A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
A Comparative Analysis of Regression Algorithms for Energy Estimation in Residential Buildings
Abstract Building energy management using statistical framework to study effects of various input variables is already in place. A machine learning solution to derive the insights on the effect of the input variables (relative compactness, surface area, wall area, roof area, overall height, orientation, glazing area, glazing area distribution) on two output variables, namely heating load (HL) and cooling load (CL), of residential buildings is provided in this paper. A comprehensively deep investigation is made by applying various algorithms to find the effect of each input variable on each of the two output variables. A comparative analysis using regression with various algorithms is provided for estimating CL and HL of the building. A dataset containing details of 768 diverse residential buildings is used to predict the CL and HL with respect to input variables. The model developed provides feasibility to train the algorithm online with real time data and predictions with trained data shows the model is accurate with RMSE of 0.4664 for HL & 1.2466 for CL. The model can be used to perform environment analysis to simulate building performance in terms of cooling and heating loads at the earliest stages of building design.
A Comparative Analysis of Regression Algorithms for Energy Estimation in Residential Buildings
Abstract Building energy management using statistical framework to study effects of various input variables is already in place. A machine learning solution to derive the insights on the effect of the input variables (relative compactness, surface area, wall area, roof area, overall height, orientation, glazing area, glazing area distribution) on two output variables, namely heating load (HL) and cooling load (CL), of residential buildings is provided in this paper. A comprehensively deep investigation is made by applying various algorithms to find the effect of each input variable on each of the two output variables. A comparative analysis using regression with various algorithms is provided for estimating CL and HL of the building. A dataset containing details of 768 diverse residential buildings is used to predict the CL and HL with respect to input variables. The model developed provides feasibility to train the algorithm online with real time data and predictions with trained data shows the model is accurate with RMSE of 0.4664 for HL & 1.2466 for CL. The model can be used to perform environment analysis to simulate building performance in terms of cooling and heating loads at the earliest stages of building design.
A Comparative Analysis of Regression Algorithms for Energy Estimation in Residential Buildings
Venkat Ramana Reddy, A. (author) / Sudheer Kumar, M. (author)
2019-06-28
12 pages
Article/Chapter (Book)
Electronic Resource
English
| British Library Online Contents | 2016