HVAC Systems Research Articles

Implementation of desk fans in open office: Lessons learned and guidelines from a field study

Desk fans allow individual thermal adjustment in shared spaces which increases occupants' thermal satisfaction. When associated with the increase of room conditioning system setpoint temperature, they can also reduce energy use. In comparison to other Personal Comfort Systems (PCS), low-power desk fans can be very efficient for cooling. Nevertheless, previous studies identify some barriers to their implementation and show no clear guidelines on how to overcome them. Therefore, this study presents the results of a field implementation of desk fans in an open office in Brazil. The intervention consisted of providing one desk fan for each occupant and progressively increasing the setpoint temperature. Indoor thermal conditions were recorded simultaneously with occupants' thermal perception using sensors and surveys. Results show fans increased thermal satisfaction by 20 %. And, when fans were available, the preferred indoor air temperature increased by 1 °C. However, many constraints affect the results. Based on this experience, we propose guidelines for future implementation. We emphasize the need to understand the HVAC system, engage building operators, and apply gradual temperature modification. As occupants’ expectations had a great impact on the potential temperature extension, we suggest a way to limit temperature extension in future implementations.

A novel rule mining method for knowledge discovery of relationships among indoor air quality, HVAC operation and occupants’ activities

This paper presents a novel data mining method to discover the occurrence time, co-occurrence and sequential association rules among indoor air quality (IAQ), Heating, Ventilation and Air Conditioning (HVAC) operation and occupants' activities. The novelty of this work includes a peak detection method to discover the pollutants' peaks and a rule mining method with extended rule selection criteria that considers both the time lags between events and relationships among multiple events. The peak detection method aimed to use moving windows and criteria to find the candidate peaks and the non-maximum suppression to filter the overlapped candidate peaks. The proposed rule mining method is based on the Apriori and Apriori-All with the rule selection criteria extended by labeling the occurrence time to events to find the rules among various occurrence times and multiple events and by limiting the time lags among the occurrences of the events to discover the sequential rules. Two datasets, one from 70 houses and one from a single commercial building, were used to evaluate the performance of this proposed data-driven method. The results showed that 93.19 % of the peak detection results matched the peaks detected from the data records. The CO2 peaked frequently at 12:00, 17:00 and from 19:00 to 24:00. The occurrence of occupants' activities could lead to pollutants’ concentrations and pollutants peaks within 2 hours in the residential buildings. The occurrence of a high Wifi connection number was frequently followed by a CO2 peak within 2 hours in the commercial building. These findings can support the development of control strategies for building HVAC systems to achieve better indoor air quality control.

Deep Weighted Fusion Learning (DWFL)-based multi-sensor fusion model for accurate building occupancy detection

With the advancement of artificial intelligence, the dominance of deep learning (DL) models over ordinary machine learning (ML) algorithms has become a reality in recent years due to its capability of handling complex pattern recognition without manual feature pre-definition. With the growing demands for power savings, building energy loss reduction could benefit from DL techniques. For buildings/rooms with the varying number of occupants, heating, ventilation, and air conditioning (HVAC) systems are often found in operations without much necessity. To reduce the building’s energy loss, accurate occupancy detection/prediction (ODP) results could be used to control the proper operations of HVACs. However, ODP is a challenging issue due to multiple reasons, such as improper selection/deployment of sensors, inefficient learning algorithms for pattern recognition, varying room conditions, etc. To overcome the above challenges, we propose a DL-based framework, i.e., Deep Weighted Fusion Learning (DWFL), to detect and predict occupancy counts with optimal multi-sensor fusion structure. DWFL fuses the extracted features from multiple types of sensors with the priority/weight assignment to each sensor. Such weight assignment considers different room conditions and the pros/cons of each type of sensor. To evaluate DWFL model in terms of occupancy prediction accuracy, we have set up an experimental testbed with low-cost cameras, carbon dioxide (CO2), and passive infrared (PIR) sensors. Among the recently proposed occupancy detection models, DeepFusion utilized deep learning model on heterogeneous sensor data and achieved 88% accuracy in occupancy count estimation (Xue et al., 2019). Another deep learning-based model MI-PIR achieved 91% accuracy on raw analog data from PIR sensors (Andrews et al., 2020). Our research outcome is 94%. Therefore, the experiment results show that our DWFL scheme outperforms the state-of-the-art ODP methods by 3%.

