Message Transmission Time Research Articles

Performance evaluation of SIP-based multimedia services in UMTS

With an ever increasing penetration of IP technologies and the tremendous growth in wireless data traffic, the wireless industry is evolving the mobile core networks towards IP technology. The third Generation Partnership Project (3GPP) has specified an IP multimedia sub-system (IMS) in UMTS Release 5/6, which is adjunct to the UMTS packet-switched (PS) GPRS core network. This IP-based network provides full packet call control capabilities by using the text-based Session Initiation Protocol (SIP). Initial indications, as to the signalling delay associated with SIP messages, have concerned mobile operators about the viability of SIP services over the UMTS air interface. This article provides an insight into the UMTS system performance, focusing on selected UMTS SIP-based services. Typical services with real-time requirements such as voice as well as delay-sensitive and non-sensitive applications, such as real-time chat and instant messaging services are investigated. Furthermore, the paper discusses and analyses the requirements and possible solutions for improving efficiency of SIP usage in a wireless environment through signalling protocol message compression. Results of a performance evaluation of SIP signalling scenarios are presented in terms of time delay and message overload in the system. Results show that message compression can considerably reduce SIP message transmission time on the radio access network while core network delay contributions are found to be still high.

Determination of LTPB parameters to guarantee message deadlines

A bandwidth allocation scheme for a linear token passing multiplex data bus is proposed based on balancing message transmission time with traffic load to each node. It is proved to provide a network worst case achievable utilization of 50%. Under this allocation scheme, closed-form expressions for the initialized value of token holding timers and token rotation timers in each node are obtained.

Compressionless wormhole routing: an analysis for hypercube with virtual channels

Several recent studies have shown that adaptive routing algorithms based on deadlock recovery have superior performance characteristics than those based on deadlock avoidance. Most of these studies, however, have relied on software simulation due to the lack of analytical modelling tools. In an effort towards filling this gap, this paper presents a new analytical model of compressionless routing in wormhole-routed hypercubes. This routing algorithm exploits the tight coupling between wormhole routers for flow control to detect and recover from potential deadlock situations. The advantages of compressionless routing include deadlock-free adaptive routing with no extra virtual channels, simple router design, and order-preserving message transmission. The proposed analytical model computes message latency by determining the message transmission time, blocking delay at each router, multiplexing delay at each network channel, and waiting time in the source before entering the network. The validity of the model is demonstrated by comparing analytical results with those obtained through simulation experiments.

Scheduling time-constrained multicast messages in circuit-switched tree networks

In this paper, we consider a kind of multicast scheduling problem in a tree network. Each multicast message is transmitted through a directed subtree within the tree network. The transmission time of each multicast message is assumed to be one unit. Two messages can be transmitted at the same time if their subtrees are edge-disjoint. Each message is constrained by a ready time and a deadline, and has a weight we can gain if it is scheduled within its deadline. The optimality criterion is the total weight we gain. We assume that the degree of each subtree is bounded by a constant d and present an approximation algorithm of which the approximation ratio is at most 4 d+15.

Mean value and tail distribution of the message delay in statistical multiplexers with correlated train arrivals

In this paper, we study a statistical multiplexer which is modelled as a discrete-time single-server infinite-capacity queueing system. This multiplexer is fed by messages generated by an unbounded population of users. Each message consists of a generally distributed number of fixed-length packets. We assume the packet arrival process to exhibit simultaneously the following two types of correlation. First, the messages arrive to the multiplexer at the rate of one packet per slot, which results in what we call a primary correlation in the packet arrival process. Also, on a higher level, the arrival process contains an additional secondary correlation, resulting from the fact that the behaviour of the user population is governed by a two-state Markovian environment. Specifically, the state of this user environment in a particular slot determines the distribution of the number of newly generated messages in that slot. In previous work on this model, we provided analytical results for the moments and the tail distribution of the system contents. Using these results, we now concentrate on the message delay performance of this system, under the important assumption of a first-come-first-served queueing discipline for packets, whereby packets that arrive during the same slot are stored in random order. Closed-form expressions are derived for the mean value of both the total delay and the transmission time of an arbitrary message. Additionally, we provide a reasonably tight upper and lower bound for the tail probabilities of the message delay. By means of some numerical examples, we discuss the influence of the environment parameters on the delay performance.

