ANT-BASED LOAD BALANCING IN TELECOMMUNICATIONS NETWORKS

This article describes a novel method of achieving load balancing in t elecommunications networks. A simulated network models a typical distr ibution of calls between nodes; nodes carrying an excess of traffic ca n become congested causing calls to be lost. In addition to calls, the network also supports a population of simple mobile agents with behav iors modeled on the trail-laying abilities of ants. The ants move acro ss the network between randomly chosen pairs of nodes; as they move, t hey deposit simulated pheromone as a function of their distance from t heir source node and the congestion encountered on their journey. They select their path at each intermediate node according to the distribu tion of simulated pheromone at each node. Calls between nodes are rout ed as a function of the pheromone distributions at each intermediate n ode. The performance of the network is measured by the proportion of c alls that are lost. The results of using ant-based control (ABC) are c ompared with those achieved by using fixed shortest-path routes, and a lso those achieved by using an alternative algorithmically based type of mobile agent previously proposed for use in network management. The ABC system is shown to result in fewer call failures than the other m ethods, while exhibiting many attractive features of distributed contr ol.