Visualization for Hyper-Heuristics: Back-End Processing
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Modern society is faced with increasingly complex problems, many of which can be formulated as generate-and-test optimization problems. Yet, general-purpose optimization algorithms may sometimes require too much computational time. In these instances, hyperheuristics may be used. Hyper-heuristics automate the design of algorithms to create a custom algorithm for a particular scenario, finding the solution significantly faster than its predecessor. However, it may be difficult to understand exactly how a design was derived and why it should be trusted. This project aims to address these issues by creating an easy-to-use graphical user interface (GUI) for hyper-heuristics and an easy-to-understand scientific visualization for the produced solutions. To support the development of this GUI, my portion of the research involved developing algorithms that would allow for parsing of the data produced by the hyper-heuristics. This data would then be sent to the front-end, where it would be displayed to the end user.
- Research Organization:
- Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA)
- DOE Contract Number:
- AC04-94AL85000
- OSTI ID:
- 1177600
- Report Number(s):
- SAND--2015-2327R; 579487
- Country of Publication:
- United States
- Language:
- English
Similar Records
A Comparison of Genetic Programming Variants for Hyper-Heuristics
Hyper-Heuristics to Automatically Target Code to Computer Architectures