Indoor Temperature Research Articles

Evidence-based strategies for optimizing long-term temperature monitoring in offices

Long-term monitoring of the thermal environment in office buildings has become increasingly relevant with the rise of wireless sensor networks. However, there is a notable absence of explicit guidelines for implementing monitoring strategies in such contexts. This lack of direction can lead to inconsistent deployment of sensor networks, resulting in higher maintenance costs and inaccurate long-term assessments of thermal conditions. Based on data analyses of high-accuracy, high-frequency field measurements conducted over a year or longer across multiple offices in Sydney and Shanghai, this study proposes a strategy for long-term temperature monitoring. The strategy advises practitioners to prioritize considerations such as air-conditioning type, room size, and space function when selecting "representative" sensor locations. Typically, sampling every 30minutes is deemed adequate for shared offices where an error margin of ±0.5°C is acceptable. For environments with stable indoor temperatures, less frequent sampling intervals suffice. A power regression model tailored for offices equipped with central AC and no operable windows was developed to predict the maximum allowable sampling interval based on several days of indoor temperature monitoring in winter. Regarding monitoring duration, the study advocates a preferred sampling period of one year to comprehensively capture seasonal variations. Alternatively, a minimum monitoring period of four to six months commencing in late spring or early summer is identified as potentially sufficient. These findings offer valuable insights for optimizing long-term thermal monitoring practices in offices and may contribute to expanding the scope of thermal comfort standards.

Vulnerability to heat-related mortality and the effect of prevention measures: a time-stratified case-crossover study in Switzerland.

Swiss climate scenarios predict increases in the frequency and intensity of extreme heat episodes in the future. For the effective prevention of heat-related mortality, several aspects of the population's vulnerability to heat must be understood on a local level. A nationwide analysis of individual death records was conducted, enabling a more comprehensive understanding than typical heat studies based on aggregated data. A total of 320,306 individual death records from the Swiss National Cohort with precise address information during the warm season (May to September) from 2003-2016 were linked to indoor and outdoor high-resolution daily temperature estimates. A time-stratified case-crossover study combined with distributed lag non-linear models was then performed to assess the temperature-mortality associations for various causes of death and to estimate the potential effect modification of individual characteristics. Additionally, it was explored whether the effect of extreme heat changed over time in regions with and without cantonal heat-health action plans (HHAPs). Using the temperature with the lowest cause-specific mortality risk (minimum mortality temperature) as the reference temperature, extreme heat (defined as ambient daily maximum temperature reaching 33 °C) was associated with a strong increase in all-cause mortality (odds ratio (OR): 1.21, 95% CI: 1.17-1.25) and disease-specific mortality from Alzheimer's disease and dementia (OR: 1.67, 95% CI: 1.48-1.88), COPD (OR: 1.37, 95% CI: 1.12-1.67), diabetes (OR: 1.34, 95% CI: 1.06-1.70), and myocardial infarction (OR: 1.26, 95% CI: 1.10-1.44). Indoor temperatures above 24 °C were found to be critical for mortality. The population most vulnerable to heat included older adults (≥75 years), unmarried individuals, people with a low education level, older women with low neighbourhood socioeconomic position, and men under 75 years old with low socioeconomic position. Overall, the risk of heat-related all-cause mortality in 2009-2016 was lower than that in 2003-2008. The decrease was significantly stronger in the region where cantonal HHAPs were implemented. This study provides important information for planning targeted and effective measures to reduce heat-related health risks in Switzerland. It demonstrates that HHAPs contribute to reducing heat-related mortality, although they may not reach the high-risk population of individuals with low socioeconomic position. Future prevention efforts should also target the less privileged population, including people younger than 75 years.

Impact of employing phase change material in building wall on energy consumption and thermal comfort level

