Application of an improved SVR based Bat algorithm for short-term price forecasting in the Iranian Pay-as-Bid electricity market

With the emergence of competitive markets in the world over the past two decades, the price of electricity has become a key factor in this environment. Using an accurate model for short-term price forecasting in the competitive environment of electric industry helps the market participants in investing and planning for short-term contracts and getting the maximum possible profit. In markets with Pay-as-Bid mechanism, such as Iran, the accurate forecasting of this factor is of great importance. Therefore, in this paper, the proposed model is applied on the price data of Iranian power market in 2013. In this model, first the input data is clustered by the fuzzy c-means technique. This makes it possible to separate the data based on the type of load or day of the year. Then, proper training data are used by the improved SVR network for short-term price forecasting. In this paper, the new Bat algorithm is used for optimizing the parameters of SVR network. Bat algorithm is a recent addition to the bio-inspired algorithms, considered as a new metaheuristic algorithm based on Bat behavior. Also, the results show the high accuracy of the proposed model.