Stochastic Unit Commitment with Transmission Constraint Using Self-Organized Maps (SOM) for Scenarios Reduction

Wind power generation capacity has been increased following the targets set by many governments. Variability and uncertainty are inherent characteristics of wind power generation resulting in technical and economical challenges for power system operators. The unit commitment (UC) problem determines the power generated by each generator in order to minimize power system operating costs. In this paper, we propose a wind speed scenarios reduction using Self organizing Map (SOM) in order to solve the unit commitment problem using a reasonable number of wind speed scenarios that take into account the uncertainties related to the stochastic variable (wind speed). The results obtained show that the proposed methodology is able to characterize the uncertainty related to power injected from wind farms. Furthermore, the simulations results show that for the system under study, the scenarios reduction technique decrease the computational burden required to solve a SUC problem.