Improving Computer Network Performance by Using Knowledge Discovery

During the past decade, the computer world has been changing a dramatic change in many aspects. In the past, personal computer was known as a desktop machine that functioned alone. All the resources, data, and computing power were within the same machine. However, in the network world today, more and more computers are connected together through the media to share data and resources or parallel the computation. The necessity to evaluate the performance of these computer networks has been recognized for a long time. Performance measurement has been significantly important to computer networks designers, administrators, and analysts to justify the impact of a new design or change compared to existing system. On the other hand, this information is also important to the users or customers to evaluate different systems from different vendors to determine whether their needs can be fulfilled, and to measure the performance of the running network Overall network performance is integration between two categories networkrelated like packet size, throughput, delay time and workstationrelated category like CPU utilization, memory utilization, resource response time, resource utilization. By recording all the events triggered in the network workstations using network monitoring tools we have a very large number of records that describe in details the network characteristics. By analyzing and mining this large amount of data we will get valuable information and extract a hidden predictive knowledge that will guide network administrators how to adjust different network parameters and adjust hardware and software resources attributes.