Near-optimal all-to-all broadcast in multidimensional all-port meshes and tori

All-to-all communication is one of the most dense collective communication patterns and occurs in many important applications in parallel and distributed computing. In this paper, we present a new all-to-all broadcast algorithm in multidimensional all-port mesh and torus networks. We propose a broadcast pattern which ensures a balanced traffic load in all dimensions in the network so that the all-to-all broadcast algorithm can achieve a very tight near-optimal transmission time. The algorithm also takes advantage of overlapping of message switching time and transmission time, and the total communication delay asymptotically matches the lower bound of all-to-all broadcast. Finally, the algorithm is conceptually simple and symmetrical for every message and every node so that it can be easily implemented in hardware and achieves the near-optimum in practice.

Synchronous bandwidth allocation for real-time communications with the timed-token MAC protocol

One of the key issues in tailoring the timed-token MAC protocol for real-time applications is synchronous bandwidth allocation (SBA), whose objective is to meet both the protocol and deadline constraints. The former constraint requires that the total time allocated to all nodes for transmitting synchronous messages should not exceed the target token rotation time. The latter constraint requires that the minimum time available for a node to transmit its synchronous messages before their deadlines should be no less than the maximum message transmission time. Several nonoptimal local SEA schemes and an optimal global SBA scheme have been proposed. Local SBA schemes use only information available locally to each node and are thus preferred to global schemes because of their lower network-management overhead. If optimal local SBA schemes, if any, can be devised, they will be superior to their global counterparts both in performance and in ease of network management. In this paper, we formally prove that there does not exist any optimal local SBA scheme. We also propose an optimal global SBA scheme which has an O(nM) polynomial-time worst-case complexity, where n is the number of synchronous message streams in the system and M is the time complexity for solving a linear programming problem with 3n constraints and n variables.

Real-time multicast in wireless communications

This paper presents methods for the reconfiguration of a multicast tree at the instance of node migration in cellular wireless networks. We consider a novel, and highly practical, formulation of the real-time multicast problem. Unlike the traditional notion of source to leaf node message transmission time being the measure for real-time, we consider the multicast tree re-construction time (in the event of a node migration) as the measure for real-time constraints. The overall goal is to minimize both the delays: i) delay of re-constructing the multicast tree and ii) source to destination transmission delay. In this paper, we introduce and provide solutions for the first objective, while the current research in real-time multicast tree considers the latter objective only. We propose two heuristics to solve the real-time multicast tree re-construction problem, one as a foreground and the other as a background algorithm, and present analysis and simulation results for several factors that contribute differently to the re-construction delay.

Configurable algorithms for complete exchange in 2D meshes

The interprocessor complete exchange communication pattern can be found in many important parallel algorithms. In this paper, we present algorithms for complete exchange on 2D mesh-connected multiprocessors. The unique feature of the proposed algorithms is that they are configurable where the time for message startups can be traded against larger message sizes. At one extreme, the algorithm minimizes the number of message startups at the expense of an increased amount of time spent in message transmission. At the other extreme, the time spent in message transmission is reduced at the expense of an increased number of message startups. The structure of the algorithms is such that intermediate solutions are feasible, i.e., the number of message startups can be increased slightly and the message transmission time is correspondingly reduced. The ability to configure these algorithms enables the algorithm characteristics to be matched with machine characteristics based on specific overheads for message initiation and link speeds to minimize overall execution time. In effect, the algorithms can be configured to strike the right balance between direct and message combining approaches on a specific architecture for a given problem size. We believe these algorithms are distinguished by this ability and contribute to efficient portable implementations of complete exchange algorithms.

