Hard real-time communication in multiple-access networks

With the increasing use of distributed hard real-time systems, the ability of computer networks to handle hard real-time message traffic is becoming more important. For traditional networks, maximizing the throughput or minimizing the average message delay is the most important performance criteria. In the hard real-time domain, however, concern focuses on satisfying the time constraints of individual messages. This paper examines recent developments in hard real-time communication in local area multiple-access networks. Two general strategies are used in hard real-time communication: the guarantee strategy and the best-effort strategy. In the former, messages are guaranteed to meet their deadlines during normal operation of the network. In the best-effort strategy, the network will attempt to send messages before their deadlines, but no guarantees are given. Real-time message traffic can be distinguished according to whether it is best suited for the guarantee strategy or the best-effort strategy. Although this paper concentrates on multiple-access networks, many of the concepts presented and lessons learned are also applicable to other types of networks.     

Stochastic regulation of queues in data networks

A new class of routing policies for the regulation of queue lengths at all nodes throughout a data network in the presence of congestion caused by heavy input traffic is developed. Regulation is achieved via a feedback algorithm which minimizes, over each successive control interval, the mean-square queueing error where the latter is the difference between the actual queueing vector and its desired nominal value. Implementation of the algorithm requires knowledge of the mean and covariance of the input traffic and of the queue length measurement error stochastic processes. In the case of the former process, on-line measurements can be used to calculate the required statistical parameters. For the latter process, a priori knowledge that reflects the uncertainty in measuring and transmitting queue lengths throughout the network is needed.     

Performance analysis of networks of queues under active queue management scheme

Analysis of networks of queues under repetitive service blocking mechanism has been presented in this paper. Nodes are connected according to an arbitrary configuration and each node in the networks employs an active queue management (AQM) based queueing policy to guarantee certain quality of service for multiple class external traffic. This buffer management scheme has been implemented using queue thresholds. The use of queue thresholds is a well known technique for network traffic congestion control. The analysis is based on a queue-by-queue decomposition technique where each queue is modelled as a GE/GE/1/N queue with single server, R (R ⩾ 2) distinct traffic classes and {N = N₁, N₂, … , N_R} buffer threshold values per class under first-come-first-serve (FCFS) service rule. The external traffic is modelled using the generalised exponential (GE) distribution which can capture the bursty property of network traffic. The analytical solution is obtained using the maximum entropy (ME) principle. The forms of the state and blocking probabilities are analytically established at equilibrium via appropriate mean value constraints. The initial numerical results demonstrate the credibility of the proposed analytical solution.     

Collision-control algorithms in carrier-sense multiple-access (collision-detection) networks

The effects of the collision-control algorithm on CSMA-CD protocols are studied. After a comparative evaluation of some algorithms and an ideal scheduling system, the required features for an optimum collision-control algorithm are enumerated. Finally, a new algorithm, incorporating most of these features, is proposed, and its performance is evaluated.     

Analysis of networks of queues via projection techniques

In this research, the author deviates from the conventional traffic models and approaches. The author uses a traffic model proposed by Cruz (1990). In Cruz's model, the rate functions of traffic sources are assumed to satisfy some linear “burstiness constraints”. Such traffic models can be used to describe a class of rate-based flow-controlled sources. A state vector is defined to describe the queueing system. The author divides the operation of the studied queueing system into multiple phases. For each phase, the author writes a system equation to describe completely the behavior of this studied queueing system. The author then proposes the iterative feasible set method to identify the feasible region of the state vector using some linear programming techniques and other existing theorems regarding the projection of convex sets into a space with a lower dimension. Using the above technique, the author studied the performance of three routing schemes in a simple dynamic routing problem, namely the route to shortest rule, the fixed routing rule and the bounded linear rule. The author first identified the feasible regions of a defined state vector for each routing scheme using the proposed method. From the identified feasible regions, the author then analyzed the extremal performance of these routing schemes and compared their performances     

Approximation methods for networks of queues with priorities

Queuing network models are commonly used to analyze the performance of computer system. Unfortunately, the class of queuing network models which can be exactly analyzed excludes CPU priority scheduling disciplines, conspicuously present in most computer systems.A popular approximation technique which we denote the reduced occupancy approximation, is often used to analyze such priority service disciplines because of its simplicity and intuitive appeal. However, despite its widespread use, questions about its accuracy and applicability have received very little attention. Further compounding this situation, is the existence of proprietary software packages which purport to analyze such priority disciplines, but which in fact exhibit behavior remarkably similar to the roa.In this paper we show where, and more importantly why, the roa fails. This understanding leads to a significantly improved approximation technique which sacrifices neither simplicity nor applicability. Although our primary focus is on a two class preemptive priority closed network structure, the basic idea is quite general and extensions to multiclass and nonpreemptive priority structures are indicated.     

Simulation output analysis for local area computer networks

Summary This paper develops discrete event simulation methods for local area computer networks. We restrict attention to local network simulations with an underlying stochastic process that can be represented as a generalized semi-Markov process. Using a geometric trials criterion for recurrence, we establish a regenerative process structure for passage times in this setting. This leads to an estimation procedure for delay characteristics of ring and bus networks.     

Robust design of a linear quadratic power control algorithm in multiple-access networks

In wireless networks under interference, power control is of the utmost importance to guarantee Quality of Service during data transmissions. A distributed perspective is commonly preferred to design controllers in each mobile user in the network for power allocation. The round-trip delay is a characteristic feature of wireless networks, and it was considered a known quantity in previous works. In this paper, we do not follow this assumption and propose the design of the power controller only with the information of upper and lower bounds on the round-trip delay as functions of a frequency gain. In a second stage, we relate the proposed robust design to common performance indicators, such as the step response overshoot. The proposed design rules can be applied to design a suitable robust controller for power control in a wireless network subject to interference.     

