Dinamik Çok lı Eniyileme Problemleri için Hibrid Çerçevenin İncelenmesi

Çok amaçlı evrimsel algoritmalar ve sezgisel seçen üst-sezgiseller ortamda meydana gelebilecek farklı dinamizm tiplerini ele alan adaptif yöntemlerdir. Bu çalışmada, bu yöntemlerin birleştirildiği yapı, dinamik çok amaçlı eniyileme problemlerini çözmek için kullanılmıştır. Bu yapıda üst-sezgiseller popülasyonun bireylerini üretecek olan sezgiselleri seçmek için kullanılır. Sezgisel seçen üst-sezgiseller içinde kullanılan farklı sezgisel seçim yöntemlerinin etkisi ile birlikte önerilen yaklaşımın performansı yapay olarak oluşturulmuş dinamik test problemleri üzerinde deneysel olarak incelenmiştir. Deneysel sonuçlar öğrenme içeren üst-sezgisellerin kullanıldığı yaklaşımın öğrenme içermeyenlere göre daha iyi sonuç verdiğini göstermiştir. Ayrıca, önerilen yaklaşımın literatürde iyi bilinen yöntemlerle karşılaştırıldığında rekabet edebilecek düzeyde sonuçlar verdiği görülmüştür

An Investigation of Hybrid Framework for Dynamic MultiObjective Problems

Multi-objective evolutionary algorithms and selection hyper-heuristics are adaptive methods that can handle different types of dynamism which may occur in the environment. In this study, a hybrid framework combining these methods is presented for solving dynamic multi-objective optimization problems. In this framework, hyper-heuristics are used to select the heuristic that will generate the individuals in the population. The performance of the approach, along with the effect of different heuristic selection methods used in the selection hyper-heuristics, is experimentally examined over a set of dynamic multi-objective optimization problems. The empirical results show that the selection hyper-heuristics with learning perform well in the framework. It is also shown that the proposed approach can compete with the well-known methods from literature

