Abstract
Biological and artificial evolution can be speeded up by environmental changes. From the evolutionary computation perspective, environmental changes during the optimization process generate dynamic optimization problems (DOPs). However, only DOPs caused by intrinsic changes have been investigated in the area of evolutionary dynamic optimization (EDO). This paper is devoted to investigate artificially induced DOPs. A framework to generate artificially induced DOPs from any pseudo-Boolean problem is proposed. We use this framework to induce six different types of changes in a 0–1 knapsack problem and test which one results in higher speed up. Two strategies based on immigrants, which are used in EDO, are adapted to the artificially induced DOPs investigated here. Some types of changes did not result in better performance, while some types led to higher speed up. The algorithm with memory based immigrants presented very good performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The idea of changing the static fitness landscape in order to make the optimization process easier is also present in other approaches. For example, in multi-objectivization, a single-objective problem is transformed into a multi-objective problem [7]. Another example is adding noise to the fitness function [5].
- 2.
In a pseudo-Boolean optimization problem P, the fitness function is \(f_P(\mathbf {x}) \in \mathbb {R}\), where \(\mathbf {x}\in \mathbb {B}^l\) is a candidate solution vector with dimension l.
- 3.
The best percentages of successful runs for DOP Type 2.2 were 66% (\(l=300\)) and 42% (\(l=400\)), against 28% (\(l=300\)) and 18% (\(l=400\)) for the static environments.
References
Cobb, H.G., Grefenstette, J.J.: Genetic algorithms for tracking changing environments. In: Proceedings of 5th International Conference on Genetic Algorithms, pp. 523–530 (1993)
Cruz, C., González, J., Pelta, D.: Optimization in dynamic environments: a survey on problems, methods and measures. Soft Comput. 15, 1427–1448 (2011)
Fu, H., Sendhoff, B., Tang, K., Yao, X.: Robust optimization over time: problem difficulties and benchmark problems. IEEE Trans. Evol. Comp. 19(5), 731–745 (2015)
Han, K.H., Kim, J.H.: Genetic quantum algorithm and its application to combinatorial optimization problem. In: Proceedings of the 2000 Congress on Evolutionary Computation, vol. 2, pp. 1354–1360 (2000)
Jin, Y., Branke, J.: Evolutionary optimization in uncertain environments-a survey. IEEE Trans. Evol. Comp. 9(3), 303–317 (2005)
Kashtan, N., Noor, E., Alon, U.: Varying environments can speed up evolution. Proc. Natl. Acad. Sci. 104(34), 13711–13716 (2007)
Knowles, J.D., Watson, R.A., Corne, D.W.: Reducing local optima in single-objective problems by multi-objectivization. In: Zitzler, E., Deb, K., Thiele, L., Coello Coello, C.A., Corne, D.W. (eds.) EMO 2001. LNCS, vol. 1993, p. 269. Springer, Heidelberg (2001)
Nguyen, T.T., Yang, S., Branke, J.: Evolutionary dynamic optimization: a survey of the state of the art. Swarm Evol. Comp. 6, 1–24 (2012)
Parter, M., Kashtan, N., Alon, U.: Facilitated variation: how evolution learns from past environments to generalize to new environments. PLOS Comput. Biol. 4(11), e1000206 (2008)
Richter, H.: Coevolutionary intransitivity in games: a landscape analysis. In: Mora, A.M., Squillero, G. (eds.) EvoApplications 2015. LNCS, vol. 9028, pp. 869–881. Springer, Heidelberg (2015)
Steinberg, B., Ostermeier, M.: Environmental changes bridge evolutionary valleys. Sci. Adv. 2(1), e1500921 (2016)
Tan, L., Gore, J.: Slowly switching between environments facilitates reverse evolution in small populations. Evolution 66(10), 3144–3154 (2012)
Tinós, R., Yang, S.: Analyzing evolutionary algorithms for dynamic optimization problems based on the dynamical systems approach. In: Yang, S., Yao, X. (eds.) Evolutionary Computation for Dynamic Optimization Problems. SCI, vol. 490, pp. 241–267. Springer, Heidelberg (2013)
Tinós, R., Yang, S.: Analysis of fitness landscape modifications in evolutionary dynamic optimization. Inf. Sci. 282, 214–236 (2014)
Yang, S.: Genetic algorithms with memory-and elitism-based immigrants in dynamic environments. Evol. Comput. 16(3), 385–416 (2008)
Acknowledgments
This work was funded partially by FAPESP under grant 2015/06462-1 and CNPq in Brazil, and partially by the Engineering and Physical Sciences Research Council (EPSRC) of U.K. under grant EP/K001310/1.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Tinós, R., Yang, S. (2016). Artificially Inducing Environmental Changes in Evolutionary Dynamic Optimization. In: Handl, J., Hart, E., Lewis, P., López-Ibáñez, M., Ochoa, G., Paechter, B. (eds) Parallel Problem Solving from Nature – PPSN XIV. PPSN 2016. Lecture Notes in Computer Science(), vol 9921. Springer, Cham. https://doi.org/10.1007/978-3-319-45823-6_21
Download citation
DOI: https://doi.org/10.1007/978-3-319-45823-6_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-45822-9
Online ISBN: 978-3-319-45823-6
eBook Packages: Computer ScienceComputer Science (R0)