探讨计算机网络故障分析及维护

计算机网络高度普及,已经成为生活中不可或缺的一部分,网络维护在计算机网络系统中有着重要地位,对于计算机网络故障的分析和研究是十分有必要的。对网络进行及时有效的维护,保障网络安全运行,分析计算机网络应用中的故障,并且结合具体的工作实践,加强计算机网络故障查处及维护有利于进一步提高计算机网络的运行质量。     

A hybrid TDMA/Random-access scheme for multiple-access communication networks

A hybrid TDMA/Random-Access multiple-access (HTRAMA) scheme is introduced for providing an access-control coordination for a multi-access communication channel. Such a scheme is applicable to a large spectrum of computer communication network applications. Under this hybrid scheme, the system sources are divided into groups. Sources in different groups are allocated disjoint time slots for their transmissions. Sources within a group share their allocated time slots by transmitting according to a tree random-access policy. The number of groups (and their sizes) is dynamically adjusted to properly (and optimally) match the underlying channel traffic characteristics. In this fashion the hybrid scheme dynamically adapts to a random-access structure at lower traffic throughput levels and to a TDMA structure at higher throughput levels. We carry out detailed delay throughput analysis for these hybrid schemes under both limited and unlimited source buffer capacities. The hybrid scheme is demonstrated to yield very good delay-throughput performance curves under wide ranges of network traffic statistical fluctuations and spans.     

Dual and selfdual networks of queues with rejection blocking

Open and closed queueing networks with rejection blocking are investigated. Using the concept of holes, a duality is derived for pairs of networks. This duality equates equilibrium state probabilities and throughputs of the given network and its dual. As an application an exact product form solution for certain closed queueing networks with rejection blocking are derived. In this case, duality provides a simple method to compute performance measures. In some cases, a network and its dual have the same structure. Duality provides relations among performance measures of different stations in this case.     

Computational algorithms for networks of queues with rejection blocking

Summary Open, closed and mixed queueing networks with reversible routing, multiple job classes and rejection blocking are investigated. In rejection blocking networks blocking event occurs when upon completion of its service of a particular station's server, a job attempts to proceed to its next station. If, at that moment, its destination station is full, the job is rejected. The job goes back to the server of the source station and immediately receives a new service. This is repeated until the next station releases a job and a place becomes available. In the model jobs may change their class membership and general service time distributions depending on the job class are allowed. Two station types are considered: Either the scheduling discipline is symmetric, in which case the service time distributions are allowed to be general and dependent on the job class or the service time distributions at a station are all identical exponential distributions, in which case more general scheduling disciplines are allowed. An exact product form solution for equilibrium state probabilities is presented. Using the exact product form solution of the equilibrium state distribution, algorithms for computation of performance measures, such as mean number of jobs and throughputs, are derived. The complexity of the algorithms is discussed.     

Interconnection of computer networks

As computer networks proliferate, interest in interconnecting networks will increase. This paper considers the problems of interconnecting heterogeneous computer networks to provide communication between processes in different networks. The treatment is tutorial with a comprehensive survey of relevant work. Topics discussed include global addressing and routing techniques, level of network interconnection, and functions performed by the interface or Gateway between networks. Various approaches to each of these problems are compared, with particular attention to the extent of changes in existing local net operations required by the different approaches. Techniques to implement internet addressing, routing, error recovery, and other necessary communication services on top of local network facilities appear feasible without demanding large changes to individual nets.     

Can high-speed networks survive with DropTail queues management?

It has been observed that TCP connections that go through multiple congested links (MCL) have a smaller transmission rate than the other connections. Such TCP behavior is a result of two components (i) the cumulative packet losses that a flow experiences at each router along its path; (ii) the longer round trip times (RTTs) suffered by such flows due to non-negligible queueing delays at congested routers. This double “bias” against connections with MCLs has been shown to approximate the so-called minimum potential delay fairness principle in the current Internet. Despite the recent proliferation of new congestion control proposals for TCP in high-speed networks, it is still unclear what kind of fairness principle could be achieved with such newly proposed congestion control protocols in high-speed networks with large-delays. Studies already show that some high-speed TCP variants may cause surprisingly severe RTT unfairness in high-speed networks with DropTail routers.This paper studies the problem of unfairness in high-speed networks with some well-known high-speed TCP variants in presence of multiple congested links and highlights the severity of such unfairness when DropTail queue management is adopted.Through a simple synchronized loss model analysis, we show how synchronized losses with DropTail in high-speed networks could lead to severe RTT unfairness and drop probability (DP) unfairness; while random marking AQM schemes, which break the packet loss synchrony mitigate such unfairness dramatically by ensuring that the packet loss probability of a flow is the sum of the loss probabilities on the congested routers it crosses.Extensive simulations are carried out and the results support our findings.     

Broadcasting cryptosystem in computer networks

A cryptosystem which can securely broadcast secret messages in a public access distributed system is proposed. Comparing with the existing broadcasting schemes, this scheme always requires fewer broadcasting messages. Furthermore, when a new user is inserted into the distributed system, the corresponding secret and public keys can be determined without changing any existing keys.     

Optimal control of finite source priority queues with computer system applications

The paper deals with the derivation of optimal control rules for finite source queueing systems with preemptive resume service discipline. The three performance measures considered are: server utilization, mean queue length and throughput.

It is indicated how the results on optimal control can be applied to multiprogrammed computer systems and some numerical examples are given.