In this study, hourly forecasting of long term electric energy demand is proposed using a novel modeling approach. Previous works regarding energy demand forecasting either treated the problem of long term prediction over yearly averages, or considered hourly prediction using a very short term time lag, such as a few hours. The proposed method produces predictions with hourly accuracy; however the proposed time lag is "years", making the model suitable for long term prediction. The model is constructed and verified using 4-year-long real-life hourly load data obtained from Turkish Electric Power Company. The method consists of a nested combination of three sub-sections for modeling. The first section is the coarse level for modeling yearly average loads. The second section refines this structure by modeling weekly residual load variations within a year. The final section reaches to the hourly variations within a week, using a novel 2-D mathematical representation at this resolution. Consequently, the combination yields a unified model for short-, medium-, and long-term hourly load forecasting. © 2009 IEEE.