Unit commitment scheduling by using the neural network-weighted frequency bin blocks based next day load forecasting

Abstract

Unit commitment (UC) and load forecasting analyses are important because low-cost generation is one of the most significant points in power systems. Since UC solves for an optimum schedule of generating units based on load forecasting data, an accurate load forecasting is also very important in power system optimal planning and operation. Scheduling improperly the generating units due to under forecasting or over forecasting will result in the requirement of purchasing power from spot market or an unnecessary commitment of generating units. Therefore, the load forecasting is made as the first step to enhance the UC solution. Artificial Neural Network (ANN) and ANN model withWeighted Frequency Bin Blocks (WFBB) are used for the load forecasting. Then UC problem is solved by using the SA method and simulation results of these methods are compared. Comparing to these total costs show that load forecasting is important for unit commitment. Fourunit Tuncbilek thermal plant which is in Kutahya region in Turkey, is used for this analysis. The data used in the analysis is taken from Turkish Electric Power Company and Electricity Generation Company. All the analyses are implemented using MATLAB.