A KNOWLEDGE-BASED OPERATION SUPPORT SYSTEM FOR NETWORK TRAFFIC MANAGEMENT

The operation of a telephone network is subject to unexpected continge ncies such as facilities impairments, trunk congestion, and focused ov erload. When contingencies happen in the network, the proper control a ctions must be taken promptly within a short period of time (e.g. 5 mi nutes); otherwise, the serious congestion will soon spread to the othe r parts of network. Until now, there has been a lack of an automated a pproach to generate a contingency routing plan to prevent network degr adation. In this paper, a knowledge-based traffic control support syst em (TRACOSS) is proposed for network traffic management. TRACOSS not o nly contains four knowledge bases to accumulate the domain expertise u sed for contingencies detection, diagnosis, affected traffic estimatio n and control commands generation, but also contains a multicommodity network flow model to formulate the operation of telephone network. Ba sed on this model, a heuristic algorithm is developed to design the co ntingency routing plan. TRACOSS has the following advantages: (1) The acceptable contingency plan can be obtained by the heuristic algorithm within the fixed time constraint. (2) Four knowledge bases can be use d to accumulate the domain expertise to automate the network traffic m anagement. (3) When new network components are installed, knowledge ba ses can be easily upgraded to adapt new technologies.