Advanced Local Predictors Based Short-Term Load Forecasting for Unit Commitment Scheduling

Theunit commitment (UC) problem is the problem of deciding which electricity generation units should be scheduled economically in a power system in order to meet therequirements of load and spinning reserve.In this paper, the UC problem is solved for an optimum schedule of generating units based on the load data forecasted using advanced local predictors. These local predictors are local support vector regression (LSVR) and local radial basis function (LRBF) Low-cost generation is important in power system analysis. Under forecasting or over forecasting will result in the requirement of purchasing power from spot market or an unnecessary commitment of generating units. Accurate load forecasting is the first step to enhance the UC solution. Total costs calculated for the actual load and two different forecasting load data are compared. A 10-units test system is used for this analysis. The results show the importance of accurate load forecasting to UC.