Building Energy Consumption Research Articles

Technical and Economica Feasibility of Photovoltaic Tiles Applies to a Single-Family Residence in Belo Horizonte-MG

Objective: The objective of this study is to verify whether photovoltaic tile technology presents technical and economic feasibility to be implemented in a single-family residence located in Belo Horizonte-MG. Theoretical framework: Through the photoelectric effect, photovoltaic tiles directly convert solar energy into electrical energy in a static, silent, non-polluting and renewable way. In this system, photons, energy-carrying particles present in sunlight, fall on a surface composed of photovoltaic cells (made of semiconductor material). At the ends of the semiconductor material, an electrical potential difference appears, responsible for setting the electrons in the structure in motion, producing electric current. Methodology: The methodology adopted for this research consists of simulating the energy consumption of a 77m2 residential building, consisting of 3 members. The tile and photovoltaic panel systems were designed to meet the energy demands of this building. Results and discussion: The results indicated that both systems present technical feasibility for their implementation, since the technologies demonstrated that they are capable of satisfying 100% of energy needs. However, from an economic point of view, only photovoltaic modules were viable. Originality/value: This work makes a contribution to the literature by analyzing a technology that is still little known in the energy market. Implications of the research: The relevance and value of this research are evidenced by the fact that photovoltaic tiles are a sustainable alternative to generate clean energy and reduce greenhouse gas emissions, which can contribute to the diversification of the Brazilian energy matrix and mitigation of impacts. of civil construction.

U-Values for Building Envelopes of Different Materials: A Review

In recent decades, the issue of building energy usage has become increasingly significant, and U-values for building envelopes have been key parameters in predicting building energy consumption. This study comprehensively reviews the U-values (thermal transmittances) of building envelopes made from conventional and bio-based materials. First, it introduces existing studies related to the theoretical and measured U-values for four types of building envelopes: concrete, brick, timber, and straw bale envelopes. Compared with concrete and brick envelopes, timber and straw bale envelopes have lower U-values. The differences between the measured and theoretical U-values of timber and straw bale envelopes are minor. The theoretical U-values of concrete and brick envelopes ranged from 0.12 to 2.09 W/m2K, and the measured U-values of concrete and brick envelopes ranged from 0.14 to 5.45 W/m2K. The theoretical U-values of timber and straw bale envelopes ranged from 0.092 to 1.10 W/m2K, and the measured U-values of timber and straw bale envelopes ranged from 0.04 to 1.30 W/m2K. Second, this paper analyses the environmental factors influencing U-values, including temperature, relative humidity, and solar radiation. Third, the relationship between U-values and building energy consumption is also analysed. Finally, the theoretical and measured U-values of different envelopes are compared. Three research findings in U-values for building envelopes are summarised: (1) the relationship between environmental factors and U-values needs to be studied in detail; (2) the gaps between theoretical and measured U-values are significant, especially for concrete and brick envelopes; (3) the accuracy of both theoretical and the measured U-values needs to be verified.

Inverse problem method application in building physics numerical optimization: new insight into ideal envelope properties determination

ABSTRACT Building thermal design optimization is pivotal for energy efficiency and built environment improvement. The optimal thermophysical properties for building walls remain ambiguous. This ambiguity stems from the constraints of traditional building physics, which: (1) disjoins the enhancement of wall thermal performance from the building service system management; and (2) relies on the forward method that fails to identify the ideal variable thermophysical property, the solution to which is inherently a function. This study elucidates the optimal temperature-dependent volumetric specific heat ( ρ c p ( t ) ) and thermal conductivity ( k ( t ) ) through the inverse problem and variation method. Illustrative example indicates that the optimal ρ c p ( t ) closely resembles a combination of two ‘ δ ’ functions, while the optimal k ( t ) mirrors a square wave function. Utilizing these ideal thermophysical properties, the building energy consumption can be significantly reduced by 77.1% with the optimized ρ c p ( t ) and 79.9% with the optimized k ( t ) . The ideal thermophysical properties for active buildings differ significantly from those recommended for passive buildings, underscoring that minimal energy consumption does not necessarily imply minimal discomfort. Therefore, the thermophysical properties of active and passive buildings should be optimized distinctly. This research offers valuable insights for defining ideal thermophysical properties of active building walls and construction materials.

