Heating, Ventilation, and Air Conditioning (HVAC) systems represent a significant portion of global energy use, yet they are often operated without optimized control strategies. This study explores the application of deep learning to accurately model heating system behavior as a foundation for predictive control and energy-efficient HVAC operation. Experimental data were collected under controlled laboratory conditions, and 288 unique hyperparameter configurations were developed. Each configuration was tested three times, resulting in a total of 864 artificial neural network models. Five key hyperparameters were varied systematically: number of epochs, network size, network shape, learning rate, and optimizer. The best-performing model achieved a mean squared error of 0.469 and featured 17 hidden layers, a left-triangle architecture trained for 500 epochs with a learning rate of 5 × 10−5, and Adam as the optimizer. The results highlighted the importance of hyperparameter tuning in improving model accuracy. Future research should extend the analysis to incorporate cooling operation and real-world building operation data for broader applicability.
Heating systems in a building’s mechanical infrastructure account for a significant share of global building energy consumption, underscoring the need for improved efficiency. This study evaluates 31 predictive models—including neural networks, gradient boosting (XGBoost), bagging, and multiple linear regression (MLR) as a baseline—to estimate heating-coil performance. Experiments were conducted on a water-based air-handling unit (AHU), and the dataset was cleaned to eliminate illogical and missing values before training and validation. Among the evaluated models, neural networks, gradient boosting, and bagging demonstrated superior accuracy across various error metrics. Bagging offered the best balance between outlier robustness and pattern recognition, while neural networks showed strong capability in capturing complex relationships. An input-importance analysis further identified key variables influencing model predictions. Future work should focus on refining these modeling techniques and expanding their application to other HVAC components to improve adaptability and efficiency.
Buildings account for over 40% of global carbon dioxide (CO2) emissions, with supply and return fans in air handling units consuming a significant portion of energy. To address this, researchers have explored innovative economizer damper control methods and identified the “split-signal” strategy, which optimizes supply airflow using a single damper as a promising approach. In this study, split-signal was further refined for practical application and energy simulation, aiming to demonstrate its effectiveness and encourage adoption in real-world building mechanical systems. Laboratory testing on chilled water variable air volume (VAV) system showed fan energy savings of 0.2–5% compared to traditional “three-coupled” control, depending on ventilation air proportions, and prevented reverse airflow. A statistical regression model, based on experimental data, was developed to predict energy savings and streamline comparisons. Energy simulations were conducted across various U.S. climate zones and revealed potential savings of 15–20% in energy use, operational costs, and CO2 emissions. With minimal financial investment, split-signal control offers a cost-effective solution to improve energy efficiency and reduce environmental impact, promoting its adoption in real-world building applications.
Climate change and the need to reduce greenhouse gas emissions have made energy efficiency in modern building operations more critical than ever. This study presents an improved damper control strategy for VAV systems, combined with techniques like DCV and duct static pressure adjustments, to optimize fan energy consumption. Using energy simulations and mathematical models, the research evaluates traditional HVAC operating methods against the proposed novel control approach across diverse climates. Findings show that the refined control integrations effectively adjust ventilation air volumes during low occupancy and achieve up to 47% savings in fan energy, cost, and CO2 savings annually. While DCV alone had minimal impact on fan energy, it significantly reduced the amount of outdoor air that required conditioning, thereby lowering cooling and heating demands. This research highlights the importance of integrating an advanced control strategy in building mechanical systems to reduce operational costs and environmental impact, contributing to sustainability and carbon reduction goals.
This study introduces a dynamic, multi-output stacking framework for real-time forecasting of HVAC cooling-coil behavior in air-handling units. The dynamic model encodes short-horizon system memory with input/target lags and rolling psychrometric features and enforces leakage-free, time-aware validation. Four base learners—Random Forest, Bagging (DT), XGBoost, and ANN—are each optimized with an Optuna hyperparameter tuner that systematically explores architecture and regularization to identify data-specific, near-optimal configurations. Their out-of-fold predictions are combined through a Ridge-based stacker, yielding state-of-the-art accuracy for supply-air temperature and chilled water leaving temperature (R2 up to 0.9995, NRMSE as low as 0.0105), consistently surpassing individual models. Novelty lies in the explicit dynamics encoding aligned with coil heat and mass-transfer behavior, physics-consistent feature prioritization, and a robust multi-target stacking design tailored for HVAC transients. The findings indicate that this hyperparameter-tuned dynamic framework can serve as a high-fidelity surrogate for cooling-coil performance, supporting set-point optimization, supervisory control, and future extensions to virtual sensing or fault-diagnostics workflows in industrial AHUs.