A Hybrid Neural-Genetic Algorithm for the Frequency Assignment Problem in Satellite Communications

A hybrid Neural-Genetic algorithm (NG) is presented for the frequency assignment problem in satellite communications (FAPSC). The goal of this problem is minimizing the cochannel interference between satellite communication systems by rearranging the frequency assignments. Previous approaches to FAPSC show lack of scalability, which leads to poor results when the size of the problem grows. The NG algorithm consists of a Hopfield neural network which manages the problem constraints hybridized with a genetic algorithm for improving the solutions obtained. This separate management of constraints and optimization of objective function gives the NG algorithm the properties of scalability required.We analyze the FAPSC and its formulation, describe and discuss the NG algorithm and solve a set of benchmark problems. The results obtained are compared with other existing approaches in order to show that the NG algorithm is more scalable and performs better than previous algorithms in the FAPSC.

[1]  Roberto Montemanni,et al.  An Exact Algorithm for the Min-Interference Frequency Assignment Problem , 1999 .

[2]  Aníbal R. Figueiras-Vidal,et al.  A mixed neural-genetic algorithm for the broadcast scheduling problem , 2003, IEEE Trans. Wirel. Commun..

[3]  Panos M. Pardalos,et al.  Frequency Assignment Problems , 1999, Handbook of Combinatorial Optimization.

[4]  Steve Hurley,et al.  Applying genetic algorithms to frequency assignment problems , 1994, Optics & Photonics.

[5]  Nirwan Ansari,et al.  A new method to optimize the satellite broadcasting schedules using the mean field annealing of a Hopfield neural network , 1995, IEEE Trans. Neural Networks.

[6]  Takeshi Mizuike,et al.  Optimization of frequency assignment , 1989, IEEE Trans. Commun..

[7]  Yoshiaki Watanabe,et al.  Solving optimization problems by using a Hopfield neural network and genetic algorithm combination , 1998, Systems and Computers in Japan.

[8]  Carlo Mannino,et al.  Models and solution techniques for frequency assignment problems , 2003, 4OR.

[9]  Roberto J. Acosta,et al.  Advanced Communications Technology Satellite (ACTS): four-year system performance , 1999, IEEE J. Sel. Areas Commun..

[10]  Arie M. C. A. Koster,et al.  Lower bounds for minimum interference frequency assignment probems , 2000 .

[11]  Nobuo Funabiki,et al.  A gradual neural-network approach for frequency assignment in satellite communication systems , 1997, IEEE Trans. Neural Networks.

[12]  Sudhakar M. Reddy,et al.  Guaranteed convergence in a class of Hopfield networks , 1992, IEEE Trans. Neural Networks.

[13]  Harilaos G. Sandalidis,et al.  An efficient evolutionary algorithm for channel resource management in cellular mobile systems , 1998, IEEE Trans. Evol. Comput..

[14]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[15]  Fam Quang Bac,et al.  New evolutionary genetic algorithms for NP-complete combinatorial optimization problems , 1993, Biological Cybernetics.

[16]  Nirwan Ansari,et al.  Optimal Broadcast Scheduling in Packet Radio Networks Using Mean Field Annealing , 1997, IEEE J. Sel. Areas Commun..

[17]  Christos Voudouris.  Solving the Radio Link Frequency Assignment Problem using Guided Local Search , 2001 .

[18]  D. E. Goldberg,et al.  Genetic Algorithm in Search , 1989 .

[19]  Yasuo Hirata,et al.  Intermodulation Interference-Minimum Frequency Assignment for Satellite SCPC Systems , 1984, IEEE Trans. Commun..