Fuel management optimization using genetic algorithms and code independence
Fuel management optimization is a hard problem for traditional optimization techniques. Loading pattern optimization is a large combinatorial problem without analytical derivative information. Therefore, methods designed for continuous functions, such as linear programming, do not always work well. Genetic algorithms (GAs) address these problems and, therefore, appear ideal for fuel management optimization. They do not require derivative information and work well with combinatorial. functions. The GAs are a stochastic method based on concepts from biological genetics. They take a group of candidate solutions, called the population, and use selection, crossover, and mutation operators to create the next generation of better solutions. The selection operator is a {open_quotes}survival-of-the-fittest{close_quotes} operation and chooses the solutions for the next generation. The crossover operator is analogous to biological mating, where children inherit a mixture of traits from their parents, and the mutation operator makes small random changes to the solutions.
- OSTI ID:
- 89304
- Report Number(s):
- CONF-941102-; ISSN 0003-018X; TRN: 95:004215-0381
- Journal Information:
- Transactions of the American Nuclear Society, Vol. 71; Conference: Winter meeting of the American Nuclear Society (ANS), Washington, DC (United States), 13-18 Nov 1994; Other Information: PBD: 1994
- Country of Publication:
- United States
- Language:
- English
Similar Records
A genetic algorithm solution to the unit commitment problem
The multi-niche crowding genetic algorithm: Analysis and applications