Intelligent Environment Monitoring and Control

Abstract

Heating, Ventilation, and Air Conditioning (HVAC) systems play a vital role in building energy management by controlling the indoor environment and ensuring the occupant’s comfort. These systems are responsible for regulating the temperature and air quality inside buildings, thereby creating a comfortable and healthy indoor environment for occupants. However, the energy consumption of HVACs contributes significantly towards overall energy usage of a building and carbon footprint creating a challenge for building energy management. To address this challenge, this research proposes the development of a predictive model for HVAC temperature forecasting using Machine Learning (ML) algorithms to optimize energy efficiency while maintaining thermal comfort in buildings. The study focuses on comparing the performance of Transformer Neural Networks and CNN-LSTM, a seq2seq model combining Convolutional Neural Networks (CNN) and Long-Short Term Memory (LSTM) on multiple forecasting horizons. Both models are validated using data obtained from multiple devices which are deployed in a room verified by feedback survey forms filled by occupants. The transformer model outperformed, achieving an R2 score of 0.936 at a 1 minute forecasting horizon, surpassing the performance of CNN-LSTM model at all tested forecasting horizons. The transformer model yielded significant energy savings thereby reducing energy consumption by almost 50 percent compared to the nonAI conventional methods, particularly at forecasting horizons of 1 minute and 60 minutes, while the occupant survey also favored a 60-minute forecasting horizon indicating that the proposed model can effectively balance energy efficiency with occupant comfort. The performance of transformer model particularly with a 60-minute forecasting horizon underscores its potential to optimize energy efficiency while ensuring thermal comfort in building energy management systems.