From fitness landscape analysis to designing evolutionary algorithms: The case study in automatic generation of function block applications

Vladimir Mironovich; Maxim Buzdalov; Valeriy Vyatkin

doi:10.1145/3205651.3208230

From fitness landscape analysis to designing evolutionary algorithms: The case study in automatic generation of function block applications

Vladimir Mironovich, Maxim Buzdalov, Valeriy Vyatkin

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference article in proceedings › Scientific › vertaisarvioitu

2 Sitaatiot (Scopus)

Abstrakti

Search-based software engineering, a discipline that often requires finding optimal solutions, can be a viable source for problems that bridge theory and practice of evolutionary computation. In this research we consider one such problem: generation of data connections in a distributed control application designed according to the IEC 61499 industry standard. We perform the analysis of the fitness landscape of this problem and find why exactly the simplistic (1 + 1) evolutionary algorithm is slower than expected when finding an optimal solution to this problem. To counteract, we develop a population-based algorithm that explicitly maximises diversity among the individuals in the population. We show that this measure indeed helps to improve the running times.

Alkuperäiskieli	Englanti
Otsikko	Proceedings of the 2018 Genetic and Evolutionary Computation Conference Companion, GECCO 2018
Kustantaja	ACM
Sivut	1902-1905
Sivumäärä	4
ISBN (elektroninen)	9781450357647
DOI - pysyväislinkit	https://doi.org/10.1145/3205651.3208230
Tila	Julkaistu - 6 heinäk. 2018
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisussa
Tapahtuma	Genetic and Evolutionary Computation Conference - Kyoto, Japani Kesto: 15 heinäk. 2018 → 19 heinäk. 2018

Conference

Conference	Genetic and Evolutionary Computation Conference
Lyhennettä	GECCO
Maa/Alue	Japani
Kaupunki	Kyoto
Ajanjakso	15/07/2018 → 19/07/2018
Muu	A Recombination of the 27th International Conference on Genetic Algorithms (ICGA) and the 23rd Annual Genetic Programming Conference (GP)

Pääsy asiakirjaan

10.1145/3205651.3208230

Muut tiedostot ja linkit

Link to publication in Scopus

Siteeraa tätä

@inproceedings{911f7da07f944e6cb920c949513f0103,

title = "From fitness landscape analysis to designing evolutionary algorithms: The case study in automatic generation of function block applications",

abstract = "Search-based software engineering, a discipline that often requires finding optimal solutions, can be a viable source for problems that bridge theory and practice of evolutionary computation. In this research we consider one such problem: generation of data connections in a distributed control application designed according to the IEC 61499 industry standard. We perform the analysis of the fitness landscape of this problem and find why exactly the simplistic (1 + 1) evolutionary algorithm is slower than expected when finding an optimal solution to this problem. To counteract, we develop a population-based algorithm that explicitly maximises diversity among the individuals in the population. We show that this measure indeed helps to improve the running times.",

keywords = "Evolutionary computation, Population diversity, Program synthesis, Search-based software engineering",

author = "Vladimir Mironovich and Maxim Buzdalov and Valeriy Vyatkin",

year = "2018",

month = jul,

day = "6",

doi = "10.1145/3205651.3208230",

language = "English",

pages = "1902--1905",

booktitle = "Proceedings of the 2018 Genetic and Evolutionary Computation Conference Companion, GECCO 2018",

publisher = "ACM",

address = "United States",

note = "Genetic and Evolutionary Computation Conference, GECCO ; Conference date: 15-07-2018 Through 19-07-2018",

}

Mironovich, V, Buzdalov, M & Vyatkin, V 2018, From fitness landscape analysis to designing evolutionary algorithms: The case study in automatic generation of function block applications. julkaisussa Proceedings of the 2018 Genetic and Evolutionary Computation Conference Companion, GECCO 2018. ACM, Sivut 1902-1905, Genetic and Evolutionary Computation Conference, Kyoto, Japani, 15/07/2018. https://doi.org/10.1145/3205651.3208230

From fitness landscape analysis to designing evolutionary algorithms: The case study in automatic generation of function block applications. / Mironovich, Vladimir; Buzdalov, Maxim; Vyatkin, Valeriy.
Proceedings of the 2018 Genetic and Evolutionary Computation Conference Companion, GECCO 2018. ACM, 2018. s. 1902-1905.

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference article in proceedings › Scientific › vertaisarvioitu

TY - GEN

T1 - From fitness landscape analysis to designing evolutionary algorithms

T2 - Genetic and Evolutionary Computation Conference

AU - Mironovich, Vladimir

AU - Buzdalov, Maxim

AU - Vyatkin, Valeriy

PY - 2018/7/6

Y1 - 2018/7/6

N2 - Search-based software engineering, a discipline that often requires finding optimal solutions, can be a viable source for problems that bridge theory and practice of evolutionary computation. In this research we consider one such problem: generation of data connections in a distributed control application designed according to the IEC 61499 industry standard. We perform the analysis of the fitness landscape of this problem and find why exactly the simplistic (1 + 1) evolutionary algorithm is slower than expected when finding an optimal solution to this problem. To counteract, we develop a population-based algorithm that explicitly maximises diversity among the individuals in the population. We show that this measure indeed helps to improve the running times.

AB - Search-based software engineering, a discipline that often requires finding optimal solutions, can be a viable source for problems that bridge theory and practice of evolutionary computation. In this research we consider one such problem: generation of data connections in a distributed control application designed according to the IEC 61499 industry standard. We perform the analysis of the fitness landscape of this problem and find why exactly the simplistic (1 + 1) evolutionary algorithm is slower than expected when finding an optimal solution to this problem. To counteract, we develop a population-based algorithm that explicitly maximises diversity among the individuals in the population. We show that this measure indeed helps to improve the running times.

KW - Evolutionary computation

KW - Population diversity

KW - Program synthesis

KW - Search-based software engineering

UR - http://www.scopus.com/inward/record.url?scp=85051521687&partnerID=8YFLogxK

U2 - 10.1145/3205651.3208230

DO - 10.1145/3205651.3208230

M3 - Conference article in proceedings

AN - SCOPUS:85051521687

SP - 1902

EP - 1905

BT - Proceedings of the 2018 Genetic and Evolutionary Computation Conference Companion, GECCO 2018

PB - ACM

Y2 - 15 July 2018 through 19 July 2018

ER -

From fitness landscape analysis to designing evolutionary algorithms: The case study in automatic generation of function block applications

Abstrakti

Conference

Pääsy asiakirjaan

Muut tiedostot ja linkit

Sormenjälki

Siteeraa tätä