scispace - formally typeset
Search or ask a question

Showing papers on "Throughput published in 1980"


Journal ArticleDOI
TL;DR: An analytic model is developed and the main result is the moment generating function of the distributed queue size (number of ready users) and mean value formulas for message delay and channel assignment delay are derived.

239 citations


Journal ArticleDOI
TL;DR: This paper considers several schemes for sharing a pool of buffers among a set of communication channels emanating from a given node in a network environment so as to make effective use of storage in a variety of applications.
Abstract: Nodal storage limitations in a store and forward computer network lead to blocking; this results in degradation of network performance due to the loss or retransmission of blocked messages. In this paper, we consider several schemes for sharing a pool of buffers among a set of communication channels emanating from a given node in a network environment so as to make effective use of storage in a variety of applications. Five sharing schemes are examined, analyzed, and displayed in a fashion which permits one to establish the tradeoffs among blocking probability, utilization, throughput, and delay. The key to the analysis lies in the observation that the equilibrium joint probability distribution of the buffer occupancy obeys the well-known product form solution for networks of queues. The study indicates advantages and pitfalls of each of the sharing schemes. We observe, in general, that sharing with appropriate restrictions on the contention for space is very much desirable.

238 citations


Journal ArticleDOI
TL;DR: The performance of the R-ALOHA protocol for multiple access is studied and numerical results from both analysis and simulation are presented to illustrate the accuracy of the analytic models as well as performance characteristics of the rhoHA protocol.
Abstract: In packet broadcast networks, users are interconnected via a broadcast channel. The key problem is multiple access of the shared broadcast channel. The performance of the R-ALOHA protocol for multiple access is studied in this paper. Two user models with Poisson message arrivals are analyzed; each message consists of a group of packets with a general probability distribution for group size. In the first model, each user handles one message at a time. In the second model, each user has infinite buffering capacity for queueing. Analytic models are developed for characterizing message delay and channel utilization. Bounds on channel throughput are established for two slightly different protocols. Numerical results from both analysis and simulation are presented to illustrate the accuracy of the analytic models as well as performance characteristics of the R-ALOHA protocol.

131 citations


Journal ArticleDOI
TL;DR: This variation of the go-back- N ARQ reduces the effect of the round-trip delay, and hence increases the system throughput efficiency, and may find applications m satellite communication systems or other systems where round- Trip delay is large.
Abstract: The conventional go-back- N ARQ is inadequate for error control on satellite channels due to the large round-trip delay and high bit rate. The throughput efficiency of this system drops rapidly as the channel error rate increases. In this paper, a variation of the go-back- N ARQ is described. This variation reduces the effect of the round-trip delay, and hence increases the system throughput efficiency. Therefore, it may find applications m satellite communication systems or other systems where round-trip delay is large.

105 citations


Journal ArticleDOI
TL;DR: A class of multiple access schemes, especially suited for use in packet switched satellite networks, are introduced, characterized by the mixing of free contention and regulated access for the use of the satellite channel.
Abstract: In this paper, a class of multiple access schemes is introduced, especially suited for use in packet switched satellite networks. These schemes, called the Interleaved Frame Flush-Out (IFFO) protocols, are characterized by the mixing of free contention and regulated access for the use of the satellite channel. Such hybrid schemes possess desirable features of both extreme strategies and have a built-in capability to adapt to the traffic load profile. A Markov chain model is introduced for their description and analysis, and an optimization problem is formulated for choosing the "best" among the members of this class of protocols. The performance of the protocols is evaluated by computation and simulation, and comparison to other protocols. It is shown to be stable and superior to that of the other protocols over a wide range of throughput values.

