A Knowledge Driven Approach to Congestion Control

Abstract

A new approach for network congestion control is discussed in this paper. By using artificial intelligence methods in network congestion control, a novel knowledge driven approach is introduced to tackle the congestion control problem. Different from conventional approaches, the knowledge driven approach focuses on knowledge manipulation and organisation to generate congestion control algorithms. An expert-system-based congestion control framework used to organise knowledge is proposed, and its application in solving TCP inter-flavour-friendliness problem is discussed. It is to shown that the knowledge driven approach has potentials in: 1) improving the performance of existing congestion control algorithm; 2) tackling congestion control problem in varying and uncertain environments by constructing complex congestion controller in an easy and reliable way