Multi-objective optimization of daylighting performance and energy consumption of educational buildings in different climatic zones of China

With the implementation of China's “Healthy Building” and “Dual Carbon” strategies, daylight health and energy-saving carbon reduction in buildings have become key research areas. In educational buildings, early design decisions significantly impact students' eye health and energy consumption reduction, making it crucial to balance these concerns. Studies indicate that sufficient and continuous daylight can significantly improve students' eye health, mood and sleep. To maximize the UDI level at the eye level (seated) and minimize EUI and DGP, this study used the multi-objective optimization tool Wallacei based on NSGA-II (Non-dominated Sorting Genetic Algorithm II) for genetic optimization. This study uses the Shiji Building of Central South University in Changsha, Hunan, as a reference model to provide optimal classroom designs for China's five major thermal design zones: severe cold, cold, hot summer and warm winter, hot summer and cold winter, and mild. The results indicate that optimizing the classroom's deflection angle, length, width, height, and WWR significantly improves energy efficiency and daylighting performance. Specific data shows that an orientation 5° east or 5° west of south helps balance energy consumption and daylighting performance in both large and small classrooms. The length and width of the classrooms vary greatly, but the height generally converges to 3.2 m. Increasing the WWR to 0.5–0.7 demonstrates good energy efficiency and daylighting performance in both large and small classrooms in hot climate zones. In all climate zones, compared to the initial scheme, the Knee solutions reduced the EUI of both types of classrooms by up to 19.0 %, reduced DGP by up to 56.4 %, and increased UDI by up to 19.0 %.

Energy efficiency in smart schools using renewable energy strategy

As smart schools increasingly rely on technology, achieving energy efficiency becomes crucial for cost reduction and sustainability. This study investigates energy efficiency strategies in smart schools, focusing on the integration of renewable energy technologies. A quantitative approach using numerical simulations and literature reviews establishes benchmarks for energy-efficient smart schools. The Design Builder software is employed to evaluate system performance, with validation achieved through analysis in the System Advisor Model software. The modeled smart school building in Design Builder consumes 75,385.63 kWh annually, based on the weather conditions of specific location. Further studies indicate that integrating photovoltaics and hot water collectors can generate approximately 86,635 kWh annually. This not only offsets the energy consumption of building but also produces an excess of 11,249 kWh, which can be transferred back to the grid for additional revenue. Validation using SAM software demonstrated a minimal difference (3.2%) in annual energy outputs, confirming the accuracy of the model. The findings suggest that photovoltaics and hot water collectors can significantly contribute to achieving net-zero energy consumption in smart school buildings. Additionally, a focus on rooftop installations promotes sustainability by minimizing land use.

Machine Learning Baseline Energy Model (MLBEM) to Evaluate Prediction Performances in Building Energy Consumption

Machine Learning Baseline Energy Model (MLBEM) to Evaluate Prediction Performances in Building Energy Consumption

Analysis of energy performance and load matching characteristics of various building integrated photovoltaic (BIPV) systems in office building

Building Integrated Photovoltaic (BIPV) is a key technology for achieving zero-energy buildings by generating electricity and reducing energy consumption. Although many studies have analyzed the impact of BIPV on building energy efficiency, there is a lack of comprehensive comparative analysis of various BIPV systems. This study compared the impact of various BIPV systems on office building energy performance and provided optimal solutions for different climate zones. Simulation models for PV rooftop, PV window, and PV shading systems were developed and validated in EnergyPlus. The energy performance of BIPV systems in different Chinese climates was evaluated using these models. The results show that the PV window and PV shading have the most power generation capability in Beijing, and the PV rooftop has the most power generation capability in Kunming. Energy savings in Kunming are the highest with PV rooftop, PV windows, and PV shading at 111.78 %, 39.36 %, and 44.43 %, respectively. Finally, the study calculated the self-sufficiency rate (SSR) and self-consumption rate (SCR), and their ratio, along with the load matching ratio, were used to assess loading matching. Optimal BIPV schemes were identified for each climate zone, revealing that the PV rooftop combined with the PV shading system achieved the best load matching in Kunming, Guangzhou, Changsha, Beijing, and Harbin, with ratios of 82.00 %, 69.38 %, 70.88 %, 74.78 % and 67.27 %, respectively. These results provide a valuable reference for implementing the BIPV system to achieve zero energy consumption in office buildings under different climatic conditions in China.