51 citations


Journal ArticleDOI
J. Roberts1, T. Healy
TL;DR: The results of this investigation indicate that a packet radio system can be designed with a modest link margin for fading and achieve identical throughput performance over a nonfading channel and a fading channel with only a small increase in average packet delay for the fading channel.
Abstract: Expressions for the throughput and average packet delay for a Pure-ALOHA single-hop packet radio system operating in slow Rayleigh fading are derived. For noncoherent frequency-shift-keying (NCFSK), an exact closed form expression is presented. For coherent phase-shift-keying (CPSK) an excellent approximation for large packet sizes is derived. This approximation technique is valid in general for other modulation schemes and for other fading channel statistical characterizations. The packet length which maximizes the useful data throughput in slow Rayleigh fading is found. The results of this investigation indicate that a packet radio system can be designed with a modest link margin for fading and achieve identical throughput performance over a nonfading channel and a fading channel with only a small increase in average packet delay for the fading channel.

51 citations


Journal ArticleDOI
TL;DR: This analysis produces both path throughput (utilization) curves and message delay curves, as a function of message generation rate, which show that the CSMA protocol is in a sense self stabalizing, serve to quantify its behaviour, and indicate loading levels which result in unacceptable message delays.
Abstract: Carrier sense multiple access (CSMA) protocols were originally conceived for use in digital radio communication. Such protocols are, however, quite applicable in a variety of distributed computing and local networking configurations based on a shared bus. The CSMA protocols are characterized by the fact that message collisions can occur only in a very small time window whose duration corresponds to the propagation delay of the bus. They are further characterized by the technique used to subsequently serialize the transmission of the colliding messages. In this paper we analyze the situation wherein colliding messages are serialized by using a set of staggered `retry' delays which are associated with the sources that may generate the colliding messages. Our analysis produces both path throughput (utilization) curves and message delay curves, as a function of message generation rate. These curves show that the protocol is in a sense self stabalizing, serve to quantify its behaviour, and indicate loading levels which result in unacceptable message delays.

49 citations


Journal ArticleDOI
TL;DR: A new simple expression is given for the probability of successful transmission on an infinite population ALOHA channel with variable length packets along with the best and the worst length densities.
Abstract: In this paper we give a new simple expression for the probability of successful transmission on an infinite population ALOHA channel with variable length packets. Expressions for the throughput and the probability density of the packet length on the channel are derived in a straightforward way along with the best and the worst length densities.

41 citations


Journal ArticleDOI
D. Sant1
TL;DR: For unslotted channels in which the dead time between successive packet transmissions due to each user exceeds twice the packet duration, the throughput is shown to be independent of the nature of the packet interarrival time distribution of any user.
Abstract: An unslotted ALOHA channel with dissimilar users and each user having an arbitrary distribution of packet interarrival time, is analyzed for its throughput. It is shown that the throughput behavior of an unslotted channel with a very large number of users is the same as that of Abramson's Poisson channel. When each user transmits many packets almost in succession and then remains silent for a long period, the throughput of the unslotted channel is shown to approach that of the slotted channel. For unslotted channels in which the dead time between successive packet transmissions due to each user exceeds twice the packet duration, the throughput is shown to be independent of the nature of the packet interarrival time distribution of any user, depending only on the average rate at which users transmit packets.

24 citations


Journal ArticleDOI
Jansen1, Kessels
TL;DR: The DIMOND is a building block for communication networks in which throughput is more important than transmission delay.
Abstract: The DIMOND is a building block for communication networks in which throughput is more important than transmission delay. Its main attraction stems from the fact that it allows the routing of messages through a network to be completely distributed over the individual building blocks.

17 citations


Proceedings ArticleDOI
01 Jan 1980
TL;DR: A communication satellite with a multiple-beam antenna and onboard signal processing is considered for use in a 'message-switched' data relay system and the reservation system appears to be the most attractive protocol.
Abstract: A communication satellite with a multiple-beam antenna and onboard signal processing is considered for use in a 'message-switched' data relay system. The signal processor may incorporate demodulation, routing, storage, and remodulation of the data. A system user model is established and key functional elements for the signal processing are identified. With the throughput and delay requirements as the controlled variables, the hardware complexity, operational discipline, occupied bandwidth, and overall user end-to-end cost are estimated for (1) random-access packet switching; and (2) reservation-access packet switching. Other aspects of this network (eg, the adaptability to channel switched traffic requirements) are examined. For the given requirements and constraints, the reservation system appears to be the most attractive protocol.

