Expert System Based Network Testing

Abstract

Networks today are not isolated entities as local-area networks (LAN) are often connected across campuses, cities, states, countries, or even continents by wide-area networks (WAN) that are just as diverse in their hardware interfaces and software protocols as LANs and may consist of multiple technologies including, too. Protocols are implemented in combinations of software, firmware, and hardware on each end of a connection. The state-of-the-art networking environment usually consists of several network operating systems and protocol stacks executing. A particular protocol stack from any manufacturer should inter-operate with the same kind of protocol stack from any other manufacturer because there are protocol standards that the manufacturers must follow. For example, the Microsoft Windows® TCP/IP stack should inter-operate with a Linux TCP/IP stack. Connections can be peer to peer, client to server, or the communications between the network components that create or facilitate connections such as routers, hubs, and bridges [1]. As converged IP networks become widespread, increasing network services demand more intelligent control over bandwidth usage and more efficient application development practices to be implemented, such as traffic shaping, quality-of-service (QoS) techniques etc. So, there is a growing need for efficient test tools and methodologies that deal with application performance degradation and faults. Network professionals need to quickly isolate and repair complex and often intermittent performance problems in their network and effectively hand over problems that are outside the network domain to the appropriate internal group or external vendor. Among the key technologies that are used for a variety of critical communication applications, we face a rapid growth of network managers’ concerns, as sometimes they find their networks difficult to maintain due to high speed operation, emerging and escalating problems in real time and in a very complex environment such as: incorrect device configuration, poorly architectured networks, defective cabling or connections, hardware failures etc. On the other hand, some problems do not cause hard failures, but instead may degrade network performance and go undetected. In particular, network management in such a diverse environment encompasses processes, methods and techniques designed to establish and maintain network integrity. In addition to its most important constituent fault management, network management includes other activities as well, such as configuration management of overall system hardware and software components, whose parameters must be maintained and updated on regular basis.