Energy Performance Modelling and Consumption Forecasting in Built Environments
R. L. Sharma1, P. K. Sharma2
1R.L.Sharma, SCE, Lovely Professional University, Phagwara, Punjab, India.
2P. K. Sharma, SCE, Lovely Professional University, Phagwara, Punjab, India.
Manuscript received on July 11, 2020. | Revised Manuscript received on July 22, 2020. | Manuscript published on July 30, 2020. | PP: 569-575 | Volume-9 Issue-2, July 2020. | Retrieval Number: F8350038620/2020©BEIESP | DOI: 10.35940/ijrte.F8350.079220
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: For all sector of the economy including the construction sector, energy consumption forecasting is critical for future planning. The building sector accounts for a staggering 30% of the world’s energy use and one-third of associated greenhouse gas (GHG) emissions worldwide. Modeling of building energy performance and consumption forecasting is significant for energy policy formulation, fixing targets and control energy usage to provide a long term energy security. Many energy models are accessible now, but the area is still under development and needs perfection on several counts. To select the most suitable and appropriate model for a specific purpose, it is often hard to evaluate the various models and their characteristics. This article provides a broad analysis of modeling methods, classification, and applications in constructed settings with an improved focus. A critical assessment of various models is also provided based on their composition, input-output relationships, strengths, and weaknesses to define study gaps and provide directions for future studies.
Keywords: Artificial neural network, Bottom-up, Energy consumption, Energy forecasting, Energy performance modeling, Machine learning Top-down etc.