Journal ArticleDOI
TL;DR: The design and performance evaluation of a single microprocessor based packet switch for use on-board a satellite and the effect of variation in the number of input and output lines, data rates, destination fucntions, speed of output lines and some other design parameters on the performance of the switch are presented and discussed.
Abstract: The design and performance evaluation of a single microprocessor based packet switch for use on-board a satellite are presented. The primary design criterion is to maximize the system throughput. A number of protocols and their impact on the switch design are discussed. System and processor hardware architectures are described. The flow charts of the software required to accomplish the essential functions are presented and modification needed for use in a multisatellite network are also indicated. Maximum throughput attainable is calculated. Desirable characteristics of microprocessors for this application are pointed out. A queue theoretic model of the packet switch has been developed. Analytical relationships of the average waiting times and the queue sizes at the queues and the overall average response time with the various design parameters of the switch have been obtained. A number of graphs showing the effect of variation in the number of input and output lines, data rates, destination fucntions, speed of output lines and some other design parameters on the performance of the switch are presented and discussed.

ReportDOI
01 Jan 1980
TL;DR: Demand-Assignment TDMA schemes, a class of hybrid TDMA/Collision- Resolving schemes, governing the sharing of multiple-access communication channels are studied, used to allocate channel capacity among sources which require real-time transmission.
Abstract: : Demand-Assignment TDMA schemes, a class of hybrid TDMA/Collision- Resolving schemes, governing the sharing of multiple-access communication channels are studied. Sources communicate with each other through a synchronized (slotted), fully-connected communication medium. This communication medium can be a terrestrial radio or line communication channel (inducing low propagation delay or a satellite channel (inducing high propagation delay). The Demand- Assignment TDMA schemes studied are used to allocate channel capacity among sources which require real-time transmission. A non-preemptive cutoff priority discipline is employed to offer priority services to important messages. The performance of the schemes is measured in terms of the message blocking (loss) probability and the message delay vs. channel throughput functions. For sources which transmit at multiple rates, a maximum normalized average waiting time is introduced as an overall system performance measure. The latter is used as an objective function in finding the optimal channel frame structure. The class of store-and-forward hybrid TDMA/Collision-Resolving schemes are composed of a TDMA component and a Tree Search component. Groups of Sources are served on a TDMA basis. Collisions among sources within each group are resolved by following a Tree Search technique. Message arrivals in a sequence of slots are assumed to be i.i.d., governed by an arbitrary distribution. The messages are assumed to contain single packets, except in the pure TDMA case where the message length distribution is arbitrary. Two cases are studied. Fixed Reservation schemes, operating on a store-and-forward basis, are also investigated.

01 Apr 1980
TL;DR: It is shown that, using the same model, it is possible to derive the actual packet delay distribution of CSMA channels, which is similar in nature to that provided for slotted ALOHA channels.
Abstract: : Existing analysis of the carrier sense multiple access mode (CSMA) has led to the determination of the average channel performance in terms of average throughput and average packet delay. This was achieved by formulating a semi-markovian model for CSMA channels with a finite population of users. In this paper, it is shown that, using the same model, it is possible to derive the actual packet delay distribution. The analysis is similar in nature to that provided for slotted ALOHA channels. These results are useful in the design of systems intended for real time applications such as digitized speech, and in the analysis of multihop packet radio systems. (Author)

Journal ArticleDOI
TL;DR: This correspondence deals with the application of a bit slice microprocessor to a satellite born packet switch, and the performance of the packet switch is evaluated by obtaining an upper bound on the system throughput.
Abstract: This correspondence deals with the application of a bit slice microprocessor to a satellite born packet switch. A system architecture for accomplishing this task is proposed, and the performance of the packet switch is evaluated by obtaining an upper bound on the system throughput.

