380
M. Antoniou et al.
11.6 Summary
This chapter provides an insight into parameter control strategies in EA. The concept
of evolutionary algorithms is introduced, along with the control parameters that need
to be set for this kind of algorithms, their mutual interactions and their influence
on the algorithm performance. Parameter tuning and parameter control, the two
categories of parameter settings, are then explained. More focus is given to the
three strategies of parameter control, i.e. deterministic, adaptive and self-adaptive
parameter control. It also discusses when and why it is more appropriate to use
either parameter tuning or parameter control strategies. Last but not least, it outlines
the motivation of using parameter control for solving some instances of real-world
optimisation problems, like the ones with a large number of variables, dynamic
changes, multiple objectives, multiple levels and uncertainty.
Acknowledgments This work is funded by the European Commission’s H2020 programme,
through the UTOPIAE Marie Curie Innovative Training Network, H2020-MSCA-ITN-2016, grant
agreement number 722734, and through the SYNERGY Twinning project, H2020-TWINN2015, grant agreement number 692286. The authors acknowledge the financial support from the
Slovenian Research Agency (research core funding no. P2-0098 and PR-07606).
References
1. D.E. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning, 1st edn.
(Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1989)
2. X.-S. Yang, Review of meta-heuristics and generalised evolutionary walk algorithm. Int. J.
Bio-Inspired Comput. 3(2), 77–84 (2011)
3. E.-G. Talbi, Metaheuristics: From Design to Implementation, vol. 74 (Wiley, New York, 2009)
4. A.E. Eiben, J.E. Smith, Introduction to Evolutionary Computing, 2nd edn. (Springer Publishing
Company, Incorporated, Berlin, 2015)
5. F.F. Orsucci, N. Sala, Reflexing Interfaces: The Complex Coevolution of Information Technology Ecosystems. IGI Global, January 2001 [Online]. Available https://www.igi-global.com/
book/reflexing-interfaces-complex-coevolution-information/865
6. A.E. Eiben, C.A. Schippers, On evolutionary exploration and exploitation. Fundam. Inf. 35(1–
4), 35–50 (1998) [Online]. Available http://dl.acm.org/citation.cfm?id=297119.297124
7. L. Hong, J.H. Drake, J.R. Woodward, E. Özcan, A hyper-heuristic approach to automated generation of mutation operators for evolutionary programming. Appl. Soft Comput. 62, 162–175 (2018) [Online]. Available http://www.sciencedirect.com/science/article/pii/
S1568494617306051
8. G. Karafotias, M. Hoogendoorn, A.E. Eiben, Parameter control in evolutionary algorithms:
trends and challenges. IEEE Trans. Evol. Comput. 19(2), 167–187 (2015)
9. A.E. Eiben, S.K. Smit, Parameter tuning for configuring and analyzing evolutionary algorithms. Swarm Evol. Comput. 1(1), 19–31 (2011)
10. D.-C. Dang, P.K. Lehre, Self-adaptation of mutation rates in non-elitist populations, in Parallel
Problem Solving from Nature – PPSN XIV, ed. by J. Handl, E. Hart, P.R. Lewis, M. LópezIbáñez, G. Ochoa, B. Paechter (Springer International Publishing, Cham, 2016), pp. 803–813
M. Antoniou et al.
11.6 Summary
This chapter provides an insight into parameter control strategies in EA. The concept
of evolutionary algorithms is introduced, along with the control parameters that need
to be set for this kind of algorithms, their mutual interactions and their influence
on the algorithm performance. Parameter tuning and parameter control, the two
categories of parameter settings, are then explained. More focus is given to the
three strategies of parameter control, i.e. deterministic, adaptive and self-adaptive
parameter control. It also discusses when and why it is more appropriate to use
either parameter tuning or parameter control strategies. Last but not least, it outlines
the motivation of using parameter control for solving some instances of real-world
optimisation problems, like the ones with a large number of variables, dynamic
changes, multiple objectives, multiple levels and uncertainty.
Acknowledgments This work is funded by the European Commission’s H2020 programme,
through the UTOPIAE Marie Curie Innovative Training Network, H2020-MSCA-ITN-2016, grant
agreement number 722734, and through the SYNERGY Twinning project, H2020-TWINN2015, grant agreement number 692286. The authors acknowledge the financial support from the
Slovenian Research Agency (research core funding no. P2-0098 and PR-07606).
References
1. D.E. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning, 1st edn.
(Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1989)
2. X.-S. Yang, Review of meta-heuristics and generalised evolutionary walk algorithm. Int. J.
Bio-Inspired Comput. 3(2), 77–84 (2011)
3. E.-G. Talbi, Metaheuristics: From Design to Implementation, vol. 74 (Wiley, New York, 2009)
4. A.E. Eiben, J.E. Smith, Introduction to Evolutionary Computing, 2nd edn. (Springer Publishing
Company, Incorporated, Berlin, 2015)
5. F.F. Orsucci, N. Sala, Reflexing Interfaces: The Complex Coevolution of Information Technology Ecosystems. IGI Global, January 2001 [Online]. Available https://www.igi-global.com/
book/reflexing-interfaces-complex-coevolution-information/865
6. A.E. Eiben, C.A. Schippers, On evolutionary exploration and exploitation. Fundam. Inf. 35(1–
4), 35–50 (1998) [Online]. Available http://dl.acm.org/citation.cfm?id=297119.297124
7. L. Hong, J.H. Drake, J.R. Woodward, E. Özcan, A hyper-heuristic approach to automated generation of mutation operators for evolutionary programming. Appl. Soft Comput. 62, 162–175 (2018) [Online]. Available http://www.sciencedirect.com/science/article/pii/
S1568494617306051
8. G. Karafotias, M. Hoogendoorn, A.E. Eiben, Parameter control in evolutionary algorithms:
trends and challenges. IEEE Trans. Evol. Comput. 19(2), 167–187 (2015)
9. A.E. Eiben, S.K. Smit, Parameter tuning for configuring and analyzing evolutionary algorithms. Swarm Evol. Comput. 1(1), 19–31 (2011)
10. D.-C. Dang, P.K. Lehre, Self-adaptation of mutation rates in non-elitist populations, in Parallel
Problem Solving from Nature – PPSN XIV, ed. by J. Handl, E. Hart, P.R. Lewis, M. LópezIbáñez, G. Ochoa, B. Paechter (Springer International Publishing, Cham, 2016), pp. 803–813