Various benchmark sets have already been proposed to facilitate comparison between metaheuristics, or evolutionary algorithms. During the competition, typically algorithms are allowed either to run until the allowed n...
详细信息
Various benchmark sets have already been proposed to facilitate comparison between metaheuristics, or evolutionary algorithms. During the competition, typically algorithms are allowed either to run until the allowed number of function calls is exhausted (and one compares the quality of solutions found), or until a required objective function value is obtained (one compares the speed in reaching the required solution). During the last 20 years several problem sets were defined using the first approach. In this study, we test 73 optimization algorithms proposed between the 1960 & PRIME;s and 2022 on nine competitions based on four sets of problems (CEC 2011, CEC 2014, CEC 2017, and CEC 2020) with different dimensionalities. We intend to test the original versions of 73 algorithms "as they are", with control parameters proposed by the authors of the particular method. The recent benchmark set, CEC 2020, includes fewer problems and allows much more function calls than the former sets. As a result, one group of algorithms perform best on older, a different one on the more recent (CEC 2020) benchmark sets. Almost all algorithms that perform best on CEC 2020 set achieve moderate -to-poor performance on older sets, including real-world problems from CEC 2011. algorithms that perform best on older sets are more flexible than those that perform best on CEC 2020 benchmark. The choice of the benchmark may have a crucial impact on the final ranking of algorithms. The lack of tuning may affect the results that were obtained in this study, hence it is highly recommended to repeat a similar large-scale comparison with control parameters of each algorithm tuned, best by different methods, separately for each benchmark set.
Initialization of metaheuristics is a crucial topic that lacks a comprehensive and systematic review of the state of the art. Providing such a review requires in-depth study and knowledge of the advances and challenge...
详细信息
Initialization of metaheuristics is a crucial topic that lacks a comprehensive and systematic review of the state of the art. Providing such a review requires in-depth study and knowledge of the advances and challenges in the broader field of metaheuristics, especially with regard to diversification strategies, in order to assess the proposed methods and provide insights for initialization. Motivated by the aforementioned research gap, we provide a related review and begin by describing the main metaheuristic methods and their diversification mechanisms. Then, we review and analyze the existing initialization approaches while proposing a new categorization of them. Next, we focus on challenging optimization problems, namely constrained and discrete optimization. Lastly, we give insights on the initialization of local search approaches.
The application of evolutionary algorithms (EAs) to complex engineering optimization problems may present difficulties as they require many evaluations of the objective functions by computationally expensive simulatio...
详细信息
The application of evolutionary algorithms (EAs) to complex engineering optimization problems may present difficulties as they require many evaluations of the objective functions by computationally expensive simulation procedures. To deal with this issue, surrogate models have been employed to replace those expensive simulations. In this work, a surrogate assisted evolutionary optimization procedure is proposed. The procedure combines the differential evolution method with a k-nearest neighbors (k-NN) similarity-based surrogate model. In this approach, the database that stores the solutions evaluated by the exact model, which are used to approximate new solutions, is managed according to a merit scheme. Constraints are handled by a rank-based technique that builds multiple separate queues based on the values of the objective function and the violation of each constraint. Also, to avoid premature convergence of the method, a strategy that triggers a random reinitialization of the population is considered. The performance of the proposed method is assessed by numerical experiments using 24 constrained benchmark functions and 5 mechanical engineering problems. The results show that the method achieves optimal solutions with a remarkably reduction in the number of function evaluations compared to the literature.
Surrogate models are techniques to approximate the objective functions of expensive optimization problems. Recently, Random Forests have been studied as a surrogate model technique for combinatorial optimization probl...
详细信息
Surrogate models are techniques to approximate the objective functions of expensive optimization problems. Recently, Random Forests have been studied as a surrogate model technique for combinatorial optimization problems. Nonetheless, Random Forests contain several hyper-parameters that are used to control the prediction process. Despite their importance, research on the effects of these hyper-parameters is scarce. Therefore, this paper performs a systematic investigation of the effects of different combinations of values for the Random Forest hyper-parameters on the approximation of well-known multi-objective combinatorial benchmark problems. The results show that the number of samples to consider when building each tree and the minimum number of samples to be at the leaf node are the two most important hyper-parameters in this context.
Many real-world problems can be naturally formulated as discrete multi-objective optimisation (DMOO) problems. We have proposed a novel Physarum-inspired competition algorithm (PCA) to tackle these DMOO problems. Our ...
详细信息
Many real-world problems can be naturally formulated as discrete multi-objective optimisation (DMOO) problems. We have proposed a novel Physarum-inspired competition algorithm (PCA) to tackle these DMOO problems. Our algorithm is based on hexagonal cellular automata (CA) as a representation of problem search space and reaction-diffusion systems that control the Physarum motility. Physarum's decision-making power and the discrete properties of CA have made our algorithm a perfectly suitable approach to solve DMOO problems. Each cell in the CA grid will be decoded as a solution (objective function) and will be regarded as a food resource to attract Physarum. The n-dimensional generalisation of the hexagonal CA grid has allowed us to extend the solving capabilities of our PCA from only 2-D to n-D optimisation problems. We have implemented a novel restart procedure to select the global Pareto frontier based on both personal experience and shared information. Extensive experimental and statistical analyses were conducted on several benchmark functions to assess the performance of our PCA against other evolutionary algorithms. As far as we know, this study is the first attempt to assess algorithms that solve DMOO problems, with a large number of benchmark functions and performance indicators. Our PCA has confirmed our assumption that individual skills of competing Physarum are more efficient in exploration and increase the diversity of the solutions. It has achieved the best performance for the Spread indicator (diversity), similar performance results compared to the strength Pareto evolutionary algorithm (SPEA2) and even outperformed other well-established genetic algorithms.
