Swarm intelligence: from natural to artificial systems
Swarm intelligence: from natural to artificial systems
Biologically inspired self-adaptive multi-path routing in overlay networks
Communications of the ACM - Self managed systems
A taxonomy of biologically inspired research in computer networking
Computer Networks: The International Journal of Computer and Telecommunications Networking
Attractor selection and perturbation for robust networks in fluctuating environments
IEEE Network: The Magazine of Global Internetworking - Special issue on biologically inspired networking
Bio-inspired networking: from theory to practice
IEEE Communications Magazine
| Hi-index | 0.00 |
Computer networks have become highly complicated and less flexible to handle emerging problems which often occur nowadays. In order to cope with unpredictable problems, the concept of biologically inspired networks has been introduced, which provides a high degree of robustness and adaptability to computer networks. However, the performance of the network often relies heavily on the configurable parameters assigned during the deployment process, where end nodes cannot change these parameters during runtime to achieve the desirable performance. In this paper, we introduce a new method, called attractor perturbation (AP) allowing end nodes to influence the average of an observable performance metric at runtime without directly manipulating any optimal parameters of underlying protocols. An example application in this paper is a traffic distribution over multi-path routing protocol in MANETs, where the target variable is end-to-end delay. The approach to solve for the appropriate amount of management influence and simulation results are shown in this paper.