An Approach Based on Swarm Intelligence for Event Dissemination in Dynamic Networks

Abstract

Dynamic networks require adaptive strategies for information dissemination, as the topology constantly changes. This work presents an event-based bio-inspired dissemination approach that employs ants, which correspond to mobile agents, to spread information throughout the network. An event is defined as a state transition of a node or link. A node which detects an event in its neighborhood triggers the dissemination. Pheromones are used to both control the ant population and help to define the paths that the agents take. An empirical study was performed, in which the proposed strategy was compared with flooding and gossip algorithms. Results show that the proposed strategy presents a good trade-off between the time required to disseminate information and the overhead in terms of the number of messages employed.