Using active cooling/heating for 1C1R grey-box model parameter identification in actual environment: A proof-of-concept study

A model predictive control (MPC) has been important method for managing both comfort and energy saving in heating, ventilation, and air conditioning (HVAC) problems. However, recent data-driven models for MPC, relying on extensive training data, pose challenges for practical implementation in real-world thermal environments due to their time-consuming nature. The grey-box approach, utilizing a simple RC model as a thermal environment proxy, is well known for its data efficiency. Nevertheless, numerical instability arising from the multi-collinearity of observed data can degrade the model’s time efficiency. To deal with this issue, we propose and implement a rapid and stable parameter identification method that integrates active cooling-heating within the actual thermal environment. Our method requires only a single day of data to estimate basic RC model parameters, allowing for immediate use of the RC model in MPC as soon as an air conditioner is installed. Practical Application Using a grey-box model for MPC in HVAC systems is efficient, but the multicollinearity problem of observed data undermines its time efficiency. Our method deals with this challenge by enabling immediate model parameter identification with just 1 day’s data, incorporating active cooling-heating. We demonstrate it in an actual thermal environment. The high level of time and data efficiency afforded by our method is particularly beneficial for IoT applications like malfunction detection and adaptive room reparameterization associated with room rearrangement.

Fault detection and diagnosis in light commercial buildings’ HVAC systems: A comprehensive framework, application, and performance evaluation

The data-driven approach currently dominates the field of Automatic Fault Detection and Diagnosis (AFDD) in HVAC systems. However, a significant concern lies in the prevalent use of labeled experimental and simulation data, which often does not represent real-world operational conditions. This study unveils a comprehensive framework for AFDD in light commercial buildings, effectively leveraging unlabeled raw data extracted directly from their Building BAS. Its main goal is to provide a versatile methodology tailored for real-world applicability. Buildings classified as “light commercial” typically have less than 2,500 square meters of floor area and no more than six stories, such as small offices, medical facilities, banks, small manufacturing facilities, etc. A common feature of these buildings is the fact that the HVAC systems tend to be relatively simple and have similar configurations, thus making it easy to develop scalable and reproducible fault detection methods. This paper focuses on a practical case study in a light commercial building HVAC system situated in Montreal, Canada, encompassing a single Air Handling Unit (AHU) and four Variable Air Volume (VAV) reheating boxes to evaluate the framework. This comprehensive framework encompasses a sequence of sub-objectives: creating a sizable, synchronized raw dataset from diverse BAS sensor tags, comprehensive data cleansing to address inconsistencies, developing an anomaly detection method, investigating these anomalies to extract underlying rules, and finally, dataset labeling. An AFDD classification model is then applied to evaluate its ability to distinguish normal from faulty conditions across various fault types. The study highlights the potential of dimensional reduction techniques and unsupervised clustering for effective anomaly detection in light commercial buildings, as well as the power of the Decision Tree classifier for uncovering hidden patterns, especially in anomaly conditions. It also highlights the significance of addressing imbalanced datasets in AFDD and the complexities of detecting sizing-related faults. Despite these challenges, the framework exhibits robust performance in detecting and diagnosing a range of HVAC faults. It offers a systematic and adaptable approach for handling real-world operational data in light commercial building HVAC systems, extendible to other building types, bridging the gap between data-driven methods and practical applications.

