Hybrid evolutionary algorithm with extreme machine learning fitness function evaluation for two-stage capacitated facility location problems

•A theorem characterizing the property of the optimal solution is presented.•A hybrid evolutionary algorithm (HEA) is proposed.•Extreme machine learning is used to approximate the fitness of most individuals.•Two heuristics are incorporated to generate a good initial population.•The proposed algorit...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Expert systems with applications Ročník 71; s. 57 - 68
Hlavní autori: Guo, Peng, Cheng, Wenming, Wang, Yi
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York Elsevier Ltd 01.04.2017
Elsevier BV
Predmet:
Algorithms
Artificial intelligence
Computation
Customer satisfaction
Evolutionary algorithm
Evolutionary algorithms
Experiments
Extreme machine learning
Facility location
Fitness
Fitness approximation
Heuristic
Industrial plants
Local search
Machine learning
Operations research
Position (location)
Search process
Site selection
Storage capacity
Transportation
Facility location
Local search
Fitness approximation
Evolutionary algorithm
Extreme machine learning
ISSN:0957-4174, 1873-6793
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:•A theorem characterizing the property of the optimal solution is presented.•A hybrid evolutionary algorithm (HEA) is proposed.•Extreme machine learning is used to approximate the fitness of most individuals.•Two heuristics are incorporated to generate a good initial population.•The proposed algorithm is computationally effective. This paper considers the two-stage capacitated facility location problem (TSCFLP) in which products manufactured in plants are delivered to customers via storage depots. Customer demands are satisfied subject to limited plant production and limited depot storage capacity. The objective is to determine the locations of plants and depots in order to minimize the total cost including the fixed cost and transportation cost. However, the problem is known to be NP-hard. A practicable exact algorithm is impossible to be developed. In order to solve large-sized problems encountered in the practical decision process, an efficient alternative approximate method becomes more valuable. This paper aims to propose a hybrid evolutionary algorithm framework with machine learning fitness approximation for delivering better solutions in a reasonable amount of computational time. In our study, genetic operators are adopted to perform the search process and a local search strategy is used to refine the best solution found in the population. To avoid the expensive consumption of computational time during the fitness evaluating process, the framework uses extreme machine learning to approximate the fitness of most individuals. Moreover, two heuristics based on the characteristics of the problem is incorporated to generate a good initial population. Computational experiments are performed on two sets of test instances from the recent literature. The performance of the proposed algorithm is evaluated and analyzed. Compared with other algorithms in the literature, the proposed algorithm can find the optimal or near-optimal solutions in a reasonable amount of computational time. By employing the proposed algorithm, facilities can be positioned more efficiently, which means the fixed cost and the transportation cost can be decreased significantly, and organizations can enhance competitiveness by using the optimized facility location scheme.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0957-4174
1873-6793
DOI:10.1016/j.eswa.2016.11.025