MULTI-OBJECTIVE OPTIMIZATION STUDY OF RESIDENTIAL ENERGY CONSUMPTION BASED ON EDH AND THE STOCHASTIC OPERATION OF AIR CONDITIONING

ABSTRACT Current requirements for residential energy-efficient design solutions in China are relatively homogeneous, requiring only improvements in overall building energy performance, often ignoring the energy differences between different residential housing units. This paper proposes a multi-objective research framework based on an occupant behavior model of air conditioning and a Non-dominated Sorting Genetic Algorithm-II (NSGA-II) to study energy-efficient design solutions for residential envelopes. The optimal energy-saving design scheme has a 22.56% and 35.34% reduction in energy consumption difference between residential units and overall building energy consumption, respectively, both of which have been optimized substantially. Moreover, the overall energy performance of the building can be improved when the “energy performance difference between housing units” (EDH) is reduced, which verifies that EDH is an important criterion for improving the energy performance of residential housing units.

Effect of thermoelectric subcooling on COP and energy consumption of a propane heat pump

The building sector has an important impact on the environment, being responsible for 30 % of the total greenhouse gas emissions. Knowing that the energy consumption devoted to HVAC systems accounts for 50 % of the total energy consumption of buildings, it is paramount to develop environmentally friendly technologies able to provide green space heating to the building sector. To that purpose, this manuscript presents a computational study on propane vapor compression heat pumps which include thermoelectric subcooling to boost their operation. The combination of these technologies has been proven in the past to be very beneficial for refrigeration systems and this study concludes for the first time that propane heat pumps can highly benefit from thermoelectric subcooling. The widely conducted research includes the following parameters: ambient temperatures from −20 to 15 °C, voltage supplies to the thermoelectric modules from 0.5 to 10 VDC, number of thermoelectric subcooling blocks from 1 to 8 and two water inlet temperatures, 40 and 55 °C to study their influence on heating capacity, compressor and thermoelectric power consumptions, subcooling degree, propane mass flow, compressor capacity, COP, energy consumption and SCOP of the combined heat pump. The obtained results are very conclusive, COP enhancements up to 12.29 % are achieved when a thermoelectric subcooler with 16 modules is included in a propane heat pump already provided with an internal heat exchanger for an ambient temperature of −20 °C and a water inlet temperature of 55 °C. Additionally, improvements in Seasonal COP up to 9.98 % are achieved if the above-mentioned technologies integration between a vapor compression heat pump and a thermoelectric subcooler substitutes a conventional propane heat pump with an internal heat exchanger for space heating a single-story two-family house.

Novel modular PCM wall board for building heating energy efficiency: Material preparation, manufacture and dynamic thermal testing

With the comprehensive implementation of China’s “dual carbon” goals, the building heating sector, characterized by high energy consumption and emissions, urgently requires low-carbon transformation. However, energy-saving measures for plateau regions are scarce and face challenges due to harsh climates. This study proposes an innovative heating method utilizing composite phase change materials. A new modular phase change thermal storage electric heating terminal integrated with a photovoltaic thermal system has been designed to address issues of high building energy consumption and problems related to heating system freezing and leakage in the Tibetan Plateau (Qinghai-Xizang Plateau). Laboratory tests were conducted on six groups of samples with different structures and placements to examine their heat storage and release characteristics. Results indicate: The system’s temperature stabilization time totals 14.6 h; Horizontally placing the terminal reduces melting time by up to 2.7 h, enhancing heat storage performance; Structure three shortens solidification time by up to 2.2 h compared to structure one, improving heat release performance; Vertically placed terminals have better heat release performance than horizontally placed ones, resulting in more effective indoor heating. This study proposes a modular design for phase change heat storage electric heating walls, simplifying installation and maintenance while maintaining aesthetic appeal. Detailed temperature measurements of different wall surfaces revealed excellent cyclic heat storage and release performance. The developed phase change heat storage electric heating terminal is expected to significantly reduce heating energy consumption in the Tibetan Plateau (Qinghai-Xizang Plateau), enhancing building energy efficiency and providing valuable insights for further applications of phase change materials in building design.

