Abstract
This work investigates a bio-inspired adaptive sampling immune optimization approach to solve a general kind of nonlinear multi-objective expected value programming without any prior noise distribution. A useful lower bound estimate is first developed to restrict the sample sizes of random variables. Second, an adaptive racing ranking scheme is designed to identify those valuable individuals in the current population, by which high-quality individuals in the process of solution search can acquire large sample sizes and high importance levels. Thereafter, an immune-inspired optimization approach is constructed to seek \(\varepsilon \)-Pareto optimal solutions, depending on a novel polymerization degree model. Comparative experiments have validated that the proposed approach with high efficiency is a competitive optimizer.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Aickelin U, Dasgupta D, Gu F (2014) Artificial immune systems. Search Methodologies. Springer US, pp 187–211
Aydin I, Karakose M, Akin E (2011) A multi-objective artificial immune approach for parameter optimization in support vector machine. Appl Soft Comput 11:120–129
Batista LS, Campelo F, Guimarães FG et al (2011) Pareto cone \(\varepsilon \)-dominance: improving convergence and diversity in multiobjective evolutionary approaches. In: Evolutionary multi-criterion optimization, Springer, Berlin, pp 76–90
Bui LT et al (2005) Fitness inheritance for noisy evolutionary multi-objective optimization. In: The 7th annual conference on genetic and evolutionary computation, ACM, pp 779–785
Cantú-Paz E (2004) Adaptive sampling for noisy problems. In: Genetic and evolutionary computation conference, GECCO2004, pp 947–958
Chen CH (2003) Efficient sampling for simulation-based optimization under uncertainty. In: Fourth International symposium on uncertainty modeling and analysis, ISUMA’03, pp 386–391
Coello CAC, Cortés NC (2005) Solving multi-objective optimization problems using an artificial immune system. Genet Program Evol Mach 6:163–190
Corne DW, Jerram NR, Knowles JD et al (2001) PESA-II: region-based selection in evolutionary multiobjective optimization. In: Genetic and evolutionary computation conference, GECCO’2001, pp 283–290
Deb K et al (2002) A fast and elitist multi-objective genetic approach: NSGA-II. IEEE Trans Evol Comput 6:182–197
Drugan MM, Nowe A (2013) Designing multi-objective multi-armed bandits approaches: a study. In: International joint conference on neural networks, IJCNN, pp 1–8
El-Wahed WFA, Lee SM (2006) Interactive fuzzy goal programming for multi-objective transportation problems. Omega 34(2):158–166
Eskandari H, Geiger CD (2009) Evolutionary multi-objective optimization in noisy problem environments. J Heuristics 15:559–595
Even-Dar E, Mannor S, Mansour Y (2006) Action elimination and stopping conditions for the multi-armed bandit and reinforcement learning problems. J Mach Learn Res 7:1079–1105
Gong MG, Jiao LC, Du HF, Bo LF (2008) Multi-objective immune approach with nondominated neighbor-based selection. Evol Comput 16:225–255
Gong MG et al (2013) Identification of multi-resolution network structures with multi-objective immune approach. Appl Soft Comput 13:1705–1717
Gutjahr WJ, Pichler A (2016) Stochastic multi-objective optimization: a survey on non-scalarizing methods. Ann Oper Res 236:475–499
Higle JL, Zhao L (2004) Adaptive and nonadaptive samples in solving stochastic linear programs: a computational investigation. The University of Arizona, Tucson
Hoeffding W (1963) Probability inequalities for sums of bounded random variables. J Am Stat Assoc 58(301):13–30
Hu ZH (2010) A multiobjective immune approach based on a multiple-affinity model. Eur J Oper Res 202:60–72
Hughes EJ (2001) Constraint handling with uncertain and noisy multi-objective evolution. In: Congress on evolutionary computation 2001, CEC’2001, pp 963–970
Jin Y, Branke J (2005) Evolutionary optimization in uncertain environments: a survey. IEEE Trans Evol Comput 9:303–317
Lee LH et al (2010) Finding the nondominated Pareto set for multi-objective simulation models. IIE Trans 42:656–674
Lee LH, Pujowidianto NA, Li LW et al (2012) Approximate simulation budget allocation for selecting the best design in the presence of stochastic constraints. IEEE Trans Autom Control 57:2940–2945
Lin Q, Chen J (2013) A novel micro-population immune multi-objective optimization approach. Comput Oper Res 40:1590–1601
Liu B (2009) Theory and practice of uncertain programming. Physica, Heidelberg
Marler RT, Arora JS (2010) The weighted sum method for multi-objective optimization: new insights. Struct Multidiscip Optim 41(6):853–862
Owen J, Punt J, Stranford S (2013) Kuby immunology, 7th edn. Freeman, New York
Park T, Ryu KR (2011) Accumulative sampling for noisy evolutionary multi-objective optimization. In: the 13th annual conference on Genetic and evolutionary computation, ACM, pp 793–800
Phan DH, Suzuki J (2012) A non-parametric statistical dominance operator for noisy multi-objective optimization. In: Simulated evolution and learning, SEAL’12, pp 42–51
Qi Y, Liu F, Liu M et al (2012) Multi-objective immune approach with Baldwinian learning. Appl Soft Comput 12:2654–2674
