Application of artificial neural networks for virtualenergy assessment

• Amir Mortazavigazar ^{[1] [2]} ; Nourehan Wahba ^[1] ; Paul Newsham ^{[1] [3]} ; Maharti Triharta ^[1] ; Pufan Zheng ^[1] ; Tracy Chen ^[1] ; Behzad Rismanchi ^[1]
  1. [1] University of Melbourne

     University of Melbourne

     Australia

     
  2. [2] Virginia–Maryland College of Veterinary Medicine

     Virginia–Maryland College of Veterinary Medicine

     Estados Unidos

     
  3. [3] Faculty of Business, UQ Business School, Economics & Law, University of Queensland,Brisbane, QLD 4072, Australia

  Mostrar afiliaciones +
• Localización: Artificial intelligence in the energy industry / Ana Belén Gil González (ed. lit.), 2022, ISBN 978-3-0365-4605-6, págs. 97-114
• Idioma: inglés
• Enlaces
  • Texto Completo Libro (pdf)
• Resumen

  • A Virtual energy assessment (VEA) refers to the assessment of the energy flow in abuilding without physical data collection. It has been occasionally conducted before the COVID-19pandemic to residential and commercial buildings. However, there is no established frameworkmethod for conducting this type of energy assessment. The COVID-19 pandemic has catalysedthe implementation of remote energy assessments and remote facility management. In this paper,a novel framework for VEA is developed and tested on case study buildings at the University ofMelbourne. The proposed method is a hybrid of top-down and bottom-up approaches: gatheringthe general information of the building and the historical data, in addition to investigating andmodelling the electrical consumption with artificial neural network (ANN) with a projection of thefuture consumption. Through sensitivity analysis, the outdoor temperature was found to be the mostsensitive (influential) parameter to electrical consumption. The lockdown of the buildings providedinvaluable opportunities to assess electrical baseload with zero occupancies and usage of the building.Furthermore, comparison of the baseload with the consumption projection through ANN modellingaccurately quantifies the energy consumption attributed to occupation and operational use, referredto as ‘operational energy’ in this paper. Differentiation and quantification of the baseload andoperational energy may aid in energy conservation measures that specifically target to minimisethese two distinct energy consumptions