PDF

___

[1] Deb, K., Rao N., U.B., ve Karthik, S.: "Dynamic Multi-objective Optimization and Decision-Making Using Modified NSGA-II: A Case Study on Hydro-thermal Power Scheduling", Evolutionary MultiCriterion Optimization: 4th International Conference, EMO 2007, Matsushima, Japan, March 5-8, 2007. Proceedings, in Obayashi, S., Deb, K., Poloni, C., Hiroyasu, T., ve Murata, T. (Ed.)^(Eds.), Springer Berlin Heidelberg, 803-817, 2007.
[2] Farina, M., Deb, K., ve Amato, P.: "Dynamic Multiobjective Optimization Problems: Test Cases, Approximation, and Applications", Evolutionary Multi-Criterion Optimization: Second International Conference, EMO 2003, Faro, Portugal, April 8–11, 2003. Proceedings, in Fonseca, C.M., Fleming, P.J., Zitzler, E., Thiele, L., ve Deb, K. (Ed.)^(Eds.), Springer Berlin Heidelberg, 311-326, 2003.
[3] Helbig, M., "Solving dynamic multi-objective optimisation problems using vector evaluated particle swarm optimisation", University of Pretoria, Faculty of Engineering, Built Environment and Information Technology, 2012.
[4] Burke, E.K., Gendreau, M., Hyde, M., Kendall, G., Ochoa, G., Özcan, E., ve Qu, R., "Hyperheuristics: a survey of the state of the art", Journal of the Operational Research Society, Cilt 64, No 12, 1695-1724, 2013.
[5] Özcan, E., Bilgin, B., ve Korkmaz, E.E., "A comprehensive analysis of hyper-heuristics", Intell. Data Anal., Cilt 12, No 1, 3-23, 2008.
[6] Cowling, P.I., Kendall, G., ve Soubeiga, E., "A Hyperheuristic Approach to Scheduling a Sales Summit". Proc. Selected papers from the Third International Conference on Practice and Theory of Automated Timetabling III, 176-190, 2001.
[7] McClymont, K., Keedwell, E., Savić, D., ve Randall-Smith, M., "A general multi-objective hyperheuristic for water distribution network design with discolouration risk", Journal of Hydroinformatics, Cilt 15, No 3, 700-716, 2013.
[8] Kiraz, B., Etaner-Uyar, A.Ş., ve Özcan, E., "Selection hyper-heuristics in dynamic environments", Journal of the Operational Research Society, Cilt 64, No 12, 1753-1769, 2013.
[9] Deb, K., Pratap, A., Agarwal, S., ve Meyarivan, T., "A fast and elitist multiobjective genetic algorithm: NSGA-II", IEEE Transactions on Evolutionary Computation, Cilt 6, No 2, 182-197, 2002.
[10] Coello, C.A., "An updated survey of GA-based multiobjective optimization techniques", ACM Comput. Surv., Cilt 32, No 2, 109-143, 2000.
[11] Jin, Y., ve Branke, J., "Evolutionary optimization in uncertain environments-a survey", IEEE Transactions on Evolutionary Computation, Cilt 9, No 3, 303-317, 2005.
[12] Yang, S., ve Yao, X., "Evolutionary Computation for Dynamic Optimization Problems", 2013.
[13] Cobb, H.G., "An investigation into the use of hypermutation as an adaptive operator in genetic algorithms having continuous, time-dependent nonstationary environments", Rep.No, Naval Research Lab., Washington, DC, 1990.
[14] Uyar, A.Ş., ve Harmanci, A.E., "A new population based adaptive domination change mechanism for diploid genetic algorithms in dynamic environments", Soft Computing, Cilt 9, No 11, 803-814, 2005.
[15] Yang, S., ve Yao, X., "Population-Based Incremental Learning With Associative Memory for Dynamic Environments", IEEE Transactions on Evolutionary Computation, Cilt 12, No 5, 542- 561, 2008.
[16] Yang, S., "Genetic algorithms with memory-and elitism-based immigrants in dynamic environments", Evol. Comput., Cilt 16, No 3, 385-416, 2008.
[17] Wang, Y., ve Li, B., "Investigation of memory-based multi-objective optimization evolutionary algorithm in dynamic environment". Proc. 2009 IEEE Congress on Evolutionary Computation, 630-637, 18-21 May 2009, 2009.
[18] Branke, J., "Evolutionary Optimization in Dynamic Environments", Kluwer Academic Publishers, 2001.
[19] Goh, C.-K., ve Tan, K.C., "A competitive-cooperative coevolutionary paradigm for dynamic multiobjective optimization", Trans. Evol. Comp, Cilt 13, No 1, 103-127, 2009.