Integration of resilient cooling technologies in building stock: Impact on thermal comfort, final energy consumption, and GHG emissions

Buildings in the EU contribute significantly to energy consumption and greenhouse gas emissions, with HVAC systems being major contributors. This paper assesses the impact of the resilience of various cooling strategies on thermal comfort, energy consumption, and GHG emissions in the residential building stock in Belgium. This study uses an innovative approach for sizing and designing cooling systems, considering the impact of climate change on future weather conditions and extreme heatwaves. The findings reveal alarming temperature increases, with potential rises of up to 4.1 °C from the 2010s to the 2090s, particularly in the high-emission SSP5-8.5 scenario. The study investigates three cooling strategies: scenario 1 (mechanical ventilation), scenario 2 (mechanical ventilation and natural ventilation), and scenario 3 (mechanical ventilation, natural ventilation, and split system). In scenario 1, there is a notable increase in Indoor Overheating Degree (IOhD), reaching up to 586% in the 2090s for semi-detached buildings, while scenario 2 consistently reduces IOhD, reaching only 0.2 °C by the 2090s. Scenario 3 achieves near-zero IOhD by the 2050s and 2090s. Notably, the “Heatwave [2081–2100]" exhibits unprecedented daytime temperatures, peaking at 46.0 °C. During the 2054 heatwave, insulated buildings maintained the Indoor Operative Temperature (IOpT) below 40 °C, whereas non-insulated buildings reached 44.3 °C, indicating challenges in meeting thermal comfort standards. Furthermore, cooling energy consumption increased by 106%–141% in the 2050s and surge by 174%–280% in the 2090s compared to the 2010s, along with significant GHG emissions growth in the future scenarios, particularly in SSP5-8.5.

Analysis of a domestic air heat pump integrated with an air-geothermal heat exchanger in real operating conditions: The case study of a single-family building

The work presents an in-depth analysis of the real performance of an air heat pump unit installed in a single-family building and quantitatively determines the reduction in energy consumption achieved by the integration of an air-geothermal heat exchanger. The case study is a single-family building located in northern Italy. It is equipped with a heating, ventilation, and air conditioning (HVAC) system consisting of an air-geothermal heat exchanger coupled with a compact air source heat pump supported by an electric heater installed in a thermal storage and devoted to cover the peak demand. The main objectives of the work are to analyse the HVAC performance under real operating conditions compared to the design values and to highlight the existence of factors that affect this performance. The analysis was carried out by developing an accurate model of the heat pump system based on the real operating data acquired by the on-board monitoring system. The results confirmed the influence of the air-inlet conditions (temperature and humidity) and of the control strategy (more specifically, the ventilation flow rate) on the unit performance in both the heating and cooling modes. In particular, the analysis showed that minimising indoor ventilation in the case of low outdoor temperatures is of paramount relevance not only because it reduces the indoor heat demand, but also because it maintains the unit efficiency close to the design values. Furthermore, the installation of a geothermal heat exchanger guarantees a reduction in electricity consumption of approximately 30%.

Comparing the life cycle costs of a traditional and a smart HVAC control system for Australian office buildings

Many smart technologies have been introduced in buildings with the aim to reduce the energy and GHG emissions associated with their operation, particularly through improved control systems for regulating heating, ventilation and air conditioning (HVAC) equipment. Despite their energy saving potential, only a few studies have comprehensively assessed the costs associated with their practical implementation from a life cycle perspective. Accordingly, this study quantifies and compares the life cycle costs of a smart HVAC control system with that of a traditional control system, in the context of an Australian office building. For both systems, the required hardware are specified based on the characteristics of these systems and the layout of the serviced spaces in the reference building. The costs incurred over the period of assessment are quantified using the net present cost (NPC) approach. To evaluate the effects of these control systems on the operational energy costs of the building HVAC system, the control logics of both these systems are modelled through building energy simulations. The results show that, over the period of assessment, the smart control system incurred a higher total cost compared to the traditional control system. However, the findings from the simulations show that the HVAC energy cost savings achieved through the specification of the smart control system offset the additional cost incurred to deploy this system over the traditional control system. The smart control system resulted in HVAC operational cost savings between 9 % and 10 % compared to the traditional control system. Sensitivity analyses indicated that the total life cycle costs varied between −27 % and +50 %, with the discount rate and energy price increase rate being the most influential parameters.