Journal ArticleDOI
TL;DR: The past fate of a retransmitted packet is taken into account to examine nodal blocking and the result is a closed-form expression in terms of its steady-state estimate, the size of the Store-and-Forward buffers, the number of transmission lines connected to a node, the traffic intensity of the network, and a function comparing orders of message packets and the acknowledgement (ACK) arrivals.
Abstract: To derive estimates for such important measures on network performance as the average queue lengths, throughput rates and buffer utilization of a large (national) computer communication network, it is always assumed that the number of a packet is geometrically distributed with PR, the steady-state nodal blocking probability. This implies that the probability remains constant for the first and subsequent transmission attempts and that these attempts are independent. In this paper, the past fate of a retransmitted packet is taken into account to examine nodal blocking. The result is a closed-form expression in terms of its steady-state estimate, the size of the Store-and-Forward buffers, the number of transmission lines connected to a node, the traffic intensity of the network, and a function comparing orders of message packets and the acknowledgement (ACK) arrivals, whose derivation requires some equalities from order statistics and the incomplete beta function.

Journal ArticleDOI
TL;DR: This paper investigates the dynamic characteristics of the non-slotted CSMA due to ground radio and shows that it is not necessary to apply the complex terminal control, i.e., synchronizing the transmission with the slot, for the system stability.
Abstract: So far, many proposals have been put forward for increasing the channel capacity of the ALOHA system. Among these is the use of the CSMA system which is known to improve to a great extent the properties of the random access system by ground radio or cable. So far, the slotted CSMA system has been studied in detail for its dynamic characteristics and traffic control effect. But in the case of non-slotted CSMA, except that its capacity is almost the same, a detailed analysis has yet to be done. In this paper, the dynamic characteristics of the non-slotted CSMA due to ground radio has been investigated by equilibrium point analysis. It is revealed that the throughput characteristics of the non-slotted CSMA system are almost similar to those for the slotted CSMA system, but the system stability is quite poor. Next it is proposed that a simple traffic control be applied in the non-slotted CSMA and the improvement in stability has been studied. It is shown that the dispersion of the packet delay is increased slightly but the operation due to this simple control system can be made sufficiently stable. Thus it is shown that it is not necessary to apply the complex terminal control, i.e., synchronizing the transmission with the slot, for the system stability.

Journal ArticleDOI
TL;DR: A study of a congestion control mechanism in a packet-switched data network is presented and it is shown that the network throughput can be maintained at a constant level, while the average transit delay remains within acceptable bounds for offered loads beyond the congestion point.

Journal ArticleDOI
TL;DR: An algorithm for the availability analysis has been developed and given the topological and physical characteristics of the network, the external traffic statistics at the network node pairs and the routing procedure, the network availability and the average loss of throughput due to single failures of lines or switching nodes are evaluated.

Book ChapterDOI
01 Jan 1980
TL;DR: The use of input buffer (IB) limits for network congestion control is introduced and the rationale for the effectiveness of IB limits is discussed.
Abstract: Congestion control mechanisms are needed for store-and-forward packet networks to maintain a high level of throughput. The basic requirements of network congestion control and some specific control techniques are examined. The use of input buffer (IB) limits for network congestion control is introduced. The rationale for the effectiveness of IB limits is discussed. Strategies for the design of IB limits have been investigated using both queueing analysis and simulation experiments. Some of our preliminary findings are presented.

Journal ArticleDOI
TL;DR: This correspondence deals with the application of a bit slice microprocessor to a satellite born packet switch, and the performance of the packet switch is evaluated by obtaining an upper bound on the system throughput.
Abstract: This correspondence deals with the application of a bit slice microprocessor to a satellite born packet switch. A system architecture for accomplishing this task is proposed, and the performance of the packet switch is evaluated by obtaining an upper bound on the system throughput.