Maximizing long-term gas industry profits in two minutes in Lotus using neural network methods
- Energy Analysis and Forecasting Div., Energy Information Administration, Washington, DC (US)
Generalized methods, commonly used in neural network research, have made it possible for the Energy Information Adminstration (EIA) to solve a gas industry optimization problem on a personal computer that would previously have required a mainframe computer because of the run time required. The resulting model was used to produce EIA's official energy forecasts published in 1988. It is shown how backpropagation - one of the basic methods used to adapt artificial neural networks - can be used by modelers with no special training in neurocomputing. Earlier applications of backpropagation to modeling and to EIA problems are reviewed that antedate the practical applications of backpropagation to modeling and to EIA problems are reviewed that antedate the practical applications to neural networks. The relations between backpropagation, the current EIA model, and economic issues related to modeling and the gas industry are discussed. Among these issues are optimization subject to constraints, and competition and efficiency in gas supply. It is also shown how more recent formulations of backpropagation are a special case of the formulation given here, further work discussing the relevance of the original formulation to the mammalian brain is cited.
- OSTI ID:
- 5347257
- Journal Information:
- IEEE (Institute of Electrical and Electronics Engineers) Transactions on Systems, Man, and Cybernetics; (USA), Journal Name: IEEE (Institute of Electrical and Electronics Engineers) Transactions on Systems, Man, and Cybernetics; (USA) Vol. 19:2; ISSN 0018-9472; ISSN ISYMA
- Country of Publication:
- United States
- Language:
- English
Similar Records
Modeling design and control problems involving neural network surrogates
A robust and efficient training algorithm for feedforward neural networks
Related Subjects
032000 -- Natural Gas-- Transport
Handling
& Storage
99 GENERAL AND MISCELLANEOUS
990200* -- Mathematics & Computers
990300 -- Information Handling
ANIMAL CELLS
ARRAY PROCESSORS
COMPUTER NETWORKS
COMPUTERIZED SIMULATION
COMPUTERS
DIGITAL COMPUTERS
EFFICIENCY
ENERGY SUPPLIES
INDUSTRY
INFORMATION SYSTEMS
MICROCOMPUTERS
NATURAL GAS INDUSTRY
NERVE CELLS
OPTIMIZATION
PARALLEL PROCESSING
PERSONAL COMPUTERS
PROGRAMMING
RESEARCH PROGRAMS
SIMULATION
SOMATIC CELLS
USES