수정된 홉필드 신경망을 이용한 최단 경로 라우팅 알고리즘

A Shortest Path Routing Algorithm using a Modified Hopfield Neural Network

  • 안창욱 (광주과학기술원 정보통신공학과) ;
  • ;
  • 최인찬 (고려대학교 산업시스템정보공학과) ;
  • 강충구 (고려대학교 전파통신학과)
  • Ahn, Chang-Wook (Dept. of Information Communication Engineering, Gwangju Institute of Science and Technology) ;
  • Ramakrishna, R.S. (Dept. of Information Communication Engineering, Gwangju Institute of Science and Technology) ;
  • Choi, In-Chan (Dept.of Industry System Information Engineering, Korea University) ;
  • Kang, Chung-Gu
  • 발행 : 2002.08.01

초록

본 논문은 신경망을 이용한 최단 경로 문제를 풀기 위해 흡필드 신경망(Hopfield Neural Network)을 변형한 준최적 라우팅 알고리즘(suboptimal routing algorithm)을 다룬다. 이 알고리즘은 기존의 흡필드 신경망 알고리즘과는 달리 뉴런(neuron)의 진화를 위해 모든 주변 뉴런 정보뿐만 아니라, 상관 관계성이 높은 자신의 뉴런 정보도 동시에 이용함으로써, 수렴 성능 및 경로의 최적성을 향상하고자 하였다. 이 알고리즘의 수렴 속도는 흡필드 신경망을 이용하는 기존의 알고리즘보다 더 우수하며, 탐색 경로의 최적성도 높다는 것을 컴퓨터 시뮬레이션을 통해 확인한다. 이 결과는 거의 모든 출발지와 도착지 쌍에 대해 기존의 흡필드 신경망 기반의 최단 경로 탐색 알고리즘에 비해 네트워크 토폴로지에 비교적 덜 민감한 것으로 나타난다. 따라서, mobile ad-hoc network과 같이 네트워크 토폴로지가 시변하는 다중-흡 무선 패킷망(Multi-hop Packet Radio Network)에서의 경로 설정 알고리즘을 구현하는데 유용할 것으로 보인다.

This paper presents a neural network-based near-optimal routing algorithm. It employs a modified Hopfield Neural Network (MHNN) as a means to solve the shortest path problem. It uses every piece of information that is available at the peripheral neurons in addition to the highly correlated information that is available at the local neuron. Consequently, every neuron converges speedily and optimally to a stable state. The convergence is faster than what is usually found in algorithms that employ conventional Hopfield neural networks. Computer simulations support the indicated claims. The results are relatively independent of network topology for almost all source-destination pairs, which nay be useful for implementing the routing algorithms appropriate to multi -hop packet radio networks with time-varying network topology.

키워드

참고문헌

  1. W. Stalling, High-Speed Networks: TCP/IP and ATM Design Principles, Prentice Hall, Inc., 1998
  2. H. E. Rauch and T. Winarske, 'Neural Networks for Routing Communication Traffic,' IEEE Control Systems Magazine, vol. 8, pp. 26-31, April 1988 https://doi.org/10.1109/37.1870
  3. L. Zhang and S. C. A. Thomopulosm, 'Neural Networks Implementation of Shortest Path Algorithm for Traffic Routing in Communication Networks,' Proceedings of Joint Conference on Neural Networks, p. 591, 1989 https://doi.org/10.1109/IJCNN.1989.118375
  4. S. L. Lee and S. Chang, 'Neural Networks for Routing of Communication Networks with Unreliable Components,' IEEE Transactions on Neural Networks, vol. 5, no. 5, pp. 854-863, September 1993 https://doi.org/10.1109/72.248462
  5. M. K. M. Ali and F. Kamoun, 'Neural Networks for Shortest Path Computation and Routing in Computer Networks,' IEEE Transactions on Neural Networks, vol. 4, no. 6, pp. 941-954, November 1993 https://doi.org/10.1109/72.286889
  6. J. E. Wieselthier, C. M. Barnhart and A. Ephremides, 'A Neural Network Approach to Routing without Interference in Multihop Radio Networks,' IEEE Transactions on Communications, vol. 42, no. 1, pp. 166-177, January 1994 https://doi.org/10.1109/26.275311
  7. D. C. Park and S. E. Choi, 'A Neural Network based Multi-destination Routing Algorithm for Communication Network,' Proceedings of Joint Conference on Neural Networks, pp. 1673-1678, 1998 https://doi.org/10.1109/IJCNN.1998.686030
  8. D. W. Tank and J. J. Hopfield, 'Simple Neural Optimization Networks: An A/D Converter, Signal Decision Circuit, and a Linear Programming Circuit,' IEEE Transactions on Circuits Systems, vol. CAS-33, no. 5, pp. 533-541, 1986 https://doi.org/10.1109/TCS.1986.1085953
  9. J. J. Hopfield and D. W. Tank, 'Neural Computations of Decisions on Optimization Problem,' Biological Cybernetics, vol. 52, pp. 141-152, 1986 https://doi.org/10.1007/BF00339943
  10. K. Atkinson, Elementary Numerical Analysis, John Wiley & Sons, Inc., 1993