earticle

영어

This paper discusses distributed processing systems to be applied to design the Education and research Computer Network. Especially, we have analyzed performance measures of computer communication networks, have solved the capacity assignment problem approximately, and have presented two algorithms by which we could decide the efficient topology of a computer communication network. In general, computer networks can be modelled by appropriate queueing models on the basis of queueing theory. But in that case we must consider several performance measures carefully to estimate the performance of the model of a computer network. In this paper, we have analyzed some important performance measure - time delay, line cost, and routing strategy. According to queueing theory, we can get optimal solutions of the network optimization problems. However, if we are to use this method we should know a great deal of data, and so it is time-consuming to find the analytic optimal solutions. In this paper, we have introduced the inefficient index(I) to describe another method - approximate method - of solving the capacity assignment problem. Meanwhile, we have presented two algorithms by which the efficient network topology can be extracted. In other words, this paper has shown construct the Education and Research Computer Network, which is one of the Five Main National Computer Networks, and we can expect it might be applied to the implementation of other computer networks. the design method of the network topology satisfying suitable utilities and costs of processors, which are components of a computer network, under the given design constraints. With applying those algorithms to the computer network including several distributed database systems, we have presented a case study. In conclusion, this paper has provided a theoretical background to