Energy crises are becoming a problem for many, most of the energy being produced is utilized in buildings. Building design and materials that are used in buildings play a vital role in saving electricity. Sustainable cities are one of the eleventh goal of Sustainable Development Goals to be achieved and this study is in context of SDGs for developing tools to create this globe sustainable and efficient society for humans. Phase change material is a type of material that can absorb and release heat energy as it changes between solid and liquid states. This ability to store and release thermal energy makes PCM a promising material for use in building insulation, Heating Ventilation Air Conditioning Systems, and other energy efficient applications. The use of PCM in buildings has the potential to significantly reduce energy consumption and improve thermal comfort levels. By incorporating PCM into building envelopes, such as walls, roofs, and floors, the material can absorb excess heat during the day and release it at night, helping to regulate indoor temperatures and reduce the need for heating and cooling systems. This study investigates the impact of using PCM in building envelopes. In this regard office building rooms are modelled in CAD software and are simulated in energy plus software. The simulation results are validated by considering the experiment and numerical study as a reference from paper. Model room is simulated for Hyderabad, Pakistan. Building envelopes without PCM have conduction rate of around 106.6 W/m2, whereas building envelopes with PCM have conduction rate around 42 W/m2. This shows that utilization of PCM reduced heat conduction up to around 40%. PCM reduced energy consumption of around 33.25 kWh/year/m2. Results show that without PCM air temperature was above the thermal comfort value. it reached 300C in hot months, it reduced up to 270C with the incorporation of PCM.

Development and validation of intelligent load control for VRF air-conditioning system with deep learning based load forecasting

Variable refrigerant flow (VRF) air-conditioning systems have seen significant growth in Asia and its application is expanding globally. Despite the expanded application, most previous studies have focused on developing fault detection and diagnostics to achieve energy-efficient operations than on predicting power consumption. It's very difficult to predict the electrical consumption owing to its complex system configuration and various control strategies. A new control strategy is described for optimal adjustment of the desired target level based on time series forecasting using the optimized sequence to sequence model for VRF systems. Sequence to sequence (seq2seq) model with attention mechanism and Bayesian optimization is developed to predict accurate hourly and daily forecasts and rapid feedback control for fluctuating power consumption for VRF systems. The optimized seq2seq model is integrated into the intelligent load control (ILC). ILC can be used to manage VRF systems by dynamically prioritizing indoor units for curtailment using both quantitative inputs and qualitative rules. Overall, the results demonstrate that the deep learning based control allows coordination of the controllable loads of VRF systems in three commercial buildings. ILC with deep learning manages the power consumption within a desired target level, as well as indoor temperature reflecting the status of controlled indoor units, as objective functions of the control algorithm.

Effect of Cool Roof Paint Application on Metal Roof Surface Temperature and Indoor Air Temperature in Tropical Climates

Abstract Increasingly hot environmental temperatures and less comfortable indoor temperatures are the impacts of inappropriate choices of building roof materials. An effort to mitigate this problem is by using a cool roof. This study was conducted through a field experiment by applying cool roof paint to the metal roof of a building in Malang, Indonesia. Field measurement results show that the cool roof paint application can reduce the maximum surface temperature above the metal roof by up to 6.6ºC and under the metal roof by up to 6.3ºC, as well as the maximum indoor air temperature by up to 0.8ºC at a height of 120 cm above the floor and up to 1.2º C at a height of 50 cm below the metal roof.

Review and Measure Winter Thermal Performance in CLT Building: A Case Study on Meldia Research Institute for Advanced Wood

Abstract CLT (Cross Laminated Timber) as a building material could help lower the carbon footprint of construction projects. Thermal performance and comfort in CLT buildings as a place to work are very important for optimizing comfort and work quality using CLT buildings. In winter conditions, measure and review is very necessary to optimize the desired building according to the standard level of comfort when working. The aims of this research is to measure and review indoor thermal comfort of CLT building during winter, with the case study Meldia Research Institute for Advanced Wood, Fukuoka, Kitakyushu. This research method involves measuring indoor temperature intensity in winter to understand how CLT buildings can achieve an optimal balance of thermal comfort. The results of measurements using PMV analysis of both rooms with the HVAC on at a temperature of 22 degrees Celsius are that the PMV value tends from a Slightly warm condition (+1) to a Neutral (0) at each measurement time and at all points. Room 1 has the highest PMV value between slightly cool (-0.5) to Slightly warm (+1), while room 2 has the lowest value between Cool (-2) to Slightly warm (+1). These findings can guide building designers in developing architectural solutions that are sustainable and focus on occupant well-being.

A novel energy-saving and emission-reduction strategy based on facile preparation of thermal insulation coatings doped with modified vacuum ceramic microbeads for concrete protection

The development of thermal insulation protective coatings suitable for constructions and buildings offers a multifaceted approach: it substantially reduces indoor temperatures, enhances residential comfort, decreases air conditioning energy consumption, and conserves energy. Additionally, these coatings provide robust resistance against corrosive substances, thereby significantly prolonging the service life of concrete. In this work, the modification of vacuum ceramic microbeads (VCM) through the polymerization of catechol and hexamethylene diamine to form poly(catecholamine) (PCA) was investigated by FT-IR, XRD, and TEM analysis. Increased levels of incorporation of VCM@PCA further decreased thermal conductivity and increased surface hydrophobicity, while excessive incorporation detrimentally affected the coating's mechanical properties. PDMS/VCM@PCA coating demonstrated exceptional thermal insulation performance, reducing coating temperature by 15.9 °C under simulated sunlight exposure, and in outdoor experiments, the interior temperature of the simulated house with this coating was 4.2 °C lower than the external temperature, highlighting its potential for energy conservation, emission reduction, and building temperature regulation. Additionally, PDMS/VCM@PCA coating provided excellent protection for concrete structures, significantly enhancing abrasion resistance. It also improved the interfacial adhesion between the organic layer and concrete under dry, wet, and 10% NaCl immersion conditions. The addition of VCM@PCA further enhanced resistance to chloride ion penetration, effectively reducing chloride ingress. This thermal insulation protective coating presents a novel strategy for energy conservation, emission reduction, and sustainable development in the civil construction industry.

An Indoor Air Quality Analysis in Newly Constructed Apartments

This study analyzes the indoor air quality inspections of newly constructed apartments by the Busan Institute of Health and Environment for the last three years (2021-2023). Of the 41 inspections, 33 exceeded the recommended standard, and the average excess rate was 80.5%. When classified by measuring households, 148 out of 332 exceeded the standards, whereas, the average excess rate by household was 44.6%. Benzene was exceeded in two out of the 332 households; therefore, the excess rate was only 0.6%. However, the relative standard deviation was the largest, showing as the highest item in the scattergram. The average concentration of toluene was 1,006.0 µg/m3, which was 100.6% of the recommended standard and was exceeded by 138 households; hence, the excess rate was 41.6%. All six items(Formaldehyde, Benzene, Toluene, Ethylbenzene, Xylene, Styrene) reached the highest concentration in spring or summer when the indoor temperature increased. The average concentration of toluene in July was 1,922 µg/m3, close to 1.9 times the recommended standard; toluene is considered an item of particular concern in summer. In the correlation analysis with indoor temperature, the formaldehyde coefficient of determination was 0.4855, regarded as somewhat significant; it was difficult to confirm the correlation with temperature for the other five items, including benzene. In correlation with relative humidity, formaldehyde showed the same tendency as indoor temperature, with a coefficient of determination of 0.4404, which is believed to be due to its small molecular weight and high solubility. Due to the chimney effect, high concentrations of volatile organic compounds could be confirmed at low atmospheric pressure in the upper floors, and this trend was most evident for formaldehyde. For most items(Formaldehyde, Benzene, Toluene, Ethylbenzene, Styrene), a negative correlation was confirmed in which the emission amount decreased as the number of households increased. For large apartment houses, it is believed that it is due to sufficient bake-out and flush-out according to the adequate construction period and the use of eco-friendly and high-end building materials. Small apartments are classified together with many small houses. The emission concentration of small houses is relatively high because the proportion of the surface area where pollutants are released is high.

Exploring the Effect of Indoor Thermal Comfort using Iris Dampers: A Justification Study

This study explores the impact of fixed damper openings on indoor thermal comfort in a lab-scaled chamber. Experiments with maximum, medium, and minimum iris damper openings were conducted under various occupancy conditions. Results show that the maximum opening maintained temperatures close to the ideal 24°C with minimal fluctuations. In contrast, medium and minimum openings resulted in higher temperature variability and less efficient air distribution. Statistical analysis highlighted significant differences in temperature stability among the different damper settings. The maximum opening ensured a stable temperature range, while the minimum opening caused noticeable temperature stratification and discomfort, especially with more occupants. The findings indicate that fixed damper openings are inadequate for maintaining consistent thermal comfort due to their lack of adaptability. This underscores the need for advanced control systems that can dynamically adjust damper positions to ensure optimal indoor temperature regulation and improve energy efficiency.

Construction of a Model for Assessing the Comfort of Residential Indoor Environment Based on Multisensory Design

Economic development and technological progress have made people’s demand for indoor environments higher and higher, and designing safe, comfortable, and healthy indoor environments through multisensory design is worthy of serious consideration. In order to realize the assessment of indoor environment comfort under multi-sensory design, this paper carries out data assessment from three dimensions of thermal environment, light environment and air environment. Relying on the PMV model of thermal environment comfort, we analyze the trends of indoor temperature and humidity, average radiant temperature, and PMV values. Combine Weber-Fechler and lighting coefficient to study the visual comfort change of indoor light environment, and analyze the lighting illuminance of indoor light environment under different working conditions by illuminance uniformity. From the basic principle of indoor wind environment, the changes of effective temperature difference and blowing sense caused by air temperature and wind speed are investigated. The temperature difference of the south-facing room decreased between 12.14% and 15.65% before and after the heating was stopped, which is a small change. The average indoor ambient radiant temperature values at different measurement points were up to 27.59 °C, and the fluctuations of the average indoor thermal ambient PMV values were within the range of [-1.2,1.6]. When the indoor light ambient illuminance value increased from 200 lux to 600 lux, the visual comfort improvement was more significant than from 600 lux to 1000 lux. The indoor air distribution characteristic ADPI value was 100% when the air velocity was 0.15m/s and 0.25m/s. Based on the results of indoor environment comfort assessment, multisensory optimization of indoor environment comfort from heat, light and air environments is proposed to provide guidance for improving people’s satisfaction with indoor environment.

Energy consumption analysis and operating characteristics research on small time scale of variable refrigerant flow air conditioning systems in public buildings

In order to analyze the energy consumption and operation characteristics of the variable refrigerant flow (VRF) air-conditioning system on small time scale and put forward effective energy-saving suggestions, the VRF system operation experiments are carried out under different indoor set temperatures, different indoor unit opening quantities and different indoor set air velocities. This experiment studies the main influencing factors of energy consumption and operation of the VRF system, such as indoor temperature difference, indoor air velocity, outdoor environment temperature and so on. The results show that the rated power of indoor unit is linearly related to the energy consumption of the VRF system. The total active power changes greatly when the VRF starts and stops, and the outdoor ambient temperature changes. The indoor set air velocities have a great influence on the energy consumption and operation of the VRF system. The performance parameters increase first and then decrease with the increase of compressor frequency and load rate. When the load rate is 40 %∼60 %, the performance parameters can reach 3.2 ∼ 4.2.

Effects of occupant thermostat preferences and override behavior on residential demand response in CityLearn

As space heating accounts for 54% of annual residential electricity consumption in Quebec, demand response programs specifically target load shifting through the automated control of thermostat setpoints during peak hours. On a district scale, varied thermostat preferences and setpoint override behaviors can have an impact on the success of the demand response program. This study examines two unique occupant types (Average, Tolerant) in terms of thermostat setpoint preferences as well as three different occupant Levels-of-Detail (LoDs) and analyzes their effects on the energy flexibility provided during demand response periods. For our baseline scenario, LoD 1, a static setpoint schedule is used and there is no control of the heat pump, while LoD 2 and LoD 3 incorporate thermostat setbacks during demand response events. LoD 2 assumes the occupant is comfortable within 2°C from the setpoint while LoD 3 allows the occupant to override the DR setbacks. We estimate the flexibility services provided by a ten-house residential community through the automated control of heat pumps during a three-month winter period, and we implement and simulate our study in CityLearn using reinforcement learning-based control for district-level energy management. When comparing LoD 3 to LoD 1, electricity cost was reduced by approximately 12% and net electricity consumption was reduced by approximately 17% during demand response periods. Likewise, we find that LoD 2 could overestimate savings in net electricity consumption, cost, and peak demand by 5% compared to LoD 3. The number of hours where the indoor temperature deviated more than ▪ from the setpoint occurred for less than 5% of the timesteps on average for the 10 buildings for LoD 3 while still achieving significant net electricity consumption reductions, thus highlighting that we can provide energy flexibility services to the grid while balancing occupant thermal comfort. Finally, the agents learned optimal decision-making that reduced the number of overrides across the training episodes for both Average and Tolerant occupants. We thus present a multi-agent framework as a means for addressing various occupant setpoint preferences and override behaviors for the control of heat pump systems at the neighborhood level.

