Short-term price forecasting under high penetration of wind generation units in smart grid environment

With the emergence of smart grids, customers have become capable of reacting to the fluctuations in electricity price. Therefore, electricity price is a key element in optimum demand side management (DSM) in this environment. Accurate short-term forecasting of electricity price is of great importance for the market participants. However, due to the nonlinear, stochastic and time-variant nature of electricity price, accurate forecasting is extremely difficult. On the other hand, distributed generation resources, especially the wind, have widely penetrated these networks and the real time balancing of the demand and generation of power systems has become extremely complicated due to the variable nature of wind generation. In this paper, considering high penetration levels of wind generation, the short-term forecasting of electricity price is investigated based on the Nord Pool power market data. The main idea is based on presenting a hybrid model which consists of a multi-layer perceptron neural network and adaptive neuro fuzzy inference system (ANFIS) which uses a data clustering technique based on imperialist competitive algorithm (ICA). The results show the high accuracy of this model in short term forecasting of electricity price.