EMPOWERING FUTURE BUILDINGS WITH IOT AND 5G TECHNOLOGY

In the realm of smart buildings, the convergence of Internet of Things (IoT) and 5G technology has unlocked unprecedented opportunities for enhanced building management, efficiency, and sustainability. This project endeavors to harness the potential of IoT sensors and actuators, including LDR, DHT, gas and smoke sensors, PIR, HVAC, lights, servo motors, buzzers, and displays, integrated with Arduino Nano microcontrollers. These microcontrollers serve as end nodes, orchestrating sensor data collection and actuator control. The data collected is transmitted to a gateway device, an ESP32 microcontroller, which interfaces with a wireless Wi-Fi router for connectivity. Leveraging the ThingSpeak platform, the gateway transmits data to the cloud, facilitating real-time monitoring and analysis. This system promises to revolutionize building management by enabling remote monitoring, predictive maintenance, energy optimization, and enhanced occupant comfort and safety. Through rigorous testing and optimization, this project aims to demonstrate the feasibility and effectiveness of IoT and 5G technology integration in empowering future building infrastructures. Keywords— Heating, Ventilation, and Air Conditioning (HVAC),Light Dependent Resistor (LDR), (Digital Humidity and Temperature(DHT)

Research on the Teaching Reform of Heating, Ventilation, and Air Conditioning Courses in Colleges and Universities Under the Internet Background

This study discusses the importance and practical strategies of Heating, Ventilation, and Air Conditioning (HVAC) course teaching reform in colleges and universities under the background of the Internet. With the rapid development of information technology, the Internet has brought unprecedented changes to the field of education. This paper first analyzes the problems existing in the traditional HVAC course teaching, such as being out of the industry demand, weak teachers, insufficient practical teaching, single teaching methods, and so on. Then, combined with the advantages of Internet technology, it puts forward a targeted teaching reform plan, taking effective reform measures to achieve the expected teaching results, aimed at improving the teaching quality of HVAC courses and training more high-quality talents to meet the needs of the times.

Carbon emission reduction in public buildings of extreme cold regions: A study on enclosure structure and HVAC system parameter optimization

AbstractThe implementation of strategies aimed at curtailing energy consumption and carbon emissions in buildings is of paramount importance. Priority should be accorded to the reduction of embodied carbon emissions from construction materials and operational carbon emissions during the usage phase. A public building situated in an extremely cold region is chosen as the subject of this study. An initial investigation is conducted into the impact of various enclosure structure materials on embodied carbon. The impact of different heating, ventilation and air conditioning (HVAC) systems on the total carbon emissions of public buildings are studied as well. The findings indicate that the amalgamation of W3 + R + G4 + H4 culminates in the least total carbon emissions. Upon establishing the foundational scheme for the public building, an optimization (nondominated sorting genetic algorithm II [NSGA II] and Criteria Importance Through Intercrieria Correlation [CRITIC]) of the enclosure structure parameters is initiated to examine the optimal parameters of the public building's enclosure structure. The findings reveal that a decrease in the heat transfer coefficient could trigger an increase in total carbon emissions. This is attributed to the fact that the carbon emissions embodied in the production process of these materials could potentially outweigh the reduction observed in operational carbon emissions. Further adjustments were also made to the parameters of the HVAC system in the buildings. The findings indicate that within the context of public buildings, given the presence of optimal parameters and an HVAC system that utilizes solar energy for both heating and cooling in the American Society of Heating, Refrigerating and Air‐Conditioning Engineers, Inc. 6 A climatic zone, the efficiency of the cooling system can exert a significant influence on the operations carbon emissions reduction.