Scheduling in broadcast networks

Broadcasting in a communications network has been the subject of many studies in recent years. The studies vary in their assumptions governing the behavior of the network and in their objectives with respect to the network. Almost all the work to date uses the unit transmission time assumption, that is, the message transmission times between all pairs of vertices are equal. In this paper, we investigated the broadcast problem under four more general transmission time assumptions. In addition, four different objective functions were considered, including the minimization of (1) the broadcast time (the maximum time for any vertex to receive the message), (2) the average time to receive the message (both with and without ready times at the vertices), (3) the weighted average time to receive the message, and (4) the cycle time. Of the 20 problems thus generated, four admit polynomial time algorithms, 15 are (in the equivalent recognition version) unary NP-complete, and the complexity status of one remains open. All these results are proved, and heuristics with an attainable constant worst-case performance ratio are provided for two of the problems for which polynomial time algorithms are not found. © 1998 John Wiley & Sons, Inc. Networks 32:233–253, 1998

Routing Control Under Uncertainty in Data Networks

A noncooperative game formulation of the routing problem is considered. Every pair of communication networks users is regarded on as a player striving to minimize its message transmission time. Uncertainty in the flow measurements is setvaluedly represented. All players use a worst-case optimization. An equilibrium in Nash sense is called to be optimal solution of the routing problem. The latter is proved to exist. A fast algorithm is proposed to search it. The approach is based on reduction of general network to ring one.

Performance evaluation of message passing strategies and routing policies in multicomputers

This paper describes a discrete-event simulator designed for the analysis of communication switching techniques adopted in distributed memory multicomputers with asynchronous direct links. The motivation comes from the observation that, even if a wide set of routing strategies have been proposed, an extensive comparison analysis among routing strategies working under different workload characteristics is still lacking in the literature. For these purposes, we have designed and implemented a modular simulator, namely IntNetSim, that solves the models of a wide combination of message passing techniques, routing policies, link conflict resolution strategies, and traffic conditions. For each class of instances, a large variety of simulation runs permits us to select the best performance technique that reduces message transmission time and/or retards saturation of the network under definite workload conditions.

Joint admission/congestion control for wireless CDMA systems supporting integrated services

A new data traffic control scheme is developed for maintaining the packet error rate (PER) of real-time voice traffic while allowing nonreal-time data traffic to utilize the residual channel capacity of the multi-access link in an integrated service wireless CDMA network. Due to the delay constraint of the voice service, voice users transmit their packets without incurring further delay once they are admitted to the system according to the admission control policy. Data traffic, however, is regulated at both the call level (i.e., admission control) and at the burst level (i.e., congestion control). The admission control rejects the data calls that will otherwise experience unduly long delay, whereas the congestion control ensures the PER of voice traffic being lower than a specified quality of service (QoS) requirement (e.g., 10/sup -2/). System performance such as voice PER, voice-blocking probability, data throughput, delay, and blocking probability is evaluated by a Markovian model. Numerical results for a system with a Rician fading channel and DPSK modulation are presented to show the interplay between admission and congestion control, as well as how one can engineer the control parameters. The tradeoff of using multiple CDMA codes to reduce the transmission time of data messages is also investigated.

Stochastic model of a cache-coherency overhead in SCI rings

The authors present a new analytical performance model of the IEEE P1596 Standard Coherent Interface, which is a distributed cache-coherency protocol for shared-memory multiprocessors. The paper focuses upon an implementation of the protocol on a unidirectional ring architecture (the ‘default’ architecture for SCI systems). The authors identify the possible memory and cache-line states and corresponding processor actions for a memory access, and derive the equilibrium line state probabilities by solving a Markov model expressed as a set of fixed-point equations. The probabilities of a processor performing a particular action then follow, from which the message transmission profile for each processor is derived. These traffic equations are then fed into an M/G/1 model for the ring architecture, in which the ring traffic at a node has priority over traffic originating in that node. Further analysis then leads to the mean message transmission time, and hence the mean memory access time and processor utilisation. The application of the model is illustrated by undertaking a performance comparison of two alternative node architectures and report some numerical results are reported for various parameterisations.

