scholarly journals What Can We Learn from Multi-Objective Meta-Optimization of Evolutionary Algorithms in Continuous Domains?

Mathematics ◽  
2019 ◽  
Vol 7 (3) ◽  
pp. 232 ◽  
Author(s):  
Roberto Ugolotti ◽  
Laura Sani ◽  
Stefano Cagnoni
Keyword(s):  
Evolutionary Algorithms ◽  
Fitness Function ◽  
Target Function ◽  
Optimization Methods ◽  
Multi Objective ◽  
Multi Objective Genetic Algorithm ◽  
Continuous Domains ◽  
Level Method ◽  
Meta Optimization ◽  
Function Time

Properly configuring Evolutionary Algorithms (EAs) is a challenging task made difficult by many different details that affect EAs’ performance, such as the properties of the fitness function, time and computational constraints, and many others. EAs’ meta-optimization methods, in which a metaheuristic is used to tune the parameters of another (lower-level) metaheuristic which optimizes a given target function, most often rely on the optimization of a single property of the lower-level method. In this paper, we show that by using a multi-objective genetic algorithm to tune an EA, it is possible not only to find good parameter sets considering more objectives at the same time but also to derive generalizable results which can provide guidelines for designing EA-based applications. In particular, we present a general framework for multi-objective meta-optimization, to show that “going multi-objective” allows one to generate configurations that, besides optimally fitting an EA to a given problem, also perform well on previously unseen ones.

Optimizing of Turning Parameters Using Multi-Objective Genetic Algorithm

2010 ◽  
Vol 118-120 ◽  
pp. 359-363 ◽  
Author(s):  
Ramezan Ali Mahdavinejad
Keyword(s):  
Genetic Algorithm ◽  
Removal Rate ◽  
Target Function ◽  
Optimization Methods ◽  
Optimization Method ◽  
Surface Finishing ◽  
Multi Objective ◽  
Multi Objective Genetic Algorithm ◽  
Engineering Problems ◽  
Stock Removal

In this research, the turning parameters of steel are optimized via multi-objective genetic algorithm and multi-objective harmony research algorithm. These two algorithms are known as strong and powerful tools in optimization of engineering problems. The stock removal rate and surface roughness, as two main of output parameters are the target function and have been considered to be optimized. Since, there are two functions here; we can not use the ordinary optimization method with single-objective algorithm. In steel machining, the stock removal rate usually decreases with the surface finishing and visa versa. Therefore, it is necessary to define the weight of these parameters. In this paper the importance of each of these parameters are determined with weight sum method. In this research, the optimization methods to solve the problems via these two algorithms are discussed first. Then, the steel samples are machined and the output data are analyzed and optimized.

Comparison of Multi-Objective Evolutionary Algorithms to Prioritize Regression Test Cases

2021 ◽  
Vol 9 (12) ◽  
pp. 1445-1454
Keyword(s):  
Fault Detection ◽  
Evolutionary Algorithms ◽  
Fitness Function ◽  
Optimal Solution ◽  
Test Suite ◽  
Test Case ◽  
Test Cases ◽  
Nsga Ii ◽  
Multi Objective ◽  
Regression Test

Regression testing is one of the most critical testing activities among software product verification activities. Nevertheless, resources and time constraints could inhibit the execution of a full regression test suite, hence leaving us in confusion on what test cases to run to preserve the high quality of software products. Different techniques can be applied to prioritize test cases in resource-constrained environments, such as manual selection, automated selection, or hybrid approaches. Different Multi-Objective Evolutionary Algorithms (MOEAs) have been used in this domain to find an optimal solution to minimize the cost of executing a regression test suite while obtaining maximum fault detection coverage as if the entire test suite was executed. MOEAs achieve this by selecting set of test cases and determining the order of their execution. In this paper, three Multi Objective Evolutionary Algorithms, namely, NSGA-II, IBEA and MoCell are used to solve test case prioritization problems using the fault detection rate and branch coverage of each test case. The paper intends to find out what’s the most effective algorithm to be used in test cases prioritization problems, and which algorithm is the most efficient one, and finally we examined if changing the fitness function would impose a change in results. Our experiment revealed that NSGA-II is the most effective and efficient MOEA; moreover, we found that changing the fitness function caused a significant reduction in evolution time, although it did not affect the coverage metric.

scholarly journals A Smart-Distributed Pareto Front Using the ev-MOGA Evolutionary Algorithm

2014 ◽  
Vol 23 (02) ◽  
pp. 1450002 ◽  
Author(s):  
J. M. Herrero ◽  
G. Reynoso-Meza ◽  
M. Martínez ◽  
X. Blasco ◽  
J. Sanchis
Keyword(s):  
Pareto Front ◽  
Optimization Methods ◽  
Optimization Method ◽  
Initial Condition ◽  
Multi Objective Optimization ◽  
Computational Burden ◽  
Multi Objective ◽  
Multi Objective Genetic Algorithm ◽  
Normalized Normal Constraint ◽  
Normal Constraint

