skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Genetic algorithm enhanced by machine learning in dynamic aperture optimization

Abstract

With the aid of machine learning techniques, the genetic algorithm has been enhanced and applied to the multi-objective optimization problem presented by the dynamic aperture of the National Synchrotron Light Source II (NSLS-II) Storage Ring. During the evolution processes employed by the genetic algorithm, the population is classified into different clusters in the search space. The clusters with top average fitness are given “elite” status. Intervention on the population is implemented by repopulating some potentially competitive candidates based on the experience learned from the accumulated data. These candidates replace randomly selected candidates among the original data pool. The average fitness of the population is therefore improved while diversity is not lost. Maintaining diversity ensures that the optimization is global rather than local. The quality of the population increases and produces more competitive descendants accelerating the evolution process significantly. When identifying the distribution of optimal candidates, they appear to be located in isolated islands within the search space. Some of these optimal candidates have been experimentally confirmed at the NSLS-II storage ring. Furthermore, the machine learning techniques that exploit the genetic algorithm can also be used in other population-based optimization problems such as particle swarm algorithm.

Authors:
 [1];  [1];  [1];  [1]
  1. Brookhaven National Lab. (BNL), Upton, NY (United States)
Publication Date:
Research Org.:
Brookhaven National Laboratory (BNL), Upton, NY (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22)
OSTI Identifier:
1439379
Alternate Identifier(s):
OSTI ID: 1439451
Report Number(s):
BNL-205720-2018-JAAM
Journal ID: ISSN 2469-9888; PRABCJ
Grant/Contract Number:
SC0012704
Resource Type:
Journal Article: Published Article
Journal Name:
Physical Review Accelerators and Beams
Additional Journal Information:
Journal Volume: 21; Journal Issue: 5; Journal ID: ISSN 2469-9888
Publisher:
American Physical Society (APS)
Country of Publication:
United States
Language:
English
Subject:
43 PARTICLE ACCELERATORS

Citation Formats

Li, Yongjun, Cheng, Weixing, Yu, Li Hua, and Rainer, Robert. Genetic algorithm enhanced by machine learning in dynamic aperture optimization. United States: N. p., 2018. Web. doi:10.1103/PhysRevAccelBeams.21.054601.
Li, Yongjun, Cheng, Weixing, Yu, Li Hua, & Rainer, Robert. Genetic algorithm enhanced by machine learning in dynamic aperture optimization. United States. doi:10.1103/PhysRevAccelBeams.21.054601.
Li, Yongjun, Cheng, Weixing, Yu, Li Hua, and Rainer, Robert. Tue . "Genetic algorithm enhanced by machine learning in dynamic aperture optimization". United States. doi:10.1103/PhysRevAccelBeams.21.054601.
@article{osti_1439379,
title = {Genetic algorithm enhanced by machine learning in dynamic aperture optimization},
author = {Li, Yongjun and Cheng, Weixing and Yu, Li Hua and Rainer, Robert},
abstractNote = {With the aid of machine learning techniques, the genetic algorithm has been enhanced and applied to the multi-objective optimization problem presented by the dynamic aperture of the National Synchrotron Light Source II (NSLS-II) Storage Ring. During the evolution processes employed by the genetic algorithm, the population is classified into different clusters in the search space. The clusters with top average fitness are given “elite” status. Intervention on the population is implemented by repopulating some potentially competitive candidates based on the experience learned from the accumulated data. These candidates replace randomly selected candidates among the original data pool. The average fitness of the population is therefore improved while diversity is not lost. Maintaining diversity ensures that the optimization is global rather than local. The quality of the population increases and produces more competitive descendants accelerating the evolution process significantly. When identifying the distribution of optimal candidates, they appear to be located in isolated islands within the search space. Some of these optimal candidates have been experimentally confirmed at the NSLS-II storage ring. Furthermore, the machine learning techniques that exploit the genetic algorithm can also be used in other population-based optimization problems such as particle swarm algorithm.},
doi = {10.1103/PhysRevAccelBeams.21.054601},
journal = {Physical Review Accelerators and Beams},
number = 5,
volume = 21,
place = {United States},
year = {Tue May 29 00:00:00 EDT 2018},
month = {Tue May 29 00:00:00 EDT 2018}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record at 10.1103/PhysRevAccelBeams.21.054601

Save / Share: