Why Tuning the Control Parameters of Metaheuristic Algorithms Is So Important for Fair Comparison?

Kazíková, Anežka; Pluháček, Michal; Šenkeřík, Roman

doi:10.13164/mendel.2020.2.009

Cited by 26 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Table 1, we show the parameter settings for NNA, DE and ADELP. Based on Kazikova et al [15], it is essential to pay attention to the quality of conducted experiments, especially when comparing several different algorithms. Parameter tuning of a metaheuristic algorithm should be an integral part of the development and testing process because it can influence the performance of the algorithm.…”

Section: Discussionmentioning

confidence: 99%

Approximate Solution for Barrier Option Pricing Using Adaptive Differential Evolution With Learning Parameter

Febrianti

Sidarto

Sumarti

2022

mendel

View full text Add to dashboard Cite

Black-Scholes (BS) equations, which are in the form of stochastic partial differential equations, are fundamental equations in mathematical finance, especially in option pricing. Even though there exists an analytical solution to the standard form, the equations are not straightforward to be solved numerically. The effective and efficient numerical method will be useful to solve advanced and non-standard forms of BS equations in the future. In this paper, we propose a method to solve BS equations using an approach of optimization problems, where a metaheuristic optimization algorithm is utilized to find the best-approximated solutions of the equations. Here we use the Adaptive Differential Evolution with Learning Parameter (ADELP) algorithm. The BS equations being solved are meant to find values of European option pricing that is equipped with Barrier option pricing. The result of our approximation method fits well to the analytical approximation solutions.

show abstract

Section: Discussionmentioning

confidence: 99%

Approximate Solution for Barrier Option Pricing Using Adaptive Differential Evolution With Learning Parameter

Febrianti

Sidarto

Sumarti

2022

mendel

View full text Add to dashboard Cite

show abstract

“…For every run, if the objective function value of the resulting solution was less than or equal to 1E-8, it was considered as zero. For all algorithms, we used the same parameter settings that was used in the corresponding CEC competition [28]. All algorithms were run in a MATLAB R2020b, on a PC with 3.2 GHz Core I5 processor, 16 GB RAM, and Windows 10.…”

Section: Comparison On Algorithms a Algorithm Selection And Experimen...mentioning

confidence: 99%

New Benchmark Functions for Single-Objective Optimization Based on a Zigzag Pattern

Kůdela

Matoušek

2022

IEEE Access

View full text Add to dashboard Cite

Benchmarking plays a crucial role in both development of new optimization methods, and in conducting proper comparisons between already existing methods, particularly in the field of evolutionary computation. In this paper, we develop new benchmark functions for bound-constrained single-objective optimization that are based on a zigzag function. The proposed zigzag function has three parameters that control its behaviour and difficulty of the resulting problems. Utilizing the zigzag function, we introduce four new functions and conduct extensive computational experiments to evaluate their performance as benchmarks. The experiments comprise of using the newly proposed functions in 100 different parameter settings for the comparison of eight different optimization algorithms, which are a mix of canonical methods and best performing methods from the Congress on Evolutionary Computation competitions. Using the results from the computational comparison, we choose some of the parametrization of the newly proposed functions to devise an ambiguous benchmark set in which each of the problems introduces a statistically significant ranking among the algorithms, but the ranking for the entire set is ambiguous with no clear dominating relationship between the algorithms. We also conduct an exploratory landscape analysis of the newly proposed benchmark functions and compare the results with the benchmark functions used in the Black-Box-Optimization-Benchmarking suite. The results suggest that the new benchmark functions are well suited for algorithmic comparisons.

show abstract

“…Because of the above, the obtained result is compared with the previous one in [51], other similar approaches that use different state-of-the-art bio-inspired algorithms, and also with a classical control approach through different study cases. On the other hand, no matter which meta-heuristic is adopted to optimize the controller, it has a set of hyper-parameters that compromise the quality of the solutions it can find [52]. A bad solution could affect the overall performance or even impact the system's stability.…”

Section: A Contributionsmentioning

confidence: 99%

Novel Asynchronous Activation of the Bio-Inspired Adaptive Tuning in the Speed Controller: Study Case in DC Motors

2021

View full text Add to dashboard Cite

The fusion of bio-inspired algorithms into online controller tuning (adaptive controller tuning) is one of the main topics in Intelligent Control. One crucial issue is to reduce the times that the tuning process performs over time. In this work, a novel Asynchronous Adaptive Controller Tuning (AACT) approach is proposed to reduce the number of tuning process activations, and hence, this promotes resource savings in the overall computational cost for the tuning process. In this approach, an event function is designed to determine the control parameter update where the use of identification and predictive stages set the current control parameters. Furthermore, an elitist initialization in the differential evolution algorithm is also incorporated for solving the optimization problems at each stage. The speed regulation of the DC motor under disturbances is the study case in the ACCT approach. Comparative results with state-of-theart bio-inspired algorithms in control tuning reveal in the AACT approach that the elitist initialization in differential evolution notably benefits the controller performance. Moreover, the comparative results with the Synchronous Adaptive Controller Tuning (SACT) approach show that the proposal reduces 61% the tuning process computation frequency with a similar speed regulation performance when disturbances appear.INDEX TERMS Optimal controller tuning, DC motor, Event based tuning, Bio-inspired algorithm.

show abstract

Why Tuning the Control Parameters of Metaheuristic Algorithms Is So Important for Fair Comparison?

Cited by 26 publications

References 19 publications

Approximate Solution for Barrier Option Pricing Using Adaptive Differential Evolution With Learning Parameter

Approximate Solution for Barrier Option Pricing Using Adaptive Differential Evolution With Learning Parameter

New Benchmark Functions for Single-Objective Optimization Based on a Zigzag Pattern

Novel Asynchronous Activation of the Bio-Inspired Adaptive Tuning in the Speed Controller: Study Case in DC Motors

Contact Info

Product

Resources

About