Back to publications

A case study on understanding energy consumption through prediction and visualisation (VIMOEN)

Baca-Ruiz, LuisĀ G. and Pegalajar, M.C. and Molina-Solana, Miguel and Guo, Yike
Engineering Applications of Artificial Intelligence , under review, pp. (SUBMITTED)

Abstract:

Energy efficiency has emerged as an overarching concern due to the high pollution and cost associated with operating heating ventilation and air-conditioning systems in buildings. Thus, energy monitoring has become one of the most important research topics with global impacts. This, along with energy forecasting represent a very decisive task for energy efficiency. The goal of this study is divided into two parts. First, to provide a methodology to predict the energy usage every hour with the goal of deciding which Machine Learning is the best approach: Trees, Support Vector Machine or Neural Networks. Since the UGR lacks a tool to properly monitoring those data, then, the second aim is to propose an intelligent system to visualize and to use those models in order to predict energy consumption in real time. For this end, we will design VIMOEN (VIsual MOnitoring of ENergy), a web-based application (using Mapbox) whose objective is to provide not only visual information about the energy consumption of a set of geographically-distributed buildings but also expected expenditures in the near future. The system has been designed to be easy-to-use and intuitive for any non-expert users. Thus, VIMOEN is intended to make easier the monitoring of a large amount of buildings and to anticipate changes in consumption. The system has been validated on data coming from buildings of University of Granada.

Links:

DOI:
PDF:

Bibtex:

@article{Baca2019a,
  author = {Baca-Ruiz, Luis~G. and Pegalajar, M.C. and Molina-Solana, Miguel and Guo, Yike},
  title = {A case study on understanding energy consumption through prediction and visualisation (VIMOEN)},
  journal = {Engineering Applications of Artificial Intelligence},
  year = {SUBMITTED},
  volume = {under review},
  doi = {},
  comment = {},
  timestamp = {22}
}