Data driven model improved by multi-objective optimisation for prediction of building energy loads

TL;DR: A generalized framework based on existing literature for different urban energy modeling methods is proposed to assist urban planners and energy policymakers when choosing appropriate methods to develop and implement in-depth sustainable building energy planning and analysis projects based on limited available resources.

TL;DR: An energy performance prediction model for non-domestic buildings supported by machine learning which is optimised using advanced evolutionary algorithms provide a robust and reliable tool for building analysts enabling them to meaningfully explore the expanding solution space.

TL;DR: Investigation of the district heating load prediction dataset from Shanghai, China found that model performance is primarily influenced by the weather forecasting data, and SVR, XGBoost and Long Short Term Memory neural network have similar performance.

TL;DR: It is shown that it is possible to develop a high performing ML model for building energy use prediction at the design stage and Gradient Boosting (GB) outperformed the other models with an accuracy of 0.67 for predicting building energy performance.

TL;DR: In this paper, the authors present a pilot study that attempts an initial probabilistic probe into the performance gap between predicted (computed) energy performance of buildings and actual measured energy use once buildings are operational.

TL;DR: In this article, the authors compared the performance of feed-forward back-propagation artificial neural network (ANN) with random forest (RF), an ensemble-based method gaining popularity in prediction, for predicting the hourly HVAC energy consumption of a hotel in Madrid, Spain.

TL;DR: In this article, support vector machines (SVM) were used to forecast building energy consumption in the tropical region, and the performance of SVM with respect to two parameters, C and ǫ, was explored using stepwise searching method based on radial-basis function (RBF) kernel.

TL;DR: In this article, a statistical machine learning framework was developed to study the effect of eight input variables (relative compactness, surface area, wall area, roof area, overall height, orientation, glazing area, etc.) on two output variables, namely heating load (HL) and cooling load (CL), of residential buildings.