A non-linear parallel optimization tool (nlparopt) for solving spacecraft trajectory problems

Alexander Ghosh, Ryne Beeson, Laura Richardson, Donald Ellison, David Carroll, Victoria Coverstone

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Modern spacecraft trajectory mission planning regularly involves Non-Linear Programming (NLP) problem formulations. As the problems being posed become more complex, scientists have adopted high performance computing methods such as parallel programming to significantly speed up the time-to-solution. Unfortunately, the NLP solvers at the core of many of the modern trajectory optimization methods are becoming a serial bottleneck, and the single largest point of solution slowdown. CU Aerospace in partnership with the University of Illinois at Urbana-Champaign (UIUC) has developed a novel, ground-up redesign of an NLP solver that takes advantage of high performance parallel computing called the Non-Linear PARallel Optimization Tool (NLPAROPT). NLPAROPT uses the Message Passing Interface (MPI) as well as Parallel Basic Linear Algebra (PBLAS) techniques to carry out traditional NLP solution methods in parallel. Preliminary tests have shown NLPAROPT's ability to reduce the runtime by orders of magnitude when compared to its serial counterpart. Applications to simple problems as well as a multiple shooting trajectory optimization test problem are demonstrated. There remains significant additional avenues for parallelism and improved robustness that should proffer further gains.

Original languageEnglish (US)
Title of host publicationAstrodynamics 2015
EditorsJames D. Turner, Geoff G. Wawrzyniak, William Todd Cerven, Manoranjan Majji
PublisherUnivelt Inc.
Pages3465-3481
Number of pages17
ISBN (Print)9780877036296
StatePublished - Jan 1 2016
EventAAS/AIAA Astrodynamics Specialist Conference, ASC 2015 - Vail, United States
Duration: Aug 9 2015Aug 13 2015

Publication series

NameAdvances in the Astronautical Sciences
Volume156
ISSN (Print)0065-3438

Other

OtherAAS/AIAA Astrodynamics Specialist Conference, ASC 2015
CountryUnited States
CityVail
Period8/9/158/13/15

ASJC Scopus subject areas

  • Aerospace Engineering
  • Space and Planetary Science

Fingerprint Dive into the research topics of 'A non-linear parallel optimization tool (nlparopt) for solving spacecraft trajectory problems'. Together they form a unique fingerprint.

  • Cite this

    Ghosh, A., Beeson, R., Richardson, L., Ellison, D., Carroll, D., & Coverstone, V. (2016). A non-linear parallel optimization tool (nlparopt) for solving spacecraft trajectory problems. In J. D. Turner, G. G. Wawrzyniak, W. T. Cerven, & M. Majji (Eds.), Astrodynamics 2015 (pp. 3465-3481). (Advances in the Astronautical Sciences; Vol. 156). Univelt Inc..