Unit Commitment by Considering the Uncertainty of Renewable Energy Sources

The main idea of Unit Commitment (UC) is to decide the optimum start-up / shut-down cycle of all units throughout the operating period with a view to minimize the overall costs with respect to various generator and system constraints. A steady rise in fuel charges and a rapid fossil fuels depletion have opened the way for the use of renewable sources for power generation. Renewable energy sources are therefore being used and installed with greater eagerness in power systems today. With the deployment of renewable sources, the UC issue becomes more complicated ,provided obvious differences in behavioral and technical restrictions on traditional thermal generation systems that need to be resolved as renewable generation will be integrated part of the electrical network. This thesis aims to solve the problem of UC with the consolidation of wind power sources into the network. This study covered the renewable energy uncertainty by forecasting day ahead wind power and studying more than one scenario for the wind behavior. Artificial Neural Network (ANN) method is used for forecasting short-term wind and then generating extra possible scenarios for the wind power values. Two optimizations method are used for UC problem: Genetic Algorithm (GA) and Dynamic Programing (DP). The suggested approach is tested by applying it to the standard IEEE 6 and 30 bus test systems. The results show that DP method outperforms GA method in term of minimizing the total production costs. This study may help the decision-makers particularly in small power generation firms in planning day-ahead performance of the electrical networks. Keywords: Artificial Neural Network, Dynamic Programing, Economic Dispatch, Genetic Algorithm, Unit Commitment and Wind Uncertainty.