An accurate analysis of the parameters aecting consumption and price uctuations of electricity in the Iranian market in summer

In this paper, a novel method is proposed to predict the cost of short-term hourly electrical energy based on combined neural networks. In this method, the in uential parameters that play a key role in the accuracy of these systems are identied and the most prominent ones are selected. In the proposed method, initially, using the Self-Organizing Map (SOM) network, similar days are placed in close clusters. In the next stage, due to their dierences in the scope and nature of their changes, the temperature parameters and prices related to similar days are trained separately in the two Multilayer Perceptron (MLP) neural networks. Finally, the two networks are merged with another MLP network. In the proposed hybrid method, an evolutionary search method is used to provide an appropriate initial weight for neural network training. Given the price data changes, the price amidst the previous hour has a signicant eect on the prediction of the current state. In this vein, in the proposed method, the predicted data in the previous hour is considered as one of the inputs of the next stage. The proposed method was assessed on the datasets of Iran in the summer. This information pertains to the 2011-2016 period.