ABSTRACT
The parameter adaptation is one of the main problems in many evolutionary algorithms, including differential evolution. Instead of manual development of new methods, a hyper-heuristic approach can be used, where an algorithm is applied to search for parameter adaptation scheme. In this study the symbolic regression genetic programming is applied to design parameter adaptation method for differential evolution algorithm with two populations L-NTADE. Due to algorithmic scheme different from popular L-SHADE, the L-NTADE may require specific adaptation mechanisms. Each solution in genetic programming consists of three trees, which generate scaling factor values based on current resource, success rate and current values in the memory cells, containing scaling factor and crossover rate. The training is performed on a set of 30 benchmark functions from CEC 2017 competition on numerical optimization, and at every generation of genetic programming new problem dimension, computational resource, optima location and rotation matrices are generated for every test function. The testing is performed on two benchmarks, CEC 2017 and CEC/GECCO 2022. The results comparison shows that the automatically designed parameter adaptation heuristics are capable of outperforming the success-history adaptation in many cases, including high-dimensional problems and problems with different computational resource.
- Rawaa Dawoud Al-Dabbagh, Ferrante Neri, Norisma Binti Idris, and Mohd Sapiyan Bin Baba. 2018. Algorithmic design issues in adaptive differential evolution schemes: Review and taxonomy. Swarm Evol. Comput. 43 (2018), 284--311.Google ScholarCross Ref
- N.H. Awad, M.Z. Ali, J.J. Liang, B.Y. Qu, and P.N. Suganthan. 2016. Problem definitions and evaluation criteria for the CEC 2017 special session and competition on single objective bound constrained real-parameter numerical optimization. Technical Report. Nanyang Technological University, Singapoure.Google Scholar
- J. Branke, Su Nguyen, Christoph W. Pickardt, and M. Zhang. 2016. Automated Design of Production Scheduling Heuristics: A Review. IEEE Transactions on Evolutionary Computation 20 (2016), 110--124.Google ScholarDigital Library
- Edmund K. Burke, Michel Gendreau, Matthew R. Hyde, Graham Kendall, Gabriela Ochoa, Ender Özcan, and Rong Qu. 2013. Hyper-heuristics: a survey of the state of the art. Journal of the Operational Research Society 64 (2013), 1695--1724.Google ScholarCross Ref
- Edmund K. Burke, Matthew R. Hyde, Graham Kendall, Gabriela Ochoa, Ender Özcan, and John Robert Woodward. 2018. A Classification of Hyper-Heuristic Approaches: Revisited. Handbook of Metaheuristics (2018).Google Scholar
- J. M. Cruz-Duarte, Iván Amaya, José carlos Ortíz-Bayliss, Santiago Enrique Conant-Pablos, and Hugo Terashima-Marín. 2020. A Primary Study on Hyper-Heuristics to Customise Metaheuristics for Continuous optimisation. 2020 IEEE Congress on Evolutionary Computation (CEC) (2020), 1--8.Google ScholarDigital Library
- Péricles B. C. de Miranda, Ricardo B. C. Prudêncio, and Gisele Lobo Pappa. 2017. H3AD: A hybrid hyper-heuristic for algorithm design. Inf. Sci. 414 (2017), 340--354.Google ScholarCross Ref
- L. Diosan and M. Oltean. 2006. Evolving Crossover Operators for Function Optimization. In EuroGP.Google Scholar
- J. Drake, M. Hyde, Khaled Ibrahim, and E. Özcan. 2014. A genetic programming hyper-heuristic for the multidimensional knapsack problem. Kybernetes 43 (2014), 1500--1511.Google ScholarCross Ref
- Tomofumi Kitamura and Alex Fukunaga. 2022. Differential Evolution with an Unbounded Population. 2022 IEEE Congress on Evolutionary Computation (CEC) (2022).Google ScholarDigital Library
- J. Koza. 1992. Genetic programming - on the programming of computers by means of natural selection. In Complex adaptive systems.Google Scholar
- Abhishek Kumar, K. Price, Ali K. Mohamed, Anas A., and P. N. Suganthan. 2021. Problem Definitions and Evaluation Criteria for the CEC 2022 Special Session and Competition on Single Objective Bound Constrained Numerical Optimization. Technical Report. Nanyang Technological University, Singapoure.Google Scholar
- Adam P. Piotrowski and Jaroslaw J. Napiorkowski. 2018. Step-by-step improvement of JADE and SHADE-based algorithms: Success or failure? Swarm and Evolutionary Computation 43 (2018), 88 -- 108. Google ScholarCross Ref
- K. Price, R.M. Storn, and J.A. Lampinen. 2005. Differential evolution: a practical approach to global optimization. Springer.Google Scholar
- Evgenii Sopov. 2017. Genetic Programming Hyper-heuristic for the Automated Synthesis of Selection Operators in Genetic Algorithms. In International Joint Conference on Computational Intelligence.Google Scholar
- Vladimir Stanovov, Shakhnaz Akhmedova, and Eugene Semenkin. 2022. The automatic design of parameter adaptation techniques for differential evolution with genetic programming. Knowl. Based Syst. 239 (2022), 108070.Google ScholarDigital Library
- Vladimir Stanovov, Shakhnaz Akhmedova, and Eugene Semenkin. 2022. Dual-Population Adaptive Differential Evolution Algorithm L-NTADE. Mathematics (2022).Google Scholar
- R. Tanabe and A.S. Fukunaga. 2013. Success-history based parameter adaptation for differential evolution. In Proceedings of the IEEE Congress on Evolutionary Computation. IEEE Press, 71--78. Google ScholarCross Ref
- J. Woodward and J. Swan. 2012. The automatic generation of mutation operators for genetic algorithms. In GECCO '12.Google Scholar
- Jingqiao Zhang and Arthur C. Sanderson. 2007. JADE: Self-adaptive differential evolution with fast and reliable convergence performance. 2007 IEEE Congress on Evolutionary Computation (2007), 2251--2258.Google ScholarCross Ref
Index Terms
- Genetic Programming for Automatic Design of Parameter Adaptation in Dual-Population Differential Evolution
Recommendations
An improved adaptive differential evolution algorithm with population adaptation
GECCO '13: Proceedings of the 15th annual conference on Genetic and evolutionary computationIn differential evolution (DE), there are many adaptive algorithms proposed for parameters adaptation. However, they mainly aim at tuning the amplification factor F and crossover probability CR. When the population diversity is at a low level or the ...
Multi-population differential evolution with adaptive parameter control for global optimization
GECCO '11: Proceedings of the 13th annual conference on Genetic and evolutionary computationDifferential evolution (DE) is one of the most successful evolutionary algorithms (EAs) for global numerical optimization. Like other EAs, maintaining population diversity is important for DE to escape from local optima and locate a near-global optimum. ...
Improving the search efficiency of differential evolution algorithm by population diversity analysis and adaptation of mutation step sizes
The aim of this research work is to improve the efficiency of differential evolution (DE) algorithm, at the cases of its unsuccessful searches. Initially, this work discusses and compares different methods to measure the population diversity of DE ...
Comments