Multi-area unit commitment with ramp-rate limits
- Illinois Inst. of Tech., Chicago, IL (United States). Dept. of Electrical and Computer Engineering
- Electric Power Research Inst., Palo Alto, CA (United States)
This paper reports that there are two tasks considered in power system generation scheduling. One is the unit commitment which determines the unit start up and shut down schedules in order to minimize the system fuel expenditure. The other is the economic dispatch which assigns the system load demand to the committed generating units for minimizing the power generation cost. The economic operation attracts a great deal of attention as a modest reduction in percentage fuel cost leads to a large saving in the system operation costs. Many studies for power system generation scheduling have successfully applied various mathematical algorithms such as Lagrangian relaxation, dynamic programming, and artificial intelligence techniques e.g., expert systems, artificial neural networks (ANN), etc. The AI techniques have incorporated the system practical operational policies in the mathematical techniques to improve system models considerably. The mechanism of ANN simulates the learning process of the human brain. One class of ANN learns the knowledge through examples, or training facts, composed by various inputs and their corresponding outputs. The extent of the intelligibility of ANN depends upon the diversity of the training facts. For an input which is not in the training facts, the trained ANN can estimate an output based on its previous knowledge about the problem.
- Sponsoring Organization:
- EPRI; Electric Power Research Inst., Palo Alto, CA (United States)
- OSTI ID:
- 7050489
- Report Number(s):
- CONF-920432--; CNN: RP8010-24
- Journal Information:
- Proceedings of the American Power Conference; (United States), Journal Name: Proceedings of the American Power Conference; (United States) Vol. 54:2; ISSN PAPWA; ISSN 0097-2126
- Country of Publication:
- United States
- Language:
- English
Similar Records
Feasibility of an expert system for planning commitment schedules of generating units
Application of neural networks in generation scheduling with fuzzy data
Related Subjects
240100* -- Power Systems-- (1990-)
240700 -- Power Transmission & Distribution-- Economic
Industrial & Business Aspects-- (1990-)
29 ENERGY PLANNING, POLICY, AND ECONOMY
296000 -- Energy Planning & Policy-- Electric Power
99 GENERAL AND MISCELLANEOUS
990200 -- Mathematics & Computers
ARTIFICIAL INTELLIGENCE
COST
ENERGY CONSUMPTION
LOAD MANAGEMENT
MANAGEMENT
MINIMIZATION
NEURAL NETWORKS
OPERATION
OPTIMIZATION
PARALLEL PROCESSING
PLANNING
POWER GENERATION
POWER SYSTEMS
PROGRAMMING
TECHNOLOGY ASSESSMENT