A multi-agent system for intelligent network load control using a market-based approach

Contemporary shifts in the nature of intelligent networks (IN) have both made the problem of IN load control increasingly important and have pointed towards agent technology as an appropriate solution to that problem. In this paper we present a multi-agent system, comprised of intelligent, autonomous and self-interested agents, which makes use of a market-based approach to perform real-time control of IN traffic. The algorithm is assessed against the benchmark automatic call capping (ACG) algorithm; the agent implementation is assessed in terms of its suitability to market-based IN load control. Simulation results show that the algorithm is capable of better performance in terms of generated network revenue when compared against ACG. We conclude that the engineering abstraction provided by agents, coupled with the distribution of autonomous decision-making, give a better granularity for fine-grained control of network components