Abstract
Existing differential evolution (DE) algorithms often face two challenges. The first is that the optimization performance is significantly affected by the ad hoc configurations of operators and parameters for different problems. The second is the long runtime for real-world problems whose fitness evaluations are often expensive. Aiming at solving these two problems, this paper develops a novel double-layered heterogeneous DE algorithm and realizes it in cloud computing distributed environment. In the first layer, different populations with various parameters and/or operators run concurrently and adaptively migrate to deliver robust solutions by making the best use of performance differences among multiple populations. In the second layer, a set of cloud virtual machines run in parallel to evaluate fitness of corresponding populations, reducing computational costs as offered by cloud. Experimental results on a set of benchmark problems with different search requirements and a case study with expensive design evaluations have shown that the proposed algorithm offers generally improved performance and reduced computational time, compared with not only conventional and a number of state-of-the-art DE variants, but also a number of other distributed DE and high-performing evolutionary algorithms. The speedup is significant especially on expensive problems, offering high potential in a broad range of real-world applications.
| Language | English |
|---|---|
| Article number | 7530859 |
| Pages | 704-716 |
| Number of pages | 13 |
| Journal | IEEE Transactions on Parallel and Distributed Systems |
| Volume | 28 |
| Issue number | 3 |
| Early online date | 3 Aug 2016 |
| DOIs | |
| Publication status | Published - 1 Mar 2017 |
Fingerprint
Keywords
- adaptive migration strategy
- cloud computing
- differential evolution
- evolutionary algorithm
- heterogeneous parallelism
Cite this
}
Cloudde : a heterogeneous differential evolution algorithm and its distributed cloud version. / Zhan, Zhi-Hui; Liu, Xiao-Fang; Zhang, Huaxiang; Yu, Zhengtao; Weng, Jian; Li, Yun; Gu, Tianlong; Zhang, Jun.
In: IEEE Transactions on Parallel and Distributed Systems, Vol. 28, No. 3, 7530859, 01.03.2017, p. 704-716.Research output: Contribution to journal › Article
TY - JOUR
T1 - Cloudde
T2 - IEEE Transactions on Parallel and Distributed Systems
AU - Zhan, Zhi-Hui
AU - Liu, Xiao-Fang
AU - Zhang, Huaxiang
AU - Yu, Zhengtao
AU - Weng, Jian
AU - Li, Yun
AU - Gu, Tianlong
AU - Zhang, Jun
PY - 2017/3/1
Y1 - 2017/3/1
N2 - Existing differential evolution (DE) algorithms often face two challenges. The first is that the optimization performance is significantly affected by the ad hoc configurations of operators and parameters for different problems. The second is the long runtime for real-world problems whose fitness evaluations are often expensive. Aiming at solving these two problems, this paper develops a novel double-layered heterogeneous DE algorithm and realizes it in cloud computing distributed environment. In the first layer, different populations with various parameters and/or operators run concurrently and adaptively migrate to deliver robust solutions by making the best use of performance differences among multiple populations. In the second layer, a set of cloud virtual machines run in parallel to evaluate fitness of corresponding populations, reducing computational costs as offered by cloud. Experimental results on a set of benchmark problems with different search requirements and a case study with expensive design evaluations have shown that the proposed algorithm offers generally improved performance and reduced computational time, compared with not only conventional and a number of state-of-the-art DE variants, but also a number of other distributed DE and high-performing evolutionary algorithms. The speedup is significant especially on expensive problems, offering high potential in a broad range of real-world applications.
AB - Existing differential evolution (DE) algorithms often face two challenges. The first is that the optimization performance is significantly affected by the ad hoc configurations of operators and parameters for different problems. The second is the long runtime for real-world problems whose fitness evaluations are often expensive. Aiming at solving these two problems, this paper develops a novel double-layered heterogeneous DE algorithm and realizes it in cloud computing distributed environment. In the first layer, different populations with various parameters and/or operators run concurrently and adaptively migrate to deliver robust solutions by making the best use of performance differences among multiple populations. In the second layer, a set of cloud virtual machines run in parallel to evaluate fitness of corresponding populations, reducing computational costs as offered by cloud. Experimental results on a set of benchmark problems with different search requirements and a case study with expensive design evaluations have shown that the proposed algorithm offers generally improved performance and reduced computational time, compared with not only conventional and a number of state-of-the-art DE variants, but also a number of other distributed DE and high-performing evolutionary algorithms. The speedup is significant especially on expensive problems, offering high potential in a broad range of real-world applications.
KW - adaptive migration strategy
KW - cloud computing
KW - differential evolution
KW - evolutionary algorithm
KW - heterogeneous parallelism
UR - http://www.scopus.com/inward/record.url?scp=85013053105&partnerID=8YFLogxK
UR - https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=71
U2 - 10.1109/TPDS.2016.2597826
DO - 10.1109/TPDS.2016.2597826
M3 - Article
VL - 28
SP - 704
EP - 716
JO - IEEE Transactions on Parallel and Distributed Systems
JF - IEEE Transactions on Parallel and Distributed Systems
SN - 1045-9219
IS - 3
M1 - 7530859
ER -