Qi Y, Hou Z, Yin M et al (2015) An immune multi-objective optimization approach with differential evolution inspired recombination. Appl Soft Comput 29:395–410
Robert C, Casella G (2013) Monte Carlo statistical methods. Springer, Berlin
Shapiro A, Dentcheva D, Ruszczyński A (2009) Lectures on stochastic programming: modeling and theory. SIAM-MPS Philadelphia
Tan KC, Lee TH, Khor EF (2001) Evolutionary approaches with dynamic population size and local exploration for multiobjective optimization. IEEE Trans Evol Comput 5:565–588
Tan KC, Goh CK, Mamun AA et al (2008) An evolutionary artificial immune system for multi-objective optimization. Eur J Oper Res 187:371–392
Trautmann H, Mehnen J, Naujoks B (2009) Pareto-dominance in noisy environments. In IEEE congress on evolutionary computation(CEC’09), pp 3119–3126
Van Veldhuizen DA (1999) Multiobjective evolutionary algorithms: classifications, analyses, and new innovations. Ph. D. Thesis, OH: Air force Institute of Technology, Technical Report No. AFIT/DS/ENG/99-01, Dayton
Zhang Q, Li H (2007) MOEA/D: a multiobjective evolutionary algorithm based on decomposition. IEEE Trans Evol Comput 11:712–731
Zhang ZH, Tu X (2007a) Immune approach with adaptive sampling in noisy environments and its application to stochastic optimization problems. IEEE Comput Intell Mag 2:29–40
Zhang ZH, Tu X (2007b) Probabilistic dominance-based multi-objective immune optimization approach in noisy environments. J Comput Theor Nanosci 4:1380–1387
Zhang ZH, Wang L, Liao M (2013a) Adaptive sampling immune approach solving joint chance-constrained programming. J Control Theory Appl 11:237–246
Zhang ZH, Wang L, Long F (2013b) Immune optimization approach solving multi-objective chance constrained programming. Evol Syst 6:41–53
Zhang W, Xu W, Liu G, et al (2015) An effective hybrid evolutionary approach for stochastic multiobjective assembly line balancing problem. J Intell Manuf 1–8. doi:10.1007/s10845-015-1037-5
Zheng JH et al (2004) A multi-objective genetic approach based on quick sort. Advances in Artificial Intelligence. Springer, Berlin
Zitzler E, Deb K, Thiele L (2000) Comparison of multiobjective evolutionary approaches: empirical results. Evol Comput 8:173–195
Zitzler E, Thiele L (1999) Multi-objective evolutionary approaches: a comparative case study and the strength Pareto approach. IEEE Trans Evol Comput 3:257–271
Acknowledgements
This work is supported by National Natural Science Foundation NSFC (61563009).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Communicated by V. Loia.
Appendices
Appendix 1
Proof Lemma 1
In the case of \({{\varvec{x}}}\in A_\varepsilon \), there exists at least a subscription \(j_0\) satisfying that
Hence, once\({\hat{{f}}}_{j_0 } ({{\varvec{y}}})+\varepsilon \le {\hat{{f}}}_{j_0 } ({{\varvec{x}}})\), one can imply that
or
Otherwise, by Eq. (18) we have that
This yields contradiction. Consequently,
Further, it follows from Eq. (20) and Theorem 1 that
Thus,
The proof is completed. \(\square \)
Proof of Theorem 2
For a given \({{\varvec{x}}}\in A_\varepsilon \), if \({{\varvec{x}}}\notin {\hat{{A}}}_\varepsilon \), there exists \({{\varvec{y}}}\in {\hat{{A}}}_\varepsilon \) such that \({{\varvec{y}}}\prec _{\hat{{\varepsilon }}} {{\varvec{x}}}\). Hence,
and accordingly,
Therefore, as related to Lemma 1 and Eq. (24), we can obtain that
This finishes the proof. \(\square \)
The proof of Theorem 3
In the case of \(x\in A_\varepsilon \), we know that
By Lemma 1, Eq. (21) implies that
Subsequently, we can easily obtain that
Thereby, the conclusion is true. \(\square \)
The proof of Theorem 3
In Step 4, those \(\beta \)-dominated and redundant B cells in \(\hbox {M}_{set}\) will be eliminated after copying \(\hbox {B}_{n}\) into \(\hbox {M}_{set}\), for which the computational complexity is \(\hbox {O}({\vert }\hbox {M}_{set}{\vert }\log {\vert }\hbox {M}_{set}{\vert })\). In particular, it is possible that the number of B cells in M\(_{set}\) is beyond (\(N+M)\). Thus, in the worst case we can assert that the complexity of Step 4 is \(\hbox {O}((N+M) \log (N+M))\). Step 5 needs to calculate PDM values of elements in \(A_{n}\); more precisely, we need to calculate their crowding distances with at most \(N\hbox {C}_{\max }\log N\hbox {C}_{\max }\) times and their values on S with \((N\hbox {C}_{\max }+1)N\hbox {C}_{\max }/2\) times. Step 8 executes mutation with at most \(Np\hbox {C}_{\max }\) times. In Step 9, the size of \(\hbox {B}_{n}\cup \hbox {E}_{n}\) is at most \(\hbox {NC}_{\max }\). Thus, when ARRA is enforced on \(\hbox {B}_{n}\cup \hbox {E}_{n}\), the complexity in the worst case is \(O(NC_{\max } (M_2 +\log NC_{\max } ))\) by means of the computational complexity in Sect. 5.1. Summarily, MEIOA’s computational complexity in the worst case is decided by
Therefore, the conclusion is right. \(\square \)
Appendix 2
See Table 7.
Appendix 3
See Table 8.
Rights and permissions
About this article
Cite this article
Yang, K., Zhang, Z. & Lu, J. Adaptive racing ranking-based immune optimization approach solving multi-objective expected value programming. Soft Comput 22, 2139–2158 (2018). https://doi.org/10.1007/s00500-016-2467-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-016-2467-5