Modeling and predicting energy consumption of chiller based on dynamic spatial-temporal graph neural network

As an important equipment in the HVAC system, the chiller accounts for 50–60 % of the total energy consumption. According to the characteristics of chiller operation data and using the multivariate time series (MTS) forecasting method, a novel chiller energy consumption prediction model (T-CADGCN) is proposed, which is based on the temporal convolution (TC) and the dynamic graph convolution (DGC) network with a channel attention (CA) mechanism. Two datasets are used to verify the prediction performance of different models. Compared with the actual energy consumption, the average MAPEs of the T-CADGCN model on the measured dataset and simulated dataset are 0.92 % and 0.08 %, respectively. Whereas they are 2.8 % and 0.91 % for LSTM, 11.45 % and 11.74 % for MTGNN_GCA, 12.3 % and 12.63 % for MTGNN, respectively. The results demonstrate that the T-CADGCN model can effectively enhance the prediction performance of chiller energy consumption, followed by LSTM, then MTGNN_GCA, and finally MTGNN. Besides, the prediction performance on different future time steps is also conducted on two datasets. It can be found that all models decrease in prediction accuracy with the increase of the prediction time steps, but the T-CADGCN model can maintain a relatively good prediction performance with high robustness. The changes of in-degree and out-degree in the chiller energy consumption node in the dynamic graph construction module indicate that the factors affecting and being affected by chiller energy consumption change over time. This study can help to predict the energy consumption of chiller accurately and thus contributes to building energy management.

Investigating the effect of lower body local radiant warming on occupant thermal comfort in battery electric vehicles during cold conditions

The wintertime decrease in the driving range of battery electric vehicles (BEVs), partially attributed to cabin heating with improper setpoints, necessitates the improvement of occupant thermal comfort with reduced energy consumption. While local warming shows promise, understanding its impact on occupant comfort with thermal transients from cabin heating, ventilation, and air conditioning (HVAC) is limited. To address this gap, we investigated thermal perception in twenty-five participants under three distinct warming modes within BEVs operating through typical winter conditions: HVAC alone, HVAC with continuous lower body local radiant warming (LRW), and HVAC with periodic lower body LRW. Results show that the rapid change in skin temperature from lower body local warming does not immediately improve comfort. While a significant improvement in comfort (p < 0.05) is observed with lower body warming, it becomes evident only when the cabin transients subside. Consequently, we propose a framework that advocates for reducing HVAC setpoint and control of LRW of the lower body based on occupant preferences. Our feasibility study demonstrates a 45.3 % reduction in energy consumption by reducing the HVAC setpoint from 25 to 18 °C. These findings enhance the prospects for efficient thermal comfort management in BEVs.

Multimodal Framework for Smart Building Occupancy Detection

Over the years, building appliances have become the major energy consumers to improve indoor air quality and occupants’ lifestyles. The primary energy usage in building sectors, particularly lighting, Heating, Ventilation, and Air conditioning (HVAC) equipment, is expected to double in the upcoming years due to inappropriate control operation activities. Recently, several researchers have provided an automated solution to turn HVAC and lighting on when the space is being occupied and off when the space becomes vacant. Previous studies indicate a lack of publicly accessible datasets for environmental sensing and suggest developing holistic models that detect buildings’ occupancy. Additionally, the reliability of their solutions tends to decrease as the occupancy grows in a building. Therefore, this study proposed a machine learning-based framework for smart building occupancy detection that considered the lighting parameter in addition to the HVAC parameter used in the existing studies. We employed a parametric classifier to ensure a strong correlation between the predicting parameters and the occupancy prediction model. This study uses a machine learning model that combines direct and environmental sensing techniques to obtain high-quality training data. The analysis of the experimental results shows high accuracy, precision, recall, and F1-score of the applied RF model (0.86, 0.99, 1.0, and 0.88 respectively) for occupancy prediction and substantial energy saving.