Effects of dynamic thermal conditioning on cognitive load and performance in an office environment

In the design of buildings with minimal environmental impact, the incorporation of higher energy flexibility is becoming increasingly relevant. This approach is associated with dynamic modulations in setpoint temperatures. Until now, a link between indoor temperatures and cognitive performance of workers has been assumed, leading to high energy consumption and overcooling of office environments in summer conditions. However, research focusing on the relationship between thermal indoor environments and cognitive performance has rarely considered the influence of dynamic temperatures or temporal effects. This is the first experimental study aiming to understand the impact of temperature in relation to time of day on the subjective perception of cognitive load and performance under various thermal conditions in real-world office environments. The results indicated no observable relationship between temperature setpoints (25–30 °C) and cognitive performance. Instead, the temporal dynamics of cooling rather than fixed and static temperature setpoints appeared to have an impact.

Comparative analysis of hydrogel-based thermotropic glazing and fixed horizontal overhangs in building performance

Thermotropic (TT) glazing is able to achieve energy-saving capabilities similar to external shading devices by dynamically regulating solar heat gain transmitted through windows in response to ambient climatic conditions. However, the building performance of TT glazing compared to traditional shading devices remains underexplored. This study aims to bridge this knowledge gap by comparing the building performance of hydrogel-based TT glazing and fixed horizontal external shading devices in terms of building energy consumption, daylighting performance, and thermal comfort. Experimental tests were conducted over a continuous ten-day period, focusing on the indoor temperature and illumination distribution within experimental rooms equipped with either TT glazing or fixed horizontal external shading device. Building performance models were developed using EnergyPlus and validated with experimental data. Subsequently, a comparative analysis was then conducted to evaluate the impact of TT glazings and fixed horizontal external shading devices on building energy consumption, daylighting performance, and thermal comfort across five typical climate conditions in China. The findings indicated that: (1) In five climate zones, TT provided the greatest energy savings in West-facing orientations, followed by East-facing orientations. (2) TT can replace fixed horizontal external shading device with a certain length to achieve similar building energy efficiency and indoor thermal comfort performance. (3) In regard to daylighting performance, TT achieved the desired values of sUDI<100lx,50 % and sUDI300–3000lx,50 % across all four orientations in the five climates. (4) In terms of thermal comfort, TT improved thermal comfort by reducing the annual daytime average PPDoverheating across all orientations in the five climate zones.

A Control Optimization Model for a Double-Skin Facade Based on the Random Forest Algorithm

Abstract: This study addresses the current difficulties in accurately controlling the indoor temperature of double-skin facades (DSFs), and its optimization, with a focus on the window opening angles of double-skin facades. The Spearman correlation coefficient method was used to select the main meteorological factors, including outdoor temperature, dew point temperature, scattered radiation, direct radiation, and window opening angle. A modified random forest algorithm was used to construct the optimization model and 80% of the data were used for model training. In the experiments, the average accuracy of the optimization model was as high as 93.5% for all window opening angles. This study provides a data-driven method for application to double-skin facades, which can effectively determine and control the window opening angles of double-skin facades to achieve energy saving and emission reduction, reduce indoor temperature, improve comfort, and provide a practical basis for decision-making. Future research will further explore the applicability and accuracy of the model under different climatic conditions.

Educational environments’ energy demand optimization based on indoor CO2 concentration and temperature: Together better than separately

Although optimization tools have been widely used to both minimize and control the energy consumption of buildings maintaining thermal comfort, the dramatic impact of the COVID-19 pandemic showed the relevance of considering the indoor air quality to act on the ventilation system.However, CO2 concentrations in closed environments with high occupancy rates, such as classrooms in schools, universities, or other educational environments, increase rapidly without effective ventilation, reaching the safe limits in about 15–30 min. Observing that the natural ventilation guides indicated by governments were insufficient to keep safe and comfortable spaces simultaneously, this study analyzes how mechanical heating, cooling, and ventilation systems would improve these results by using optimized control strategies in the same buildings that now use natural ventilation.Setting the objective function to minimize energy consumption, this study optimizes the use of mechanical systems considering the indoor temperature and CO2 concentration of educational indoor spaces in 4 types of schools and 3 climate zones in winter and summer. Results show that, at full occupancy, the ventilation should activate every 12 min, making slow-frequency control strategies inappropriate to keep the spaces safe.A 1-min step modeling asks for high computation that makes it critical for real-time control strategies, however, it allows a perfect setting of the working limits for legacy conditional equipment for establishing control policies on a one-day horizon.

The Cost-Optimal Control of Building Air Conditioner Loads Based on Machine Learning: A Case Study of an Office Building in Nanjing

Building envelopes and indoor environments exhibit thermal inertia, forming a virtual energy storage system in conjunction with the building air conditioner (AC) system. This system represents a current demand response resource for building electricity use. Thus, this study centers on the CatBoost algorithm within machine learning (ML) technology, utilizing the LASSO regression model for feature selection and applying the Optuna framework for hyperparameter optimization (HPO) to develop a cost-optimal control method for minimizing building AC loads. This method addresses the challenges associated with traditional load forecasting and control methods, which are often impacted by environmental temperature, building parameters, and user behavior uncertainties. These methods struggle to accurately capture the complex dynamics and nonlinear relationships of AC operations, making it difficult to devise AC operation and virtual energy storage scheduling strategies effectively. The proposed method was applied and validated using a case study of an office building in Nanjing, China. The prediction results showed coefficient of variation in root mean square error (CV-RMSE) values of 6.4% and 2.2%. Compared with the original operating conditions, the indoor temperature remained within a comfortable range, the AC load was reduced by 5.25%, and the operating energy costs were reduced by 24.94%. These results demonstrate that the proposed method offers improved computational efficiency, enhanced model performance, and economic benefits.

Enhancing demand response and heating performance of air source heat pump through optimal water temperature scheduling: Method and application

Air source heat pump (ASHP) is a key technology for the electrification of building heating, and its participation in demand response (DR) has important implications for reducing the grid peak load. However, current DR strategies mainly focus on changing the setpoint of indoor temperature, using the building’s thermal mass as a passive thermal storage, while the impacts of water temperature on the performance of ASHP units are often overlooked. Therefore, this study proposes an optimal water temperature scheduling (OWTS) method to respond time–of–use tariffs. It is developed based on a room thermal dynamic prediction model and an ASHP power consumption prediction model, optimizing supply water temperature schedule with objectives of maintaining indoor thermal comfort and reducing heating operating costs. The effectiveness of the OWTS method was tested on a field ASHP system in Beijing, and compared with two benchmark methods. Results demonstrate that the application of the OWTS method can enhance the DR capability of the ASHP heating system, with the average value of Flexibility Factor increasing from 0.134 to 0.728, and can reduce the heating operating costs by 20.8%–43.0%. This study thereby offers a promising method for ASHP heating systems to effectively participate in DR.

Development and evaluation of a buoyancy-driven airflow window with multioperation modes

This study introduces a novel, cost-effective window-integrated passive system (WIPS) that enhances indoor air quality and maintains comfortable temperatures throughout both summer and winter. The WIPS utilizes buoyancy-driven air flow through dual air cavities that alternately preheat or cool the incoming air depending on the season. The system’s design was optimized for Seoul, Korea, through computational fluid dynamics (CFD) simulations using Fluent 2021 R2 software, which employed a Reynolds-Averaged Navier-Stokes (RANS) model with RNG κ-ε turbulence modeling. Key design adjustments included the use of glass and unplasticized polyvinyl chloride (UPVC) to minimize unintended airflow, as well as modifications to the geometry and size of the air cavities to maximize efficient air flow and thermal effectiveness. The optimized design demonstrated significant improvements in thermal performance, achieving a preheating effect up to 35 °C in winter and reducing indoor temperatures by 10 °C in summer. These results underline the potential of WIPS to provide a sustainable solution for building ventilation and climate control.

Enhanced temperature regulation in compound heating systems: Leveraging guided policy search and model predictive control

With the widespread application of solar-energy-air-source heat pump composite heating, optimizing the regulation of air temperature in heating zones, enhancing system thermal comfort, and reducing energy consumption have become crucial. To ensure residential comfort while minimizing HVAC system energy costs, a control method combining guided policy search (GPS) with model predictive control (MPC) is proposed for composite heating systems. This method replaces state estimation in MPC with policy search and substitutes the offline trajectory optimization used in guided policy search with MPC, thus integrating the strengths of both approaches. This strategy not only improves control precision but also reduces energy consumption and enhances system robustness. The GPS-MPC control algorithm was validated against reinforcement learning and MPC. A simulation model was developed and validated on a real physical platform. Simulations compared the control effects of on-off control and MPC on pump frequency, flow rate, stratified thermal storage tank temperature, component, and system energy consumption. The data results indicate that the GPS-MPC algorithm offers superior predictive accuracy, efficiency, and robustness in composite heating control systems compared to conventional methods. Under the GPS-MPC strategy, indoor temperature fluctuations, pump frequency response speed, and energy consumption were significantly improved, with temperature fluctuation limited to only 0.8 °C, and the system achieving energy savings of over 12 %.