The paper discusses the possibility to manage search direction in genetic algorithm crossover and mutation operators using "Depository of Weak Individuals' Fitness Values". In order to control crossover ...
详细信息
ISBN:
(纸本)9788021436756
The paper discusses the possibility to manage search direction in genetic algorithm crossover and mutation operators using "Depository of Weak Individuals' Fitness Values". In order to control crossover and mutation, it was decided to observe the individuals that take part in those operators. All offsprings that are produced during crossover operator run will be compared with the individuals that are their predecessors - worse individual fitness value will be kept in the "Depository of Weak Individuals' Fitness Values" during all generations. And mutation operator consists of several steps - individual's mutation will be repeated until better offspring is found If better solution is found, then the individual selected for mutation will be kept during all generations in the "Depository of Weak Individuals Fitness Values".
Optimal capacitor placement problem is a significant and precious strategy which can be supposed as an always appropriate solution to reduce the operating costs in the power systems. Nevertheless, as the result of non...
详细信息
Optimal capacitor placement problem is a significant and precious strategy which can be supposed as an always appropriate solution to reduce the operating costs in the power systems. Nevertheless, as the result of nonlinear and discrete characteristics of this problem, traditional optimization methods can not solve it effectively. Therefore, this paper proposes a novel optimization framework based on shuffled frog leaping algorithm (SFLA) to solve the optimal capacitor placement and sizing problem properly. In this regard, a new modification approach based on the mutation and crossoveroperators is suggested to improve the local search ability of this algorithm. The effectiveness and satisfying performance of the proposed method is assessed on two IEEE test systems. Comparative results sow the superiority of the proposed optimization method than the other popular methods in the area.
A real-valued genetic algorithm is proposed to the optimization problem with continuos variables. It is composed of a simple and general-purpose dynamic scaled fitness and selection operator, real-valued crossover ope...
详细信息
ISBN:
(纸本)0780337263
A real-valued genetic algorithm is proposed to the optimization problem with continuos variables. It is composed of a simple and general-purpose dynamic scaled fitness and selection operator, real-valued crossover operator, mutationoperators and adaptive probabilities for these operators. The proposed algorithm are tested by two generally used functions and is used to the training of a neural network for image recognition. Experiment results show that the proposed algorithm is a efficient global optimization algorithm.
University course timetabling is one of the most important and time-consuming problem which takes place frequently in all the educational institutes. This paper proposes design and implementation system to generate ti...
详细信息
ISBN:
(纸本)9781479900800
University course timetabling is one of the most important and time-consuming problem which takes place frequently in all the educational institutes. This paper proposes design and implementation system to generate timetable based on genetic algorithm using different combinations selection algorithm and mutation types. Two cases small problem and big problem are studied. The results show that two cases tournament selection is giving solutions better than roulette wheel Selection. The worst pair is roulette wheel selection and mutation. mutation error method helps to reach to the best solution faster. In case of conflicts and no solution, our system generates a report, containing conflict constraints that must be remove or modified.
作者：
Bilgesu AkErdem KocBilgesu AK
Ondokuz Mayıs University Industrial Engineering Department Samsun-55139 Turkey Erdem KOÇ
Ondokuz Mayıs University Mechanical Engineering Department Samsun-55139 Turkey
Parallel Machine Scheduling (PMS) and Flexible Job-shop Scheduling (FJS) are the hardest combinatorial optimization problems, they require very large scale search space. Solving this kind of combinatorial optimization...
详细信息
Parallel Machine Scheduling (PMS) and Flexible Job-shop Scheduling (FJS) are the hardest combinatorial optimization problems, they require very large scale search space. Solving this kind of combinatorial optimization problems with classical methods are almost impossible or takes considerable long time. Genetic Algorithms (GAs) have shown great advantages in solving combinatorial problems. GAs have the flexibility of set up different chromosome structures in case of distinctive scheduling problems. This paper presents a PMS and FJS chromosome structure, crossover and mutation operator from literature in order to guide for new researchers about scheduling with GAs.
The Resource Constrained Project Scheduling Problem (RCPSP) is a prevalent problem in the domains of Project Management and Operations Research. This problem demands a huge number of computational resources as the pro...
详细信息
The Resource Constrained Project Scheduling Problem (RCPSP) is a prevalent problem in the domains of Project Management and Operations Research. This problem demands a huge number of computational resources as the project's complexity increases. Hence, approximate methods using heuristics and metaheuristics have proven to provide feasible solutions to the problem in acceptable time. This research adapts a prominent Swarm Intelligence (SI) metaheuristic, the Firefly Algorithm (FA), to solve the RCPSP with some modifications. By applying a 2-point crossover for the intensity-based firefly movement, a discrete framework has been provided. Further, to reduce the occurrence of the solution being stuck in the local optima, a swap-based mutation is introduced. The performance of the proposed research has been thoroughly evaluated through extensive experiments conducted on widely recognized benchmark instances. Comparison with seminal works demonstrated the competitiveness of the approach.
暂无评论