Using adaptive timeouts to achieve at-most-once message delivery

We extend the at-most-once message delivery algorithm of Liskov, Shrira, and Wroclawski to adapt dynamically to changes in message transmission time and degree of clock synchronization. The performance of their algorithm depends on its being supplied with a good estimate of the maximum message lifetime - the sum of the message delivery time and the difference in processor clock values between sender and recipient. We present two algorithms that are suitable for use in a system where the message lifetime is unknown or may change. Our extensions allow the automatic and continuous determination of a suitable value for the maximum lifetime. We prove that whenever the actual message lifetime is bounded, then our adaptive algorithms converge to an accurate estimate of its true value. Our two algorithms differ in the behavior they require from the network and achieve different performance levels. Our formal statement of convergence is expressed in terms of the number of messages received, rather than time elapsed. We show that this formulation is necessary by proving that no method for estimating the lifetime can achieve convergence in a bounded amount of time.

Unison, canon, and sluggish clocks in networks controlled by a synchronizer

The effect of using a simple synchronizer on the performance of a directed, strongly connected, distributed network, is analysed. In this paper we assume that the time of message transmission is positive but negligible. It is shown that the synchronizer is sufficient to assure that a full rate of computation is achieved in networks with a global clock, in spite of the absence of a global start-up signal. In fact,unison is reached within linear time. A similar phenomenon occurs if there is no global clock, but all local clocks have the same rate. In case the local clocks do not have the same rate, it is shown that the computational rate is not slower than anysluggish clock; i.e., a clock such that between any two of its ticks, every local clock ticks at least once.

Approximate analysis of timer-controlled priority scheme in the single-service token-passing systems

This paper presents an approximate analysis of delay performance in the timer-controlled priority scheme of single-service token passing systems, where each priority queue is allowed to transmit one message at a time. This is the practical case of real-time networks such as those used in aircraft and spacecraft control, process control and factory communications. The token passing systems consist of N stations, each of which has (K+1) priority queues. The highest priority queues can transmit a message whenever the token arrives. A lower priority queue can transmit a message if the token rotation time (which was reset and restarted at the previous token arrival instant) is not expired when the token arrives. An analytical model is developed based on the independent and identically distributed random variables of conditional effective service times (time interval between two consecutive instants at which a priority queue has an opportunity to transmit a message) of each priority queue. The condition is assigned on the basis of the contribution of message transmission time to the effective service time. The approximate mean waiting time for each priority queue is determined using the well-known results from Kuehn (1979), who first introduced the conditional cycle time. The approximate analytical model is validated by comparison with the simulation results.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Performance and parameter region for real-time use in IEEE 802.4 token bus network

The upper and lower bounds for the mean cycle time and the mean message transmission time of class six and class four in the IEEE 802.4 token bus network, within which the minimum utilization constraint of class four is guaranteed, are derived. Stability conditions for the token bus network are also derived. These bounds and stability conditions are represented in terms of the high-priority token hold time, the token rotation time, the arrival rate, the total number of stations, etc. A parameter-tuning algorithm in a partially symmetric token bus network with two classes is suggested. This algorithm maximizes the utilization of class four for a given high-priority token hold time and at the same time meets the constraints of the stability condition of the network, the real-time constraint, and the minimum utilization of class four. >

Hypercube clock synchronization

AbstractAlgorithms for synchronizing the times and frequencies of the clocks of Intel and Ncube hypercube multiprocessors are presented. Bounds for the error in estimating clock offsets and frequencies are formulated in terms of the clock read error and message transmission time. Clock and communication performance of the Ncube and Intel hypercubes are analysed, and performance of the synchronization algorithms is presented.

Communication protocols with untraceability of sender and receiver

Previous research on information security has focused on the protection of the contents of messages. But in many cases it is equally important to protect the identities of the sender and receiver and also the time of message transmission. This paper proposes communication protocols which make it impossible both for the entities other than the right receiver to decipher the message and for any third party to identify the communicating entities. Since it is impossible in these protocols for any third party to identify the communicators, the protocols are classified into four groups according to whether or not the communicating pair can identify each other. In addition, the security, the implementability, and the mutual relationship of these four kinds of communication protocols are studied.