ABSTRACT
Wireless Sensor Actuator Networks (WSANs) extend wireless sensor networks through actuation capability. Designing robust logic for WSANs however is challenging since nodes can affect their environment which is already inherently complex and dynamic. Fixed (offline) logic does not have the ability to adapt to significant environmental changes and can fail under changed conditions. To address this challenge, we present In situ Distributed Genetic Programming (IDGP) as a framework for evolving logic post-deployment (online) and implement this framework on a physically deployed WSAN. To demonstrate the features of the framework including individual, cooperative and heterogeneous evolution, we apply it to two simple optimisation problems requiring sensing, communications and actuation. The experiments confirm that IDGP can evolve code to achieve a system wide objective function and is resilient to unexpected environmental changes.
- I. Akyildiz and I. Kasimoglu. Wireless sensor and actor networks: Research challenges. In Ad Hoc Networks Journal, volume 2, no. 4, pages 351--367. 2004.Google ScholarCross Ref
- P. A. N. Bosman and H. L. Poutré. Learning and anticipation in online dynamic optimization with evolutionary algorithms: The stochastic case. In Proc 9th Ann Conf on Genetic and Evolutionary Computation, pages 1165--1172, 2007. Google ScholarDigital Library
- D. Floreano and F. Mondada. Automatic creation of an autonomous agent: Genetic evolution of a neural-network driven robot. In Proc 3rd Int Conf on Simulation of Adaptive Behavior, 1994. Google ScholarDigital Library
- S. Hettiarachchi. Distributed online evolution for swarm robotics. Presented at Autonomous Agents and Multi Agent Systems, Doctoral Mentoring Program, 2006.Google Scholar
- S. Hettiarachchi, W. Spears, W. Kerr, D. Zarzhitsky, and D. Green. Distributed agent evolution with dynamic adaptation to local unexpected scenarios. In Proc. Second GSFC/IEEE Workshop on Radical Agent Concepts. Springer-Verlag, 2006. Google ScholarDigital Library
- J. H. Holland. Escaping brittleness: The possibilities of general-purpose learning algorithms applied to parallel rule-based systems. In T. M. M. Ryszard S. Michalski, Jaime G. Carbonell, editor, Machine learning: An artificial intelligence approach, volume II, pages 593--623. Morgan Kaufmann, 1986.Google Scholar
- J. H. Holland. Adaptation in Natural and Artificial Systems. MIT Press, Cambridge, MA, USA, 1992. Google ScholarDigital Library
- D. M. Johnson, A. Teredesai, and R. T. Saltarelli. Genetic programming in wireless sensor networks. In 8th European Conf onGenetic Programming, LNCS 3447, pages 96--107, 2005. Google ScholarDigital Library
- J. Koza. Genetic Programming: On the Programming of Computers by Means of Natural Selection. MIT Press, 1992. Google ScholarDigital Library
- W. Martin, J. Lienig, and J. Cohoon. Population structures: island (migration) models: evolutionary algorithms based on punctuated equilibria. In Back, Fogel, and Michalewicz, editors, Evolutionary Computation, chapter 6.3:1--6.3:16. Institute of Physics Publishing, Oxford University Press, New York, 1997.Google Scholar
- G. Nan and M. Li. Evolutionary based approaches in wireless sensor networks: A survey. In Fourth International Conference on Natural Computation, volume 5, pages 217--222, 2008. Google ScholarDigital Library
- H. N. Pham, D. Pediaditakis, and A. Boulis. From simulation to real deployments in wsn and back. In Proc. IEEE Int. Symposium on a World of Wireless, Mobile and Multimedia Networks, pages 1--6, June 2007.Google ScholarCross Ref
- J. Pintér. Global optimization: Software, test problems, and applications. In P. Pardalos and H. Romeijn, editors, Handbook of Global Optimization, volume 2, chapter 15, pages 515--569. Kluwer Academic Publishers, Dordrecht Boston London, 2002.Google ScholarCross Ref
- R. Poli, W. B. Langdon, and N. F. McPhee. A field guide to genetic programming. Published via http://lulu.com and freely available at http://www.gp-field-guide.org.uk, 2008. Google ScholarDigital Library
- Q. Qiu, Q. Wu, D. Burns, and D. Holzhauer. Lifetime aware resource management for sensor network using distributed genetic algorithm. In Proc. of the Int. symposium on Low power electronics and design, pages 191--196. New York, NY, USA, 2006. Google ScholarDigital Library
- P. Sikka, P. Corke, L. Overs, P. Valencia, and T. Wark. Fleck - a platform for real-world outdoor sensor networks. In 3rd International Conference on Intelligent Sensors, Sensor Networks and Information, pages 709--714. 2007.Google ScholarCross Ref
- A. Silva, A. Neves, and E. Costa. Evolving controllers for autonomous agents using genetically programmed networks. In Proc. 2nd European Workshop on Genetic Programming, LNCS 1598, pages 255--269. Springer-Verlag, 1999. Google ScholarDigital Library
- T. Wark, P. Corke, P. Sikka, L. Klingbeil, Y. Guo, C. Crossman, P. Valencia, D. Swain, and G. Bishop-Hurley. Transforming agriculture through pervasive wireless sensor networks. Pervasive Computing, IEEE, 6(2):50--57, April-June 2007. Google ScholarDigital Library
- T. Weise and K. Geihs. Genetic programming techniques for sensor networks. In P. J. Marron, editor, Proceedings of 5. GI/ITG KuVS Fachgesprach Drahtlose Sensornetze, pages 21--25. University of Stuttgart, Stuttgart, Germany, 2006.Google Scholar
- D. H. Wolpert and W. G. Macready. No free lunch theorems for search. In Technical report TR-95-02-010. Santa Fe Institute, Sante Fe, NM, USA, 1995.Google Scholar
Recommendations
Distributed Coordinate-free Boundary Nodes Identification in Wireless Sensor Networks
Q2SWinet '17: Proceedings of the 13th ACM Symposium on QoS and Security for Wireless and Mobile NetworksIn a wireless sensor network (WSN), coverage holes may appear due to sensor random deployment or node failure. They may restrain the network from providing comprehensive and quality data for end users. In order to heal the coverage holes, the network ...
Fitness importance for online evolution
GECCO '10: Proceedings of the 12th annual conference companion on Genetic and evolutionary computationTo complement standard fitness functions, we propose "Fitness Importance" (FI) as a novel meta-heuristic for online learning systems. We define FI and show how it can be used to dynamically bias the population composition in order to vary the ...
Energy Efficient Distributed Face Recognition in Wireless Sensor Network
Face recognition enhances the security through wireless sensor network and it is a challenging task due to constrains involved in wireless sensor network. Image processing and image communication in wireless sensor network reduces the life time of ...
Comments