Decentralized optimization of wireless sensor network lifetime based on neural network dynamics

The wireless sensor networks, which collect various data from a physical environment, are usually defined as an ad hoc network consisted of a huge number of tiny wireless sensor nodes whose computing power and battery capacity are limited. Because it is difficult to replace all of batteries on such a huge number of sensor nodes, maximization of the lifetime of the network has been one of the important research issues. To optimize such a network with a huge number of the sensor nodes, autonomous and decentralized computing and reconfiguration schemes can be considered suitable. Therefore, in this paper, we propose a routing reconfiguration method based on an autonomous optimization dynamics of the mutually connected neural network which minimizes its own energy function with autonomous and distributed computing. We show that the proposed method can optimize the routes for maximizing the lifetime of the sensor network, without any centralized computing nodes.

[1]  Hiroshi Harada,et al.  Autonomous and Decentralized Optimization of Large-Scale Heterogeneous Wireless Networks by Neural Network Dynamics , 2008, IEICE Trans. Commun..

[2]  Leandros Tassiulas,et al.  Routing for network capacity maximization in energy-constrained ad-hoc networks , 2003, IEEE INFOCOM 2003. Twenty-second Annual Joint Conference of the IEEE Computer and Communications Societies (IEEE Cat. No.03CH37428).

[3]  Wendi Heinzelman,et al.  Proceedings of the 33rd Hawaii International Conference on System Sciences- 2000 Energy-Efficient Communication Protocol for Wireless Microsensor Networks , 2022 .

[4]  Kazuyuki Aihara,et al.  Solving combinatorial optimization problems by nonlinear neural dynamics , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[5]  Mikio Hasegawa,et al.  User-Centric Optimum Radio Access Selection in Heterogeneous Wireless Networks Based on Neural Network Dynamics , 2008, 2008 IEEE Wireless Communications and Networking Conference.

[6]  John J. Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities , 1999 .

[7]  J. J. Hopfield,et al.  “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.

[8]  Hiroshi Nozawa,et al.  A neural network model as a globally coupled map and applications based on chaos. , 1992, Chaos.

[9]  D. E. Van den Bout,et al.  Improving the performance of the Hopfield-Tank neural network through normalization and annealing , 1989, Biological Cybernetics.

[10]  James H. Aylor,et al.  Computer for the 21st Century , 1999, Computer.

[11]  Sartaj Sahni,et al.  An online heuristic for maximum lifetime routing in wireless sensor networks , 2006, IEEE Transactions on Computers.

[12]  E. Aarts,et al.  Boltzmann machines for travelling salesman problems , 1989 .

[13]  Mark Weiser,et al.  The computer for the 21st Century , 1991, IEEE Pervasive Computing.

[14]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.