Computer Networks (1976)最新文献

For voice transmissions in a local-area network, it is desirable to have a small coefficient of variation for the interdeparture time of voice packets at the destination. This may be achieved by the proper design of the medium access protocol. A token ring protocol with provision for voice traffic is considered. An analytic model is developed to study the performance of this protocol with respect to voice traffic. Numerical results showing the effect of model parameters on interdeparture time are presented.

The CCITT Draft Recommendation S.a defines the Document Interchange Protocol for the Telematic Services. This protocol allows for the interchange of mixed text and facsimile documents by means of Teletex Mixed Mode and Group 4 Facsimile Terminals. The concept for the structuring of documents, which are based on the ISO/ECMA work on Office Document Architecture, and the concepts for the formal specification and the encoding of protocol elements, which are based on the CCITT Presentation Transfer Syntax for Message Handling Systems, are described.

Quantitative evaluation of availability in distributed database systems must take into account both hardware and software failures. Therefore parameters such as the failure and the recovery probabilities must be evaluated for each “component” of the system.

The most difficult problems arise when the evaluation procedure has to deal with failure mechanisms which functionally depend on the state of the system.

In this paper, after a short introduction to a general methodology for availability evaluation, an example of state-dependent fault mechanism is described together with a technique for evaluating its impact on the life of the whole system.

Telecommuting, working at home through a data terminal/micro processor, is feasible with today's technology. However, it has profound consequences for individuals, organizations, and society, particularly in widespread application. This paper explores the major impacts of telecommuting and suggests further areas for research.

Simulation results of three adaptive, decentralized controlled job scheduling algorithms which assume absolutely no a priori knowledge about jobs are presented. The results provide insight into the workings and relative effectiveness of the three algorithms, as well as insight into the performance of a special type of decentralized control. The simulation approach includes tuning the parameters of each algorithm, and then comparing the three algorithms based on response time, load balancing and the percentage of job movement. Each of the algorithm is compared under light, moderate, and heavy loads in the system, as well as a function of the traffic in the communication subnet and the scheduling interval. Modifications to the models are then introduced to further investigate the impact of various other parameters such as the cost of the scheduling algorithm itself, the effect of highly degraded state information and eliminating the movement of large (in size) jobs. Three simple analytical models are also presented and compared to the simulation results. A general observation is that, if tuned correctly, the decentralized algorithms exhibit stable behavior and considerably improve performance (response time and load balancing) at modest cost (percentage of job movement and algorithm execution cost).