speech samples is determined primarily by the voice packet length, and the use of short packets is recommended.

Asynchronous packet manage

Abstract: The Asynchronous Packet Manager is the interface for transferring data in a first format between a data terminal equipment and a combination data and telephone switching system in a properietary packet format. A microprocessor accepts data from a universal asynchronous receiver transmitter and forwards the data to a mini packet receiver transmitter, when it is formatted into mini packets and converted to an alternate mark inversion signal and sent to the switching network.

Packet flow controlling system

Abstract: PURPOSE: To realize the flow control which can cope with the overload condition of traffic, by controlling the transmission throughput by a packet terminal so that its own transmission throughput does not exceed a reported maximum throughput and abandoning excess packets or disconnecting a logical channel by an exchange if the packet terminal transmits packets with a throughput exceeding the reported value. CONSTITUTION: The number of packets is counted by a transmission packet (throughput) counter 14 in every throughput decision cycle which is a certain period reported by a throughput cycle switching report line 51, and the counted value is defined as the transmission throughput in the current cycle and is arranged with a network at the time of originating a call or the like, and it is checked by a throughput value comparator 16 whether this throughput value exceeds a maximum transmission throughput value stored in a throughput value holding device 15 or not. If it does not exceeds, a transmission permission report line 54 is set to the transmittable state and a packet transmission (throughput) controller 12 transmits packets from a transmission packet buffer 13. If it exceeds, the transmission permission report line 54 is set to the untransmittable state and the packet transmission (throughput) controller 12 stops the transmission. COPYRIGHT: (C)1988,JPO&Japio

Performance Analysis of a Quasi-M/D/1 Cut-Through Switching Network with Noisy Channels

Abstract: Cut-through switching is advantageous in that it can reduce the transmission delay compared with the conventional message or packet switching. In this paper, when the channel is noisy, we investigate various properties of M/D/1 quasi-cut-through switching including actual traffic intensity and overall network delay. In the analysis of delay resulting from retransmission of erroneous packets, we have included the average transmission time of negative acknowledgment signal and queueing time for the retransmitted packet so that the overall network delay can be obtained accurately. In addition, we have obtained distributions of the number of nodes to be traversed and the number of nodes through which packets pass by cut. According to the analysis results, the performance of cut-through switching is superior to that of conventional packet switching in most practical ranges of parameter values.

The butterfly satellite IMP for the wideband packet satellite network

Abstract: Multiprocessor computer systems have proven effective as high performance switching nodes in packet switched data communications networks. They are well suited to performing the required queuing, routing, and scheduling tasks, and can scale upward to provide higher system throughput when combined with software that exploits the parallelism provided by the hardware. This paper describes the packet switch used in the DARPA Wideband Packet Satellite Network and the Butterfly™ Multiprocessor on which it is based.

Optimal hop-by-hop flow control in computer networks

Abstract: The problem of hop-by-hop flow control in a computer network is formulated as a Markov decision process with a cost function composed of the delay of the messages and the buffer constraints. The optimal control is shown to be a linear truncated function of the state and the explicit form is found when the arrival process of the messages is a Bernoulli process. For a renewal arrival process, the long-rnn average cost of any policy with a linear truncated structure is expressed by a set of linear equations.

Data flow graph partitioning to reduce communication cost

Abstract: This paper presents a cost-effective scheme for partitioning large data flow graphs. Standard data flow machine architectures are assumed in this work. The objective is to reduce the overhead due to token transfers through the communication network of the machine. When this scheme is employed on large graphs, the load distribution on the rings of the data flow machine is also improved. A canonical form of a data flow graph is introduced to establish the relationship between the communication overhead and the size reduction of the partition cut-set. General lower estimates on the overhead are derived in terms of processing and transmission delay parameters of the machine. The method uses heuristics and an evaluation function to guide the partition algorithm. Some implications of the proposed method on the organization of the data flow machines are discussed.