A K-Nearest-Neighbors Pareto Rank Assignment Strategy and Compound Crossover Operator Based NSGA-II and Its Applications on Multi-objective Optimization Functions

  • Weiya Guo
  • Zhenhua Li
  • Dan Zhao
  • Tim Wong
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5370)


We try to improve the NSGA-II, one of the most classical MOP algorithms, in two ways. To measure individual crowding distance by edge weight of minimum spanning tree and k-nearest-neighbors Pareto rank assignment strategy is helpful on diversity of population; A compound crossover operator increases the extent and the ability of search. Experimental results on ZDTs and DTLZs, suggest that A K-Nearest-Neighbors Pareto Rank Assignment Strategy and Compound Crossover Operator Based NSGA-II (KC NSGA-II) works faster and has more diverse solutions than its origins.


Multi-Objective Evolutionary Algorithm NSGA-II Minimum Spanning Tree K-Nearest-Neighbors Compound Crossover Operator 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Srinivas, N., Deb, K.: Multi-objective optimization using non-dominated sorting ingenetic algorithms. Evolutionary Computation 2(3), 221–248 (1994)CrossRefGoogle Scholar
  2. 2.
    Srinivas, N., Deb, K.: Multi-Objective Function Optimization Using Non-Dominated Sorting Genetical Algorithms. Evolutionary Computation 2(3), 221–248 (1995)CrossRefGoogle Scholar
  3. 3.
    Deb, K.: Multi-objective genetic algorithms: Problem difficulties and construction of test functions. Evolutionary Computation 7(3), 205 (1999)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Mitra, K.: Multi-objective optimization of an industrial grinding operation using elitist nondominated sorting genetic algorithm. Chemical Engineering Science, 385–396 (2004)Google Scholar
  5. 5.
    Parsopoulos, K.E., Tasoulis, D.K., Pavlidis, N.G., Plagianakos, V.P., Vrahatis, M.N.: Vector Evaluated Differential Evolution for – Multiobjective OptimizationGoogle Scholar
  6. 6.
    Liu, Y.: A fast optimization method of using nondominated sorting genetic algorithm (NSA-II) and 1-nearest neighbor (1NN) classifier for numerical model calibration. In: IEEE International Conference on 2005, pp. 544–549 (2005)Google Scholar
  7. 7.
    Akbari, A.A.: Pareto-Optimal Solutions for Multi-Objective Optimization of Turning Operation using Non-dominated Sorting Genetic Algorithm. In: TICME 2005, pp. 404–413 (2005)Google Scholar
  8. 8.
    Wei, X.: Ramp Shape Optimum Design for Airplane Land-Based Ski-Jump Take off via NSGA II. In: International Conference on 2006, pp. 995–1000 (2006)Google Scholar
  9. 9.
    Price, A.R.: Mul-tiobjective Tuning of Grid-Enabled Earth System Models Using a Non-dominated Sorting Genetic Algorithm (NSGA-II). In: IEEE International Conference on 2006, p. 117 (2006)Google Scholar
  10. 10.
    Nazemi, A.: Extracting a Set of Robust Pareto-Optimal Parameters for Hydrologic Models using NSGA-II and SCEM. In: IEEE Congress on 2006, pp. 1901–1908 (2006)Google Scholar
  11. 11.
    Deb, K., Thiele, L., Laumanns, M., Zitzler, E.: Scalable multi-objective optimization test proiproblems. In: Congress on Evolutionary Computation, pp. 825–830 (2002)Google Scholar
  12. 12.
    Shi, Y.: A New Strategy for Parameter Estimation of Dynamic Differential Equations Based on NSGA II. Simulated evolution and learning, 345–352 (2006)Google Scholar
  13. 13.
    Bharti, S.: Optimal structural design of a morphing aircraft wing using parallel non-dominated sorting genetic algorithm II (NSGA II). Smart structures and materials, 616602-1–616602-12 (2006)Google Scholar
  14. 14.
    Xu, L.: Multi-objective Parameters Selection for SVM Classification Using NSGA-II. Advances in data mining, 365–376 (2006)Google Scholar
  15. 15.
    Goudos, S.K.: Electric Filter Optimal Design Suitable For Microwave Communications By Multi-Objective Evolutionary Algorithms. Microwave and Optical Technology Letters, 2324–2329 (2007)Google Scholar
  16. 16.
    Gallego, R.A., Monticelli, A., Romero, R.: Transmission system expansion planning by an extended genetic algorithm. IEE Proc. Gener,Transm. Distrib. 145(3), 329–335 (1998)CrossRefGoogle Scholar
  17. 17.
    Guo, T., Kang, L.: A New Algorithm to Optimize Function with In equation and Restraints. Journal of Wuhan University: Natural Science 45(5), 771–775 (1999)Google Scholar
  18. 18.
    Huang, Z.: A Effective Multi-Objective Evolutionary Algorithm. Computer Engineering and Applications 43(11), 75–79 (2007)Google Scholar
  19. 19.
    Yu, R., Wang, Y.: A NSGA-II for Multi-Objective Minimum Spanning Tree Problem. Electronic Sci. & Tech. 126(6), 33–36 (2007)Google Scholar
  20. 20.
    Yang, S.: A Multi-Objective Evolutionary Algorithm Based on Parato Optimility and Limited Elitist. Computer Engineering and Applications 43(2), 108–111 (2007)Google Scholar
  21. 21.
    Peng, W., Huang, H.: A novel Multi-Objective Immune Algorithm Based on Memory Clonal Selection. Computer Engineering and Applications 44(16), 56–59 (2008)Google Scholar
  22. 22.
    Li, M., Zheng, J.: Mutil-objective evolutionary algorithm based on neighborhood. Computer Application 28(6), 1571–1574 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Weiya Guo
    • 1
  • Zhenhua Li
    • 1
  • Dan Zhao
    • 1
  • Tim Wong
    • 1
  1. 1.China University Of GeosciencesChina

Personalised recommendations