A new prediction model based on multi-block forecast engine in smart grid

By changing the electricity market in smart grids, the consumers will be able to react to the electricity price. As close correlation of price and load, the density of this reaction can affect to demand curve and shift it in market. For this purpose, an accurate prediction model is demanded for optimal operation as well as planning in power system. For this purpose, we proposed a new hybrid forecast model based on dual-tree complex wavelet transform and multi-stage forecast engine (MSFE). In this model at first, the signal entered to proposed wavelet transform and then, it is filtered by new feature selection. After that, the signal predicted by proposed MSFE in three steps. An intelligent algorithm is applied to the forecast engine to increase its ability and prediction accuracy during the process. Finally, the improved fusion algorithm gather the outputs of MSFE. Effectiveness of the proposed method has been implemented over Australia's and New England electricity market data. Obtained results compared with several prediction models which demonstrate the validity of proposed model.