The technological assessment of green buildings using artificial neural networks

This study aims to construct a comprehensive evaluation model for efficiently assessing appropriate technologies within green buildings. Initially, an Internet of Things (IoT)-based environmental monitoring system is devised and implemented to collect real-time environmental parameters both inside and outside the building. To evaluate the technical suitability of green buildings, this study employs a multifaceted approach encompassing various criteria, including energy efficiency, environmental impact, economic benefits, user comfort, and sustainability. Specifically, it involves real-time monitoring of environmental parameters, analysis of energy consumption data, and indoor environmental quality indicators derived from user satisfaction surveys. Subsequently, a Multi-Layer Perceptron (MLP) is selected as a conventional artificial neural network (ANN) model, while a Long Short-Term Memory (LSTM) model is chosen as an advanced recurrent neural network model in the realm of deep learning. These models are utilized to process and explore the collected data and assess the technical suitability of green buildings. The dataset comprises physical quantities such as temperature, humidity, and light intensity, as well as economic indicators including energy efficiency and building operating costs. Furthermore, the assessment process considers the building's life cycle assessment and indoor environmental quality factors such as health, comfort, and safety. By incorporating these comprehensive criteria, a holistic evaluation of green building technologies is achieved, ensuring the selected technologies' suitability and effectiveness. The model prediction results demonstrate that the proposed hybrid evaluation model exhibits high accuracy and robust stability in predicting building environmental parameters. For instance, the Root Mean Square Error (RMSE) for temperature prediction is 1.2 °C, the Mean Absolute Error (MAE) is 0.9 °C, and the determination coefficient (R2) reaches 0.95. Similarly, for humidity prediction, the RMSE, MAE, and R2 are 3.5 %, 2.8 %, and 0.88. Compared to the traditional MLP and LSTM models alone, the proposed hybrid model shows significant improvements in predicting building energy consumption, with approximately 15 % and 12 % reductions in RMSE and MAE, respectively, and an increase in R2 values of approximately 7 percentage points. These findings indicate that by amalgamation of the IoT and ANNs, this study successfully establishes a comprehensive model for accurately assessing technologies suitable for green buildings. This approach offers a novel perspective and methodology for the design and evaluation of green buildings.

On the Role of the Building Envelope on the Urban Heat Island Mitigation and Building Energy Performance in Mediterranean Cities: A Case Study in Southern Italy

The urban heat island (UHI) effect is one of the largest climate-related issues concerning our cities due to the localized temperature increase in highly urbanized areas. This paper aims to investigate the impact of UHI mitigation techniques in promoting climate resilience, by reducing urban air temperatures and cooling energy consumption in buildings. To this end, four mitigation solutions regarding the building envelope—green roofs, green walls, cool roofs, and cool walls—were investigated for the city of Bari in Southern Italy and compared with the current baseline scenario. Hence, five scenarios were simulated—using the ENVI-met microclimate software—during three representative summer days, and the resulting microclimate changes were assessed. Based on these analyses, new climate files—one for each scenario—were generated and used as input to run energy simulations in EnergyPlus to estimate the building cooling consumption. Coupling the microclimate and the consumption outcomes, the mitigation strategies were evaluated from both an urban and building point of view. The study shows that urban characteristics, mainly geometry and materials, are crucial for the UHI phenomenon. All the applied technologies seem to be effective. However, green walls proved to be more efficient in reducing outdoor temperatures (1 °C reduction in daily temperatures), while cool walls performed better in reducing cooling energy consumption, with an overall saving of 6% compared to the current scenario.

