We consider the modeling and forecasting of daily electricity spot prices on the Nord Pool  Elspot power market. A method that can handle seasonal and non-seasonal persistence is proposed in the form of a generalized exponential (GEXP) model for the power prices. As the presence of spikes can distort estimation of the dynamic structure of the series, we consider an iterative estimation strategy which, conditional on a set of parameter estimates, clears the spikes using a data cleaning algorithm, and re-estimates the parameters using the cleaned data so as to robustify the estimates. Conditional on the estimated model, the best linear predictor is constructed.