Obtaining multi-objective optimization solutions with a small number of points smartly distributed along the Pareto front is a challenge. Optimization methods, such as the normalized normal constraint (NNC), propose the use of a filter to achieve a smart Pareto front distribution. The NCC optimization method presents several disadvantages related with the procedure itself, initial condition dependency, and computational burden. In this article, the epsilon-variable multi-objective genetic algorithm (ev-MOGA) is presented. This algorithm characterizes the Pareto front in a smart way and removes the disadvantages of the NNC method. Finally, examples of a three-bar truss design and controller tuning optimizations are presented for comparison purposes.

Optimization of Production Equipment Layout Based on Fuzzy Decision and Evolutionary Algorithm

2019 ◽  
Vol 11 (3) ◽  
pp. 13-29
Author(s):  
Wenfang Chen
Keyword(s):  
Evolutionary Algorithms ◽  
Optimization Model ◽  
Fitness Function ◽  
Production Equipment ◽  
Production Costs ◽  
Practical Case ◽  
Fuzzy Decision ◽  
Pareto Solution ◽  
Total Cost ◽  
Multi Objective

A method of optimizing equipment layout is proposed in production equipment layout of a complex manufacturing system, using fuzzy decisions combined with evolutionary algorithms. First, the optimization model is improved, the total cost is minimized, while the requirements of adjacent equipment and the space utilization are maximized; the material handling cost, the resetting cost, the loss of production costs are considered in the total cost objective. Second, this method takes into account the ambiguity of the satisfaction and priority of users such as cost, utilization and proximity requirements, based on the fuzzy decision theory, the multi-objective optimization model is fuzzified, and the fuzzy fitness function is designed to evaluate the pareto solution set according to the user's priority relation. Based on the characteristics of the solution model, the chromosomal coding method of multi-objective evolutionary algorithms and the genetic operation mode are improved, and the practicability and efficiency of the model is improved. Finally, the effectiveness of the method is proved by the optimization of the practical case.

An Efficient Framework Using Normalized Dominance Operator for Multi-Objective Evolutionary Algorithms

2019 ◽  
Vol 10 (1) ◽  
pp. 15-37 ◽  
Author(s):  
Muneendra Ojha ◽  
Krishna Pratap Singh ◽  
Pavan Chakraborty ◽  
Shekhar Verma
Keyword(s):  
Evolutionary Algorithms ◽  
Pareto Front ◽  
Optimization Problem ◽  
Computational Cost ◽  
Optimization Methods ◽  
Objective Test ◽  
Test Problems ◽  
Multi Objective Optimization ◽  
Pareto Dominance ◽  
Multi Objective

Multi-objective optimization algorithms using evolutionary optimization methods have shown strength in solving various problems using several techniques for producing uniformly distributed set of solutions. In this article, a framework is presented to solve the multi-objective optimization problem which implements a novel normalized dominance operator (ND) with the Pareto dominance concept. The proposed method has a lesser computational cost as compared to crowding-distance-based algorithms and better convergence. A parallel external elitist archive is used which enhances spread of solutions across the Pareto front. The proposed algorithm is applied to a number of benchmark multi-objective test problems with up to 10 objectives and compared with widely accepted aggregation-based techniques. Experiments produce a consistently good performance when applied to different recombination operators. Results have further been compared with other established methods to prove effective convergence and scalability.

Multi-objective Design Optimization of Microdisk Resonator

2020 ◽  
Vol 10 (4) ◽  
pp. 478-485
Author(s):  
M. Sutagundar ◽  
B.G. Sheeparamatti ◽  
D.S. Jangamshetti
Keyword(s):  
Design Optimization ◽  
Optimization Methods ◽  
Interior Point Algorithm ◽  
Multi Objective Optimization ◽  
Disk Resonator ◽  
Multi Objective ◽  
Design Time ◽  
Full Wave ◽  
Multi Objective Genetic Algorithm ◽  
Motional Resistance

Objective: This paper presents a multi-objective design optimization of MEMS disk resonator using two techniques. Methods: Determining the optimized dimensions of disk resonator for a particular resonance frequency so as to achieve higher quality factor and lower motional resistance is attempted. One technique used is constraint-based multi-objective optimization using the interior-point algorithm. The second technique is based on multi-objective genetic algorithm. Results: The algorithms are implemented using MATLAB. The two techniques of optimization are compared. Conclusion: The developed optimization methods can provide faster design optimization compared to full-wave simulators resulting in significant reduction of design time.