Thermo-economic assessments on building heating by a sewage source heat pump coupled with heat storage system

To enhance the economic feasibility of building heating systems, phase change heat storage materials are often utilized to utilize renewable energy and address system peak loads. This article presents an innovative method of integrating a sewage source heat pump with a heat storage device. Upon an industrial building in Xilinhot as a case study, numerical models for the heat accumulator coupled with the energy consumption of buildings are established, taking into account dynamic hourly loads and meteorological conditions. Through a comprehensive analysis, the thermophysical properties of the heat accumulator as well as the economic implications of the multi-energy complementary heating system are investigated. Results demonstrate that the complete melting time for a 95 % filling rate is significantly reduced, 87.11 % shorter than that of pure phase change material, achieving the highest heat storage efficiency. Furthermore, the phase change storage device with a 75 % filling rate had the shortest investment payback period, requiring only 6 years. These findings have significant implications for guiding green renovation projects in building heating systems.

Fabrication of passive cooling fabric as thermal management curtain for building energy-saving

In the past years, a great deal of attention has been paid to passive cooling envelope materials or smart windows to cope with the increase in building energy consumption due to global warming. However, combining curtains with passive cooling could enable on-demand thermal management based on its dynamically adjustable characteristics. Herein, a superhydrophobic passive cooling cotton fabric with low thermal conductivity (0.0342 W/mK), high solar reflectivity (0.9280) and high infrared emissivity (0.9698) was obtained by wrapping the cotton fabric with a porous SiO2/poly(vinylidene fluoride-hexafluoropropylene) composite coating via solvent exchange phase separation and sanding. The superhydrophobic passive cooling fabrics realized an average of 10.3 °C cooling during the daytime and showed impressive passive cooling performance relative to the pristine cotton. Notably, the superhydrophobic passive cooling fabric demonstrated superior daytime cooling and nighttime insulation performance during outdoor testing and energy consumption simulations compared to commercial curtains. Therefore, superhydrophobic passive cooling cotton fabrics as curtains allow for reducing the energy consumption in building thermal management and broadening the practical application of radiative cooling materials.

Optimizing Window Configurations for Energy-Efficient Buildings with Aluminum Alloy Frames and Helium-Filled Insulating Glazing

This research investigates building energy consumption in the Fujian region of China, characterized by warm winters and hot summers. The study focuses on window configurations and their impact on heat exchange and solar gain management. Initially examining three aluminum alloy window frames, the study utilizes the Multi-Quality Metric Calculator (MQMC) software V1 to assess the benefits of filled insulating glass. The reference values for the heat transfer coefficient, visible transmittance, and sun shading coefficient are established. Subsequently, Ecotect software V5.6 is employed to conduct a comprehensive year-round energy consumption simulation analysis, identifying an optimal window layout tailored to Fujian’s climate. In the Fuzhou simulation, aluminum–plastic co-extruded windows exhibit the lowest cooling energy consumption, while aluminum alloy windows have the highest. Summer cooling energy consumption, comprising about 75% of the total annual energy usage in hot summer and warm winter regions, significantly influences overall energy consumption. Windows made of aluminum–plastic co-extruded material with superior thermal insulation qualities can greatly reduce building energy consumption. The results contribute valuable insights to sustainable building practices and energy-conscious designs in regions characterized by warm winters and hot summers.

Energy consumption prediction and energy-saving suggestions of public buildings based on machine learning

Energy consumption prediction can help the government to formulate building energy consumption quotas and buildings energy consumption correlation analysis can provide a clear direction for buildings energy conservation and renovation. In the study, the energy consumption data of four types of public buildings in Guangxi in the four quarters of 2021 based on five machine learning models was trained and predicted. The energy consumption data was analyzed for correlation based on two methods of influencing factor correlation analysis. Finally, based on the prediction model and correlation analysis results, suggestions for energy conservation and renovation were given to eight buildings. The results showed that compared to other models, CNN had higher prediction accuracy, and the fitting regression index was generally above 0.95. The season had little impact on the characteristics correlation, but the building type had a significant impact. The electricity consumption had a high correlation with the energy consumption of all types of buildings. Through case analysis, it was concluded that some buildings did not need energy-saving renovation for the time being, while others require multiple phases of energy reduction over several quarters to meet the requirements.

