The recent introduction of powerful special purpose semiconductor digital signal processing (DSP) circuits allows the implementation of complex and high performance communications functions. Specifically, the integrat...
详细信息
The recent introduction of powerful special purpose semiconductor digital signal processing (DSP) circuits allows the implementation of complex and high performance communications functions. Specifically, the integration of such DSP circuits provides high speed communications capabilities to workstations and personal computers (PCs) for communication across the public switching telephone network (PSTN). The Motorola DSP56000 and DSP56300 family members of DSP circuits, designed as V.34 Plus data/V.17 fax/voice data pump modems, efficiently implement such functions. A data pump is a self-contained function block implemented with a combination of DSP circuitry and internal memory, that requires an analog front end and an external processor for control, but no additional user software programming is required. The data pump is responsible for the signal modulation and demodulation, coding, low level training, line equalization, echo canceling and the many other layer one (and part of layer two) functions such as those required by the V.34 Plus data modem and V.17 fax standards. By the simple addition of a DSP data/fax/voice pump, workstations and PCs can communicate with data resources such as electronic mail systems, bulletin boards, public data bases, internet Service Providers (ISPs), corporate data bases, distant local area networks (LANs) and other PCs. Workstations and PCs now not only have the ability to be linked via a high speed V.34 Plus telephone modem but also provide many additional functions such as a telephone dialer, a telephone answering machine, a hands-free speakerphone, and a facsimile machine amongst others. Further, users can implement a direct digital modem (DDM) efficiently connecting an Integrated Services Digital networks Services (ISDN) terminal adapter (TA) either to a far-end ISDN TA, or an analog modem which normally requires significant and complex circuitry. Similarly, the implementation of a "modem pool" is now implemented in a cost effe
We suggest the M|G|/spl infin/ input process as a viable model for network traffic due to its versatility and tractability. We characterize the process as short- or long-range dependent by means of a simple test. To g...
详细信息
We suggest the M|G|/spl infin/ input process as a viable model for network traffic due to its versatility and tractability. We characterize the process as short- or long-range dependent by means of a simple test. To gauge its performance, we study the large buffer asymptotics of a multiplexer driven by an M|G|/spl infin/ input process. The decay rate of the tail probabilities for the buffer content (in steady-state) is investigated using large deviations techniques suggested by Duffield and O'Connell (see Mathematical Proceedings of the Cambridge Philosophical Society, no.118, p.363-74, 1995). We show that the selection of the appropriate large deviations scaling is related to the forward recurrence time of the service time distribution, and a closed-form expression is derived for the corresponding generalized limiting log-moment generating function associated with the input process. We apply our results to cases where the service time distribution in the M|G|/spl infin/ input model is (i) Rayleigh, (ii) gamma, (iii) geometric, (iv) Weibull, (v) log-normal and (vi) Pareto-cases (v) and (vi) have been found adequate for modeling packet traffic streams in certain networking applications. Finally, we comment on the insufficiency of the short- vs. long-range dependence characterization of an input process as a means to accurately describe the corresponding buffer dynamics.
internet programming languages, such as Java, have the potential to address many problems inherent in military networking, and are particularly suitable for networkcontrol applications. However, issues of security an...
详细信息
ISBN:
(纸本)0780336836
internet programming languages, such as Java, have the potential to address many problems inherent in military networking, and are particularly suitable for networkcontrol applications. However, issues of security and performance arise immediately. By placing the code for a control application at the Remote control Unit (RCU) that services a network element any user needing to access the element can connect to the RCU and receive the current version of the user interface for immediate execution on the user's local platform. Ensuring that the user is authorized to access an element, that the interface delivered to the user has not been altered, and that the interface can be transferred without unacceptable delays is problematic for network elements that are located on the battlefield and connected to the network through low speed channels. To evaluate the potential and problems associated with internet programming fools, Electrospace has constructed a Monitor and control Applique' (MCA), using Java, for the Electrospace secure digital switch family. Security and performance issues have been assessed against advantages in logistics, distributed control and survivability.
The one of the problems that arise in the satellite packet communication system is the existence of a long access timing delay. In this paper, we clarify the effect of this access timing delay on the performance of CD...
详细信息
ISBN:
(纸本)0780333365;0780333373
The one of the problems that arise in the satellite packet communication system is the existence of a long access timing delay. In this paper, we clarify the effect of this access timing delay on the performance of CDMA ALOHA systems and then propose a new access control protocol, called Modified Channel Load Sensing Protocol (MCLSP), for the CDMA ALOHA systems. As a result, we found that by employing MCLSP, a significant improvement in the throughput performance was obtained even in the presence of a long access timing delay.
In previous work, we proposed to enhance TCP's congestion control mechanisms using binary congestion notification (BCN). With this combined scheme called BCN-TCP, congestion is indicated both by packet losses and ...
详细信息
ISBN:
(纸本)0818674539
In previous work, we proposed to enhance TCP's congestion control mechanisms using binary congestion notification (BCN). With this combined scheme called BCN-TCP, congestion is indicated both by packet losses and by having switches inform sources about their congestion stale by setting a congestion bit. Unlike other studies, our approach maintains the basic elements of TCP's congestion control mechanisms and models the response of TCP to the congestion bit to that of the ATM available bit rate service (ABR). We compared the performance of BCN-TCP to the versions currently implemented in hosts (Tahoe and Reno TCP). However BCN-TCP only offered significant performance improvements if part of the path contained ATM ABR services. In this paper, we present further results an the performance of BCN-TCP when used in heterogeneous environments, i.e., internet paths where only some end systems support BCN-TCP. We also consider the fairness between long and short-hard connections and discover that BCN-TCP treats long-haul connections worse than Tahoe and Reno TCP. We investigate the cause of this unfairness and suggest possible remedies.