[20] Sahmoud, S., ve Topcuoglu, H.R., "A Memory-Based {NSGA-II} Algorithm for Dynamic Multiobjective Optimization Problems". Proc. 19th European Conference, EvoApplications 2016, Porto, Portugal, 296--310, 2016.
[21] Helbig, M., Deb, K., ve Engelbrecht, A.P., "Key challenges and future directions of dynamic multiobjective optimisation". Proc. {IEEE} Congress on Evolutionary Computation, Vancouver, BC, Canada, 1256--1261, 2016.
[22] Nareyek, A.: "Choosing Search Heuristics by Non-Stationary Reinforcement Learning", Metaheuristics: Computer Decision-Making, in (Ed.)^(Eds.), Springer US, 523-544, 2004.
[23] Ozcan, E., Uyar, S.E., ve Burke, E., "A greedy hyper-heuristic in dynamic environments". Proc. Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference: Late Breaking Papers, Montreal, Canada, 2201-2204, 2009.
[24] Uludağ, G., Kiraz, B., Etaner-Uyar, A.Ş., ve Özcan, E., "A hybrid multi-population framework for dynamic environments combining online and offline learning", Soft Computing, Cilt 17, No 12, 2327-2348, 2013.
[25] Topcuoglu, H.R., Ucar, A., ve Altin, L., "A hyper-heuristic based framework for dynamic optimization problems", Applied Soft Computing, Cilt 19, No, 236-251, 2014.
[26] Burke, E.K., Silva, J.D.L., ve Soubeiga, E.: "Multi-Objective Hyper-Heuristic Approaches for Space Allocation and Timetabling", Metaheuristics: Progress as Real Problem Solvers, in Ibaraki, T., Nonobe, K., ve Yagiura, M. (Ed.)^(Eds.), Springer US, 129-158, 2005.
[27] McClymont, K., ve Keedwell, E.C., "Markov chain hyper-heuristic (MCHH): an online selective hyper-heuristic for multi-objective continuous problems". Proc. Proceedings of the 13th annual conference on Genetic and evolutionary computation, Dublin, Ireland, 2003-2010, 2011.
[28] Zitzler, E., Laumanns, M., Thiele, L., "SPEA2: Improving the Performance of the Strength Pareto Evolutionary Algorithm", Rep.No: 103, Swiss Federal Institute of Technology (ETH) Zurich 2001.
[29] Gomez, J.C., ve Terashima-Marín, H.: "Approximating Multi-Objective Hyper-Heuristics for Solving 2D Irregular Cutting Stock Problems", Advances in Soft Computing: 9th Mexican International Conference on Artificial Intelligence, MICAI 2010, Pachuca, Mexico, November 8-13, 2010, Proceedings, Part II, in Sidorov, G., Hernández Aguirre, A., ve Reyes García, C.A. (Ed.)^(Eds.), Springer Berlin Heidelberg, 349-360, 2010.
[30] Kumari, A.C., Srinivas, K., ve Gupta, M.P., "Software module clustering using a hyper-heuristic based multi-objective genetic algorithm". Proc. 2013 3rd IEEE International Advance Computing Conference (IACC), 813-818, 22-23 Feb. 2013, 2013.
[31] Suganthan, P.N., "Performance assessment on multi-objective optimization algorithms". Proc. IEEE Conference on Evolutionary Computation Special Session-competition on performance assessment of multi-objective optimization algorithms, 2007.
[32] Das, S., ve Suganthan, P.N., "Differential Evolution: A Survey of the State-of-the-Art", IEEE Transactions on Evolutionary Computation, Cilt 15, No 1, 4-31, 2011.
[33] Tan, K.C., Lee, T.H., ve Khor, E.F., "Evolutionary Algorithms for Multi-Objective Optimization: Performance Assessments and Comparisons", Artificial Intelligence Review, Cilt 17, No 4, 251-290, 2002.
[34] Özcan, E., Misir, M., Ochoa, G., ve Burke, E.K., "A Reinforcement Learning-Great-Deluge HyperHeuristic for Examination Timetabling", Int. J. Appl. Metaheuristic Comput., Cilt 1, No 1, 39-59, 2010.
[35] Zhang, Q., Zhou, A., ve Jin, Y., "RM-MEDA: A Regularity Model-Based Multiobjective Estimation of Distribution Algorithm", IEEE Transactions on Evolutionary Computation, Cilt 12, No 1, 41- 63, 2008.
[36] Koo, W.T., Goh, C.K., ve Tan, K.C., "A predictive gradient strategy for multiobjective evolutionary algorithms in a fast changing environment", Memetic Computing, Cilt 2, No 2, 87-110, 2010.
[37] Zhou, A., Jin, Y., Zhang, Q., Sendhoff, B., ve Tsang, E., "Prediction-based population reinitialization for evolutionary dynamic multi-objective optimization". Proc. Proceedings of the 4th international conference on Evolutionary multi-criterion optimization, Matsushima, Japan, 832- 846, 2007.