Despite III-nitride and silicon carbide being the materials of choice for a wide range of applications, theoretical studies on their quaternary alloys are limited. Here, we report a systematic computational study on t...
详细信息
Despite III-nitride and silicon carbide being the materials of choice for a wide range of applications, theoretical studies on their quaternary alloys are limited. Here, we report a systematic computational study on the electronic structural properties of (SiC)(x) (AlN)(1-x) and (SiC)(x) (AlN)(1-x) quaternary alloys, based on state-of-the-art first-principles evolutionary algorithms. Trigonal (SiCAlN, space group P3m1) and orthorhombic (SiCGaN, space group Pmn2(1)) crystal phases were as predicted for x = 0.5. SiCAlN showed relatively weak thermodynamic instability, while that of SiCGaN was slightly elevated, rendering them both dynamically and mechanically stable at ambient pressure. Our calculations revealed that the Pm31 crystal has high elastic constants, (C-11 similar to 458 GPa and C-33 similar to 447 GPa), a large bulk modulus (B-0 similar to 210 GPa), and large Young's modulus (E similar to 364 GPa), and our results suggest that SiCAlN is potentially a hard material, with a Vickers hardness of 21 GPa. Accurate electronic structures of SiCAlN and SiCGaN were calculated using the Tran-Blaha modified Becke-Johnson semi-local exchange potential. Specifically, we found evidence that SiCGaN has a very wide direct bandgap of 3.80 eV, while that of SiCAlN was indirect at 4.6 eV. Finally, for the quaternary alloys, a relatively large optical bandgap bowing of similar to 3 eV was found for SiCGaN, and a strong optical bandgap bowing of 0.9 eV was found for SiCAlN.
In the past few decades, meta-heuristic algorithms have become a research hotspot in the field of evolutionary computing. The electric fish optimization algorithm (EFO) is a new meta-heuristic algorithm. Because of it...
详细信息
In the past few decades, meta-heuristic algorithms have become a research hotspot in the field of evolutionary computing. The electric fish optimization algorithm (EFO) is a new meta-heuristic algorithm. Because of its simplicity and easy implementation, it has attracted the attention of researchers. However, it still faces premature convergence and poor balance between exploration and exploitation. To address this problems, an orthogonal electric fish optimization algorithm with quantization (QOXEFO) is proposed in this paper. In QOXEFO, orthogonal cross-design and quantification technique are employed to enhance the diversity of population and convergence precision of EFO. Secondly, the dynamic boundary mechanism is adopted to improve the convergence speed of EFO. At the same time, a sine-based update strategy of active electrolocation is used to change the direction of movement of individuals, thereby helping them jump out of the local optimum. Finally, the CEC2017 benchmark function and Speed reducer design problem are used to verify the performance of the proposed QOXEFO. Experimental results and statistical analysis show that compared with 9 famous evolutionary algorithms, QOXEFO is competitive in solution accuracy and convergence speed.
Numerical comparison serves as a major tool in evaluating the performance of optimization algorithms, especially nondeterministic algorithms, but existing methods may suffer from a "cycle ranking" paradox an...
详细信息
Numerical comparison serves as a major tool in evaluating the performance of optimization algorithms, especially nondeterministic algorithms, but existing methods may suffer from a "cycle ranking" paradox and/or a "survival of the nonfittest" paradox. This article searches for paradox-free data analysis methods for numerical comparison. It is discovered that a class of sufficient conditions exist for designing paradox-free analysis. Rigorous modeling and deduction are applied to a class of profile methods employing a filter. It is thus further discovered and proven that algorithm-independent filter conditions can prevent cycle ranking and survival of nonfittest paradoxes from occurring. By adopting an algorithm-independent filter, popular profile methods such as the "modified data profile method," "the accuracy profile method," and "the operational characteristics zones method" can be paradox free in comparing or benchmarking the performance of optimization algorithms.
Mobile Crowdsensing (MCS), which assigns outsourced sensing tasks to volunteer workers, has become an appealing paradigm to collaboratively collect data from surrounding environments. However, during actual task imple...
详细信息
Mobile Crowdsensing (MCS), which assigns outsourced sensing tasks to volunteer workers, has become an appealing paradigm to collaboratively collect data from surrounding environments. However, during actual task implementation, various unpredictable disruptions are usually inevitable, which might cause a task execution failure and thus impair the benefit of MCS systems. Practically, via reactively shifting the pre-determined assignment scheme in real time, it is usually impossible to develop reassignment schemes without a sacrifice of the system performance. Against this background, we turn to an alternative solution, i.e., proactively creating a robust task assignment scheme offline. In this work, we provide the first attempt to investigate an important and realistic RoBust Task Assignment (RBTA) problem in MCS systems, and try to strengthen the assignment scheme's robustness while minimizing the workers' traveling detour cost simultaneously. By leveraging the workers' spatiotemporal mobility, we propose an assignment-graph-based approach. First, an assignment graph is constructed to locally model the assignment relationship between the released MCS tasks and available workers. And then, under the framework of evolutionary multi-tasking, we devise a population-based optimization algorithm, namely EMTRA, to effectively achieve adequate Pareto-optimal schemes. Comprehensive experiments on two real-world datasets clearly validate the effectiveness and applicability of our proposed approach.
In the field of engineering design, there is a class of constrained multi-objective optimization problems where the optimal solutions are often found at the constraint boundaries. However, effectively utilizing the in...
详细信息
暂无评论