Many real-world applications, such as industrial manufacturing systems and water distribution networks, are complex systems, which may be hard to describe with explicit mathematical models. These are commonly labeled as black-box problems. Due to the increasing complexities of today’s fast changing environment, the demands for solving problems without any explicitly defined mathematical functions have dramatically increased. Traditional mathematical solvers, for example, the gradient descent method and the quasi-Newton methods, cannot be easily used to solve complex black-box optimization problems without gradient information. Evolutionary optimization as such provides the appropriate gradient-free alternative for solving black-box problems. However, with the rapid development of complex systems, the optimization problems become much larger. For example, the dimension of objective functions, decision variables or constraints is high, which poses challenges to existing evolutionary algorithms.

This special issue has attracted researchers to report the newest research on the development and applications in the field of evolutionary optimization for large complex problems. Following a rigorous peer review process, five papers have been accepted for publication in this special issue.

The first paper included in the special issue is entitled “fSDE: Efficient Evolutionary Optimisation for Many-Objective Aero-Engine Calibration” authored by Liu et al., which models a real aero-engine calibration problem as a many-objective optimisation problem. A fast many-objective evolutionary optimisation algorithm with shift-based density estimation, called fSDE, is designed to search for parameters with an acceptable performance accuracy and improve the calibration efficiency. Experiments on the benchmark test suite and a real aero-engine calibration problem show its superior performance.

The second paper included in the special issue is entitled “Accelerate the Optimization of Large-Scale Manufacturing Planning Using Game Theory” authored by Zhen et al., where a real-world manufacturing problem is modeled as a bi-objective integer programming problem. To deal with the large-scale problems with such block-like structures, authors propose a game theory based decomposition algorithm. Extensive experimental results on real-world industrial manufacturing planning problems show that the proposed method is more effective than the world fastest commercial solver Gurobi.

The third paper included in the special issue is entitled “Two-stage Improved Grey Wolf Optimization Algorithm for Feature Selection on High-dimensional Classification” authored by Shen and Zhang, where a two-stage improved gray wolf optimization (IGWO) algorithm for wrapper feature selection on high-dimensional data is proposed to reduce the computational cost. In the first stage, a multilayer perceptron (MLP) network is first trained to construct an integer optimization problem for pre-selection of features and optimization of the hidden layer structure. In the second stage, an MLP network is retrained using the compressed dataset, and the proposed algorithm is employed to construct the discrete optimization problem for feature selection. The experimental results show that the proposed algorithm not only removes almost more than 95.7% of the features in all datasets, but also has better classification accuracy on the test set.

The forth paper included in the special issue is entitled “A Hybrid Ant Lion Optimization Chicken Swarm Optimization Algorithm for Charger Placement Problem” authored by Deb and Gao, which proposes a novel metaheuristic considering the hybridization of Chicken Swarm Optimization (CSO) with Ant Lion Optimization (ALO) for effectively and efficiently coping with the charger placement problem. The hybrid algorithm is tested on the standard benchmark functions as well as the above charger placement problem. Simulation results demonstrate that it performs moderately better than the counterpart methods.

The fifth paper included in the special issue is entitled “Simplified Phasmatodea Population Evolution Algorithm for Optimization” authored by Song et al., which proposes a population evolution algorithm to deal with optimization problems based on the evolution characteristics of the Phasmatodea (stick insect) population. The proposed imitates the characteristics of convergent evolution, path dependence, population growth and competition in the evolution of the stick insect population in nature. The stick insect population tends to be the nearest dominant population in the evolution process, and the favorable evolution trend is more likely to be inherited by the next generation. Experiments on 30 benchmark functions and several engineering optimization problems show the good performance of the proposed algorithm.

The sixth paper included in the special issue is entitled “Surrogate-assisted evolutionary algorithm for expensive constrained multi-objective discrete optimization problems” authored by Q. Gu et al., which proposes a random forest-assisted evolutionary algorithm to deal with expensive constrained multi-objective discrete optimization problems. Also, an improved stochastic ranking strategy based on the fitness mechanism and adaptive probability operator is presented, which considers both convergence and diversity to advance the quality of candidate solutions. Numerical experiments on benchmark problems demonstrate that the proposed algorithm is very promising for the expensive constrained multi-objective discrete optimization problems.

The guest editors of this special issue would like to thank Prof. Yaochu Jin, the Editor-in-Chief of Complex & Intelligence System, for his great support in initiating and developing this special issue together. Many thanks to all members of the editorial team for their kind support during the editing process of this special issue. Last but not least, we would also like to thank the authors for submitting their valuable research outcomes as well as the reviewers who have critically evaluated the papers. We sincerely hope and expect that readers will find this special issue useful.