Multi-Objective Optimization with Controlled Model Assisted Evolution Strategies

2009 ◽  
Vol 17 (4) ◽  
pp. 577-593 ◽  
Author(s):  
Jan Braun ◽  
Johannes Krettek ◽  
Frank Hoffmann ◽  
Torsten Bertram
Keyword(s):  
Evolutionary Algorithms ◽  
Optimization Problems ◽  
Fitness Function ◽  
Pressure Control ◽  
Evolution Strategy ◽  
Model Quality ◽  
Contrast Model ◽  
Loop Optimization ◽  
Multi Objective ◽  
Search Spaces

Evolutionary algorithms perform robust search in complex and high dimensional search spaces, but require a large number of fitness evaluations to approximate optimal solutions. These characteristics limit their potential for hardware in the loop optimization and problems that require extensive simulations and calculations. Evolutionary algorithms do not maintain their knowledge about the fitness function as they only store solutions of the current generation. In contrast, model assisted evolutionary algorithms utilize the information contained in previously evaluated solutions in terms of a data based model. The convergence of the evolutionary algorithm is improved as some selection decisions rely on the model rather than to invoke expensive evaluations of the true fitness function. The novelty of our scheme stems from the preselection of solutions based on an instance based fitness model, in which the selection pressure is adjusted to the quality of model. This so-called λ-control adapts the number of true fitness evaluations to the monitored model quality. Our method extends the previous approaches for model assisted scalar optimization to multi-objective problems by a proper redefinition of model quality and preselection pressure control. The analysis on multi-objective benchmark optimization problems not only confirms the superior convergence of the model assisted evolution strategy in comparison with a multi-objective evolution strategy but also the positive effect of regulated preselection in contrast to merely static preselection.

scholarly journals ESTIMATES FROM EVOLUTIONARY ALGORITHMS THEORY APPLIED TO DIRECTED EVOLUTION

2020 ◽  
pp. 56-76
Author(s):  
A. V. Eremeev ◽  
A. V. Spirov
Keyword(s):  
Evolutionary Algorithms ◽  
Evolutionary Computation ◽  
Dna Sequences ◽  
Upper Bound ◽  
Fitness Function ◽  
Optimization Methods ◽  
Target Area ◽  
Expected Time ◽  
Royal Road ◽  
Expected Hitting Time

The field of evolutionary computation emerged in the area of computer science due to transfer of ideas from biology and developed independently for several decades, enriched with techniques from probability theory, complexity theory and optimization methods. Our aim is to consider how some recent results form the theory of evolutionary computation may be transferred back into biology. It has been noted that the non-elitist evolutionary algorithms optimizing Royal Road fitness functions may be considered as models of evolutionary search for the synthetic enhancer sequences “from scratch”. This problem asks for a tight cluster of supposedly unknown motifs from the initial random (or partially random) set of DNA sequences using SELEX approaches. We apply the upper bounds on the expected hitting time of a target area of genotypic space in order to upper-bound the expected time to finding a sufficiently fit series of motifs in a SELEX procedure. On the other hand, using the theory of evolutionary computation, we propose an upper bound on the expected proportion of the DNA sequences with sufficiently high fitness at a given round of a SELEX procedure. Both approaches are evaluated in computational experiment, using a Royal Road fitness function as a model of the SELEX procedure for regulatory FIS factor binding site.

A Kriging Metamodel Assisted Multi-Objective Genetic Algorithm for Design Optimization

2006 ◽  
Author(s):  
Mian Li ◽  
Genzi Li ◽  
Shapour Azarm
Keyword(s):  
Genetic Algorithm ◽  
Design Optimization ◽  
Pareto Frontier ◽  
Computational Cost ◽  
Optimization Methods ◽  
Optimization Approach ◽  
Multi Objective ◽  
Multi Objective Genetic Algorithm ◽  
Main Challenge ◽  
Engineering Design Problems

The high computational cost of population based optimization methods, such as multi-objective genetic algorithms, has been preventing applications of these methods to realistic engineering design problems. The main challenge is to devise methods that can significantly reduce the number of computationally intensive simulation (objective/constraint functions) calls. We present a new multi-objective design optimization approach in that kriging-based metamodeling is embedded within a multi-objective genetic algorithm. The approach is called Kriging assisted Multi-Objective Genetic Algorithm, or K-MOGA. The key difference between K-MOGA and a conventional MOGA is that in K-MOGA some of the design points or individuals are evaluated by kriging metamodels, which are computationally inexpensive, instead of the simulation. The decision as to whether the simulation or their kriging metamodels to be used for evaluating an individual is based on checking a simple condition. That is, it is determined whether by using the kriging metamodels for an individual the non-dominated set in the current generation is changed. If this set is changed, then the simulation is used for evaluating the individual; otherwise, the corresponding kriging metamodels are used. Seven numerical and engineering examples with different degrees of difficulty are used to illustrate applicability of the proposed K-MOGA. The results show that on the average, K-MOGA converges to the Pareto frontier with about 50% fewer number of simulation calls compared to a conventional MOGA.

Sign in / Sign up

Export Citation Format

Share Document