Regression analysis for energy demand projection: An application to TIMES-Basilicata and TIMES-Italy energy models.

A reliable energy supply is fundamental to ensure energy security and support the mitigation of climate change by promoting the use of renewable sources and reducing carbon emissions. Energy system analysis provides a sound methodology to assess energy needs, allowing to investigate the energy system behavior and to individuate the optimal energy-technology configurations for the achievement of strategic energy and environmental policy targets. In this framework, the estimation of future trends of exogenous variables such as energy demand has a fundamental importance to obtain reliable and effective solutions, contributing remarkably to the accuracy of models' input data. This study illustrates an application of regression analysis to predict energy demand trends in end use sectors. The proposed procedure is applied to characterize statistically the relationships between population and gross domestic product (independent variables) and energy demands of Residential, Transport and Commercial in order to determine the energy demand trends over a long-term horizon. The effectiveness of linear and nonlinear regression models for energy demand forecasting has been validated by classical statistical tests. Energy demand projections have been tested as input data of the bottom-up TIMES model in two applications (the TIMES-Basilicata and TIMES-Italy models) confirming the validity of the forecasting approach. • Energy systems modeling requires a detailed description of energy demand development (85). • Relationships among energy demand, population and economic variables are emphasized (83). • Regression analysis is applied to end-use demand forecasts as input for TIMES models (84). • The efficacy of regression analysis is validated by classical statistical tests (79). • Energy trends are tested with two energy models: TIMES-Basilicata and TIMES-Italy (81). [ABSTRACT FROM AUTHOR]