The operational and indoor environmental quality of buildings has a significant impact on global energy consumption and human quality of life. One of the key directions for improving building performance is the optimization of building control systems. In modern buildings, the presence of numerous actuators and monitoring points makes manually designed control algorithms potentially suboptimal due to the complexity and human factors. To address this challenge, model predictive control based on artificial neural networks can be employed. The advantage of this approach lies in the model’s ability to learn and understand the dynamic behavior of the building from monitoring datasets. It should be noted that the effectiveness of such control models is directly dependent on the forecasting accuracy of the neural networks. In this study, we adapt neural network architectures such as GRU and TCN for use in the context of building model predictive control. Furthermore, we propose a novel hybrid architecture that combines the strengths of recurrent and convolutional neural networks. These architectures were compared using real monitoring data collected with a custom-developed device introduced in this work. The results indicate that, under the given experimental conditions, the proposed hybrid architecture outperforms both GRU and TCN models, particularly when processing large sequential input vectors.

Enhancing energy efficiency within the building sector is imperative to curbing energy losses, given that this sector alone contributes to over 34% of global energy consumption. Employing a building management system, along with its regular updates, presents a strategic avenue to decrease energy usage, enhance building energy efficiency, and more. Tailored control strategies, aligned with the unique characteristics and usage patterns of each building, are essential for achieving energy savings. This article presents an evaluation of HVAC system efficiency in office buildings, utilizing a data-driven approach coupled with simulations conducted in IDA ICE software. The research explores the control strategy of an office building equipped with a constant air volume HVAC system, featuring a regularly controlled air handling unit. The objective is to boost energy efficiency while striking a balance between occupant comfort and energy consumption. Findings indicate that by analyzing measured data and adjusting configurable parameters, building energy consumption can be significantly reduced. Close monitoring of indoor parameters by building operators and corresponding adjustments to the HVAC system can yield energy savings of up to 16%. Leveraging these insights, the paper suggests integrating data-driven and dynamic simulation methods into building management system models to optimize HVAC systems, enhance energy efficiency, and advance ambitious carbon neutrality objectives.

Optimal- heating-start strategies can reduce unnecessary heating, ventilation, and air conditioning (HVAC) operation while maintaining acceptable indoor temperatures at occupancy. However, forecasting models are often evaluated using aggregate prediction errors that may not reflect operational performance. This study compares four data-driven approaches: gated recurrent unit (GRU) and long short-term memory (LSTM), recurrent networks with different memory mechanisms; temporal convolutional network–GRU (TCN-GRU), combining temporal convolutions and recurrence; and extreme gradient boosting (XGBoost), using gradient-boosted decision trees. Using measurements from an occupied office building, these models were compared with four conventional optimal-start strategies using 24 h of historical inputs and a 6 h prediction horizon. Performance was assessed through temperature prediction errors, recovery-time errors, temperature-deficit exposure, and unnecessary heating runtime. Uncertainty was evaluated using paired day-level bootstrap resampling of 22 recovery events. XGBoost achieved the lowest temperature mean absolute error (MAE) (0.182 $°$C), while LSTM achieved the lowest recovery-time MAE (25 min) and unnecessary heating runtime (5.7 min/day). TCN-GRU achieved the lowest temperature-deficit exposure (4.9 K$·$min/day), despite a higher aggregate forecasting error. With considerable uncertainty in some comparisons, no model was consistently superior across objectives. These findings show that optimal-start model selection should consider operational trade-offs, not forecasting accuracy alone.