Impact of low-frequency noise on a residential zone due to commercial HVAC systems

Low frequency noise (LFN) is a serious growing global challenge for the urban environment where noise itself is an undervalued pollutant. The commercial establishments are equipped with multiple HVAC (Heating Ventilation and Air Conditioning) units responsible for the generation of LFN. To assess the impact of LFN, the noise was monitored using A and C-weighting sound level meters at HVAC outlets as well as in and around the residential premises. The noise due to HVAC units is found to be highly intensive in the lower frequency zones (<250Hz), affecting psychological and physiological health of living beings in the residential zones. A substantial 39.4 dB sound pressure level discrepancy between A and C-weighting inside the residential premises underscores the pronounced predominance of low-frequency noise. Noise monitoring using A-weighting failed to highlight the significant impact of lower frequency octave bands. The C-weighting noise monitoring revealed a substantial contribution of lower frequency octave bands (8Hz–250Hz) with 48.2 dB(C), in the overall equivalent noise level of 48.6(C), primarily attributed to HVAC units. The study suggests monitoring and assessment of the LFN, its mitigation and control strategies and its impact on the noise environment, especially on a residential zone.

Assessing the Impact of Climate Changes, Building Characteristics, and HVAC Control on Energy Requirements under a Mediterranean Climate

Assessing the Impact of Climate Changes, Building Characteristics, and HVAC Control on Energy Requirements under a Mediterranean Climate

SMART TEMPERATURE SENSORS FOR TEMPERATURE CONTROL SYSTEMS

Temperature control systems are pivotal in various applications, ranging from industrial processes and environmental monitoring to everyday comfort and safety. Smart temperature sensors represent a significant advancement in this field, enabling precise, efficient, and intelligent temperature regulation. This article provides an overview of the latest developments in smart temperature sensors and their integration into temperature control systems. The paper begins by discussing the fundamental importance of temperature control systems in maintaining optimal conditions in diverse settings. It highlights the growing need for sensors that offer improved accuracy, reliability, and adaptability, all of which smart temperature sensors are designed to provide. Subsequently, the article delves into the key features and capabilities of smart temperature sensors. These sensors incorporate advanced technologies such as microelectromechanical systems (MEMS), integrated digital signal processing, and wireless connectivity, enabling them to collect and transmit data with unprecedented precision and efficiency. Moreover, smart temperature sensors often offer real-time data monitoring, remote access, and the capacity for data analytics, making them invaluable tools for enhancing temperature control. The discussion then shifts to the various applications of smart temperature sensors. Whether it be optimizing energy consumption in HVAC systems, ensuring compliance with safety standards in industrial processes, or monitoring temperature-sensitive goods during transport and storage, these sensors have the potential to revolutionize temperature control across numerous domains. Additionally, the article addresses the challenges and considerations in implementing smart temperature sensors, including calibration, data security, and power efficiency. The integration of artificial intelligence and machine learning algorithms for predictive temperature control is explored, as they promise to further enhance the adaptability and responsiveness of temperature control systems. In conclusion, smart temperature sensors are at the forefront of temperature control system innovation. Their ability to provide real-time, highly accurate data, alongside intelligent features, positions them as key components in achieving optimal temperature conditions in a wide range of applications. As technology continues to evolve, the adoption of smart temperature sensors is expected to grow, ushering in a new era of temperature control efficiency and precision. Keywords: Smart temperature sensors, Precision temperature monitoring, Digital signal processing, Safety, Industrial processes.

