Skip to main content

Research Repository

Advanced Search

All Outputs (7)

Genetic algorithm-determined deep feedforward neural network architecture for predicting electricity consumption in real buildings (2020)
Journal Article

A genetic algorithm-determined deep feedforward neural network architecture (GA-DFNN) is proposed for both day-ahead hourly and week-ahead daily electricity consumption of a real-world campus building in the United Kingdom. Due to the comprehensive r... Read More about Genetic algorithm-determined deep feedforward neural network architecture for predicting electricity consumption in real buildings.

Comparative study of machine learning-based multi-objective prediction framework for multiple building energy loads (2020)
Journal Article

Buildings are one of the significant sources of energy consumption and greenhouse gas emission in urban areas all over the world. Lighting control and building integrated photovoltaic (BIPV) are two effective measures in reducing overall primary ener... Read More about Comparative study of machine learning-based multi-objective prediction framework for multiple building energy loads.

Feature extraction and genetic algorithm enhanced adaptive deep neural network for energy consumption prediction in buildings (2020)
Journal Article

Accurate forecast of energy consumption is essential in building energy management. Owing to the variation of outdoor weather condition among different seasons, year-round historical weather profile is needed to investigate its feature thoroughly. Da... Read More about Feature extraction and genetic algorithm enhanced adaptive deep neural network for energy consumption prediction in buildings.

A novel clustering-enhanced adaptive artificial neural network model for predicting day-ahead building cooling demand (2020)
Journal Article

To accurately predict hourly day-ahead building cooling demand, year-round historical weather profile needs to be evaluated. The daily weather profiles among different time periods result in various features of historical datasets. The different appr... Read More about A novel clustering-enhanced adaptive artificial neural network model for predicting day-ahead building cooling demand.