Abstract
Energy demand forecasting is practiced in several time frames; different explanatory variables are used in each case to serve different decision support mandates. For example, in the short, daily, term building level, forecasting may serve as a performance baseline. On the other end, we have long-term, policy-oriented forecasting exercises. TIMES (an acronym for The Integrated Markal Efom System) allows us to model supply and anticipated technology shifts over a long-term horizon, often extending as far away in time as 2100. Between these two time frames, we also have a mid-term forecasting time frame, that of a few years ahead. Investigations here are aimed at policy support, although in a more mid-term horizon, we address issues such as investment planning and pricing. In this paper, we develop and evaluate statistical and neural network approaches for this mid-term forecasting of final energy and electricity for the residential sector in six EU countries (Germany, the Netherlands, Sweden, Spain, Portugal and Greece). Various possible approaches to model the explanatory variables used are presented, discussed, and assessed as to their suitability. Our end goal extends beyond model accuracy; we also include interpretability and counterfactual concepts and analysis, aiming at the development of a modelling approach that can provide decision support for strategies aimed at influencing energy demand.
Highlights
Mid-term energy demand is of known importance to policymakers as well as the full spectrum of energy-related businesses
In Japan [9], the price elasticity of electricity demand was found to be significant, a conclusion opposing previous approaches in the country, such as that of the Japan Business Federation [8] in 2003, which claimed that price elasticity of energy demand is low, and a carbon tax cannot suppress carbon emissions [10]
This paper provides data and modelling insights into final energy and electricity consumption in the residential sector, with the main and practical end purpose to support mid-term energy planning
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. In order to properly model the demand-side of the energy market, several approaches have been proposed as to the selection of the independent and explanatory variables or features, as called in the AI literature. Suganthi L. et al [13] provides an exhaustive review of econometric and machine learning models. For the latter, they suggest that GNP, energy price, gross output, technological development, and energy efficiency are the most prominent. They suggest that GNP, energy price, gross output, technological development, and energy efficiency are the most prominent They suggest that a mixed approach, building on both statistics (ARIMA based models) and neural networks, can provide for increased accuracy.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
