Journal of Korean Society of Transportation (대한교통학회지)

Korean Society of Transportation (대한교통학회)
권호 표지

Incorporating Genetic Operators into Optimizing Highway Alignments

도로선형최적화를 위한 유전자 연산자의 적용

  • 김응철 (인천대학교 토목환경시스템공학과)
  • Published : 2004.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

This study analyzes characteristics and applicability of genetic algorithms and genetic operators to optimize highway alignments. Genetic algorithms, one of artificial intelligence techniques, are fast and efficient search algorithms for generating, evaluation and finding optimal highway alignment alternatives. The performance of genetic algorithms as an optimal search tool highly depends on genetic operators that are designed as a problem-specific. This study adopts low mutation operators(uniform mutation operator, straight mutation operator, non-uniform mutation operator whole non-uniform mutation operator) to explore whole search spaces, and four crossover operators(simple crossover operator, two-point crossover operator, arithmetic crossover operator, heuristic crossover operator) to exploit food characteristics of the best chromosome in previous generations. A case study and a sensitivity analysis have shown that the eight problem-specific operators developed for optimizing highway alignments enhance the search performance of genetic algorithms, and find good solutions(highway alignment alternatives). It has been also found that a mixed and well-combined use of mutation and crossover operators is very important to balance between pre-matured solutions when employing more crossover operators and more computation time when adopting more mutation operators.

본 연구에서는 인공지능(Artificial Intelligence)방법 중의 하나인 유전자 알고리즘(Genetic Algorithm)을 도로선형최적화 모형개발의 탐색엔진으로 활용하기 위한 핵심도구인 유전자 연산자(Genetic Operator)의 개발과 적용과정을 통해 그 특징과 유용성을 제시하였다. 균일돌연변이 연산자, 직선돌연변이 연산자. 비균일 돌연변이 연산자, 전체 비균일 돌연변이 연산자 등 4개의 돌연변이 연산자가 탐색영역(Search space)의 가능한 모든 부분을 탐험(Exploration)하기 위해 적용되었으며, 단순교차 연산자, 두 개의 점을 이용한 교차 연산자, 산술교차 연산자, 학습교차 연산자 등 4개의 교차 연산자가 노선대안의 우수한 유전형질을 다음세대에 효과적으로 전달(Exploitation)하기 위해 시험되었다. 사례연구와 민감도 분석과정을 통해 유전자 알고리즘 및 개발 적용된 8개 유전자 연산자의 도로선형최적화과정 도입이 우수한 노선대안을 빠르고 효과적으로 탐색함을 알 수 있었으며, 돌연변이 연산자와 교차 연산자의 효과적 조합이 상호보완기능을 통해 탐색능력의 향상에 큰 영향을 끼치는 것으로 파악되었다. 또한, 개발 적용된 연산자 이외에도 새로운 연산자의 개발 가능성이 무한하며, 이는 도로선형최적화에 유전자 알고리즘의 적용이 타당함을 반증함도 주목할 만하다.

Keywords

References

  1. OECD(1973), 'Optimisation of Road Alignment by the Use of Computers', Organisation of Economic Co-operation and Development, Paris
  2. Shaw, J. F. B. and Howard, B. E.(1982), 'Expressway Route Optimization by OCP', Transportation Engineering Journal of ASCE, Proceedings of the American Society of Civil Engineers, ASCE, Vol.108, No.TE3, pp.227-243
  3. Fwa, T. F.(1989), 'Highway Vertical Alignment Analysis by Dynamic Programming', Transportation Research Record 1239, TRB, National Research Council, Washington, D.C., pp.1-9
  4. Jha, Manoj K.(2000), 'A Geographic Information Systems-Based Model for Highway Design Optimization', Ph. D. Dissertation, University of Maryland, College Park
  5. Jong, J-C(1998), 'Optimizing Highway Alignments with Genetic Algorithms', Ph. D. Dissertation, University of Maryland, College Park
  6. 김응철(2001), 'Modeling Intersections and Other Structures in Highway Alignment Optimization', 박사학위논문, University of Maryland, College Park
  7. Goldberg, D. E.(1989), 'Genetic Algorithms in Search, Optimization, and Machine Learning', Addison-Wesley Publishing Company, Inc., Massachusetts
  8. Lovell, D. J.(1999), 'Automated Calculation of Sight Distance from Horizontal Geometry', Journal of Transportation Engineering, Vol.125, No.4, pp.297-30 https://doi.org/10.1061/(ASCE)0733-947X(1999)125:4(297)
  9. Mortenson, M. E.(1997), 'Geometric Modeling', 2nd Edition, John Wiley & Sons, Inc., New York
  10. Michalewicz, Z.(1996), 'Genetic Algorithms +Data Structures=Evolution Programs', Third Edition, Springer-Verlag, New York