Application of artificial neural networks to stochastic electric power production, production costing and operations planning
- Temple Univ., Philadelphia, PA (United States). Dept. of Electrical Engineering
The paper presents a new method for stochastic electric power system production costing and operations planning. In the method the authors formulate a stochastic Hopfield/Chua-Kennedy neural network in which unit availability and system load demand are random parameters with known statistics. Unit outages are modeled as Markov processes. The unit commitment-status variables are (0, 1) integers while the unit dispatch/loading levels take on decimal values. The unit commitment-status variables together with the unit dispatch/loading levels are random processes satisfying appropriately derived deterministic equivalent differential equations. A review of the techniques that are currently employed by utilities for production costing and operations planning with particular emphasis on those for the stochastic problem is also presented. Among the shortcomings of these techniques are their inability to commit and dispatch units simultaneously, and to account for the effect of forced outages on unit availability in a chronological manner. The authors` method addresses these shortcomings.
- OSTI ID:
- 103718
- Report Number(s):
- CONF-950414--
- Country of Publication:
- United States
- Language:
- English
Similar Records
Two-stage minimax stochastic unit commitment
Two‐stage minimax stochastic unit commitment