Building heating load forecasting based on the theory of transient heat transfer and deep learning

Reliable and accurate heating load forecasting can provide comprehensive information for the monitoring and control of Heating, Ventilation, and Air Conditioning (HVAC) in buildings, which reduce uncertainty on the load demand of energy effectively. Data-driven method has demonstrated a potential to forecast heating load, but current methods generally lack the consideration of features on model forecasting performance and applicability. Based on the theory of transient heat transfer and conduction transfer function for building hourly heating load calculation, this study proposes an idea that comprehensively selects physical variables affecting the hourly dynamic changes of the building heating load as features, which enhances the persuasiveness of selecting datasets features. Then we use the deep learning method to build short-term heating load forecasting models, and explore the influence of different feature combinations and time steps on the model forecasting performance. Combining the physical property of building heat gains, we divide the features into external heat gains, internal heat gains and historical heating load and then show their performance of models at different time steps. It is shown that the two-hour data of external heat gains and internal heat gains, the three-hour data of past heat load have the highest value. The best model can achieve a mean absolute error of 0.153 kW and a mean absolute percentage error of 6.2 %. These findings are helpful for researchers to select more relevant features to forecast heating load in buildings and improve their models through physical aspect.

Design and Optimization of Cross-Corrugated Triangular Ducts with Trapezoidal Baffles Based on Response Surface Methodology and CFD

Plate heat exchangers are widely used in the Heating, Ventilation, and Air Conditioning (HVAC) field. Cross-corrugated triangular ducts are commonly employed in plate heat exchangers. Inserting baffles into the cross-corrugated triangular ducts can improve the heat transfer performance of the plate heat exchangers. This study focuses on intricate interdependencies among the flow channel apex angle, the trapezoidal baffle inclination angle, baffle position, and Reynolds number (Re) on heat transfer and pressure drop using response surface methodology (RSM) and computational fluid dynamic (CFD). To identify the factors that maximize the Nusselt number (Nu) and minimize friction factor (f), the RSM is used to design factors, conduct numerical studies, and establish regression equations. The results show that the apex angle, baffle angle, X-direction position, and Re have significantly affected Nu and f. Compared to a non-baffled channel with the same apex angle and Re conditions, the optimized channel enhances heat transfer by 1.54 times and has an almost identical pressure drop. The inclined baffle significantly enhances comprehensive performance at low Re. The synergistic effect of the heat transfer and pressure drop is most optimal when the apex angle of the flow channel is 90°, the trapezoidal baffle inclination angle is 52.5°, and the Re is 1000, with the baffle position at 0.625H in the X-direction.

Non-intrusive thermal load disaggregation and forecasting for effective HVAC systems

Non-Intrusive Thermal Load Monitoring (NITLM) tracks the sub-loads generated by each heat source (e.g. occupants, equipment, solar radiation etc.) from the total thermal load and indirectly provides a room’s thermal properties without additional sensors. Since sub-loads can improve the efficiency of HVAC systems, NITLM is a very attractive technology for building energy management. NITLM has traditionally focused on analyzing past and present sub-loads. However, by forecasting future sub-loads, HVAC systems will be able to schedule operations that take into account the thermal properties of future rooms. This work focuses on a new NITLM framework that forecasts future sub-loads based on the current and past total thermal loads. In experiments, we selected occupant loads that are closely connected to HVAC systems and performed sub-load forecasting using two types of approaches. One is a two-step approach that separately performs them in turn. This approach use separately trained model for disaggregation and forecasting, this allow us to fine-tuning the hyper-parameter for dedicate model. Moreover, the two-step approach can take into account the different properties and difficulties of each inference, resulting in smaller errors in sub-load forecasting. The other is an integrated approach. This approach combines load disaggregation and forecasting into a single estimation process, eliminating error propagation and reducing overall error in sub-load forecasting. Moreover, this approach utilizes the Adaptive Moment Estimation (Adam) algorithm for effective parameter optimization, enabling complex training and improving the accuracy of sub-load forecasting. We conducted evaluations of thermal load disaggregation and forecasting across a range of realistic building scenarios. The findings indicate that the integrated approach predicts sub-loads with a MAE that is up to 34.9% lower than that of the two-step approach. Additionally, it identifies occupants presence with an 18.5% higher F-score. This demonstrates its enhanced suitability for accurately predicting sub-loads and estimating future occupancy schedules.