PROSPECTS FOR THE USE OF ARTIFICIAL-INTELLIGENCE IN REAL-TIME NETWORK TRAFFIC MANAGEMENT

This paper describes results and plans for further work in the development of a proposed real-time network management system using a combination of conventional optimisation techniques and artificial intelligence (AI). The objective of the proposed system is to achieve the best possible performance from a circuit-switched network under adverse conditions (particularly traffic overload or equipment failure). It is proposed to develop a real-time AI system which will suggest good control actions quickly, and which will use a combination of conventional optimisation and AI to fine-tune the controls. The design of the proposed system, and its present state of development are described.