Recently, optical ATM switches, composed of optical switches, fiber delay lines and other devices, have been proposed by researchers world-wide as a way of overcoming the EMI, pinout and interconnection problems that ...
详细信息
ISBN:
(纸本)0819423211
Recently, optical ATM switches, composed of optical switches, fiber delay lines and other devices, have been proposed by researchers world-wide as a way of overcoming the EMI, pinout and interconnection problems that would be encountered in future large electronic switch cores. Attaining the size of buffers in optical ATM fabrics that would be required in practice is a major problem; in this paper, an architectural solution is presented. A technique is introduced for cascading many small switches to form a bigger switch with a larger buffer depth. A special feature of this scheme is that the number of cascaded switches is proportional to the logarithm of the buffer depth, providing an economical and feasible hardware solution. Architectural concepts are discussed and justified mathematically, and an electronic control scheme is introduced. Cell loss and delay performance, and buffer dimensioning are considered. The performance in terms of crosstalk and noise will be covered in a companion paper. In conclusion, it is clear that optical switching elements, with a buffer depth of several hundred required for bursty traffic, can be constructed using fewer components than other schemes, and, by implication, better noise and crosstalk performance.
This paper proposes a MAC protocol for 2D grid networks, termed slotted grid protocol (SGP), for high speed LANs/MANs. To support high speed transmission and all- optical operation, intermediate routing and buffering ...
详细信息
ISBN:
(纸本)0819423211
This paper proposes a MAC protocol for 2D grid networks, termed slotted grid protocol (SGP), for high speed LANs/MANs. To support high speed transmission and all- optical operation, intermediate routing and buffering is avoided. SGP combines the linear optical network concepts with 2D grid topology. It employs prefixed slotting and routing mechanisms, consequently resulting in scalable, all- optical or almost-all-optical techniques that results in high performance. SGP consists of two layers. The lower layer is slotted ring based protocol which employs two uni- directional trains to transport the packets along each of the merged rings which connect a group of nodes in the network. The upper layer is a token driven protocol which is to control the merging process so that al nodes are involved in the transmission simultaneously and every node can get a chance to work as a merging node. Multiple-queue strategy is adapted to realize the one-cycle full inter-connection on a unidirection ring. The multiple-queue strategy makes also the benefits for balancing the traffic load of the network, and for eliminating the head-queue effects. Consequently extendable capacity of the network and wider effective traffic load range are achieved based on the same node configuration and network configuration as that of the linear protocol, such as DQDB. The primary properties of the SGP are modeled and analyzed based on polling system principles. Simulation results are presented in this paper, which includes the comparison of the performance of SGP with that of DQDB.
The software agent paradigm is a promising technique for developing complex software systems. By evolving control code for agents with a genetic algorithm (GA), it promises to allow agents to adapt their behaviour to ...
详细信息
ISBN:
(纸本)0780333373
The software agent paradigm is a promising technique for developing complex software systems. By evolving control code for agents with a genetic algorithm (GA), it promises to allow agents to adapt their behaviour to local network conditions, and hence re-program themselves as circumstances change. Current work has focussed on studying the performance of evolved agent behaviours on two search problems.
A new ATM service category, the Available Bit Rate service, has been introduced in the ATM Forum. It dynamically allocates available bandwidth to users by controlling the flow of user traffic with feedback. The Forum ...
详细信息
ISBN:
(纸本)0780333373
A new ATM service category, the Available Bit Rate service, has been introduced in the ATM Forum. It dynamically allocates available bandwidth to users by controlling the flow of user traffic with feedback. The Forum hus ratified the rate-based flow control framework for the support of this new service. In this paper we provide a recipe for designing rate-based feedback schemes demonstrating the rich variety of available switch mechanisms. Each aspect of the feedback control loop mechanism is explored in detail and several available choices are investigated Two example switch mechanisms are provided that illustrate the rate-based control design principles. The ability of these mechanims to support the desired objectives of an ABR service is compared using a reference network configuration. Simulation results show that the rate-based framework allows a great degree of architectural flexibility in the design of switch mechanisms. The rate-based framework provides switch vendors sufficient flexibility to choose a mechanism among several available options, based on their performance requirements and cost budgets.
Frequency chirp in modulator devices is of increasing importance at higher bit rates and increased transmission distances. The chirping behavior of reflective, resonant electroabsorptive optical modulators is analyzed...
详细信息
ISBN:
(纸本)0819423211
Frequency chirp in modulator devices is of increasing importance at higher bit rates and increased transmission distances. The chirping behavior of reflective, resonant electroabsorptive optical modulators is analyzed and compared to the non-resonant case for a Framz-Keldysh effect based device. The chirp is found to display oscillatory behavior which is explained by the interaction of the electric field induced changes in complex refractive index with the cavity. The effect of a front face reflectivity lower than that for matching is shown to be poorer modulation and chirping performance. If the front face reflectivity is greater than that needed to match then negative chirp is possible but the insertion loss is greater than 8 dB. By fine tuning the length of the device it is shown that this can be reduced to 3 dB producing a contrast ratio of 4.5 dB and -500 MHz chirp for 400 ps, 15V pulses.
暂无评论