Litcius/Paper detail

Developing machine-learning meta-models for high-rise residential district cooling in hot and humid climate

Biao Jia, Danlin Hou, Athar Kamal, Ibrahim Hassan, Liangzhu Wang

2021Journal of Building Performance Simulation21 citationsDOI

Abstract

Cooling accounts for a significant amount of energy consumption in hot and humid climates, and district cooling is an energy-efficient solution. During its planning stage, an accurate and fast prediction of district cooling loads is required to assist decision-making. This study investigated the development of machine-learning-based meta-models to predict the cooling load of high-rise residential buildings at a district scale. Four machine-learning models have been evaluated, including Multiple Linear Regression, Support Vector Regression, Artificial Neural Networks (ANN), and eXtreme Gradient Boosting. The meta-model development starts with the sensitivity analysis to determine the critical parameters as independent variables. The results show that the ANN model with 30 neurons of the hidden layer, trained by eight epochs with 20% sample data, manifested superior performance when predicting monthly energy use intensity for the testing cases. A minimum of eight independent variables for the meta-model was also shown to be acceptable.

Topics & Concepts

Artificial neural networkCooling loadGradient boostingSupport vector machineMachine learningMetamodelingLinear regressionArtificial intelligenceComputer scienceRegression analysisEnergy consumptionExtreme learning machineEngineeringRandom forestMechanical engineeringAir conditioningElectrical engineeringProgramming languageBuilding Energy and Comfort OptimizationWind and Air Flow StudiesUrban Heat Island Mitigation
Developing machine-learning meta-models for high-rise residential district cooling in hot and humid climate | Litcius