Gaussian-based plug load profile prediction in non-residential buildings archetype

This paper presents an innovative approach to addressing the prevalent challenge of simulation uncertainty in urban building energy modeling (UBEM), focusing on accurately determining occupant-related input parameters. Traditional UBEM methods typically rely on standard schedules to create archetype models, which often fail to reflect the variability observed in real-world scenarios. To overcome this limitation, this research introduces a novel framework for generating electricity use profiles in institutional building archetypes across various climate zones. This framework integrates k-means clustering with Gaussian processes, effectively incorporating uncertainties into the prediction models. The evaluation of this stochastic model suggests that the methodology can give acceptable predictions on the electricity consumption of institutional buildings. The model demonstrates robust predictive capabilities, achieving a CVRMSE as low as 11% on weekdays and 8.7% on weekends, reflecting its strong predictive performance. However, its performance varies among different clusters and time periods, with specific clusters displaying more significant predictive inaccuracies at particular times. These results emphasize the importance of fine-tuning models and offer opportunities for improvement in predicting urban building energy consumption. This can be achieved by incorporating sensor-derived data to develop more detailed building profiles that include variable electricity usage patterns. This methodology has been integrated into a UBEM tool, enabling the generation of more realistic electricity load profiles.

МОДЕЛЮВАННЯ ЕНЕРГОЕФЕКТИВНОСТІ ЖИТЛОВОЇ БУДІВЛІ ЗА УМОВ РІЗНИХ ДЖЕРЕЛ ТЕПЛОВОЇ ЕНЕРГІЇ

The paper presents the results of modeling the process of energy consumption in public, residential, and commercial buildings as a result of the use of various sources of thermal energy. Buildings with such energy sources as: a) a low-temperature gas boiler with a capacity of up to 120 kW for the needs of heat supply of a residential building and freon air conditioning systems for the needs of cooling the building; b) a gas condensing boiler with a thermal capacity of up to 120 kW with a temperature regime of 55/45°C for heat supply and freon air conditioning systems for cooling; c) reversible heat pumping unit of the “ground-water” type with a temperature regime of 35/28°C for the needs of the heating and cooling system and a reversible heat pumping machine with a regime of 55/45°C for the needs of hot water supply; d) a reversible air-to-air heat pump for heating and cooling systems and electric boilers for hot water supply; e) a biomass solid fuel boiler with manual fuel loading with a heat output of more than 100 kW for heat supply and freon systems for cooling; f) a fuel pellet boiler with automatic mechanized fuel loading with a heat output of more than 100 kW for building heating and cooling and freon systems for cooling; g) centralized heating system of the building. The results of calculations of the specific primary energy consumption and specific greenhouse gas emissions for each of the above heat sources are presented. It is established that biomass boilers have the lowest values of primary energy consumption and specific greenhouse gas emissions. The lowest efficiency is achieved by a district heating system with a centralized energy source. The modeling was conducted for the climatic conditions of Vinnytsia. At the same time, the disadvantage of using solid fuel boilers is the limitation of their use in densely populated areas, which is explained by the complexity of flue gas cleaning and regular biomass supply. Therefore, it has been determined that the most efficient source of thermal energy for buildings of various types to achieve the standardized energy efficiency indicators is a ground-to-water heat pump system. This installation, along with providing buildings with thermal energy, allows for cooling in the warm season, operating in reverse mode.

Study on multi-band spectral regulation performance of single-layer thermochromic coatings based on VO2 core-shell particles for building energy conservation

The spectral regulation performance of smart windows significantly impacts building energy consumption. Compared to thermochromic coatings that modulate only the sunlight band, those capable of multi-band modulation-including both sunlight and mid-to-far infrared bands-have the potential to further reduce energy consumption in buildings. The thermochromic coating based on multi-layer structures with multi-band modulation ability reported so far is unsuitable for practical application due to its complex preparation process and high cost. This study proposed a single-layer smart window coating utilizing core@VO2 particles to achieve multi-band modulation. This single-layer coating offers the advantages of simple preparation and convenient construction. We investigated the influence of parameters such as the shell-to-core ratio, particle volume fraction, and refractive index of the substrate on the spectral radiative properties using the FDTD method. Additionally, the impacts of variations in these parameters on energy consumption and carbon dioxide emissions were analyzed using EnergyPlus. The simulation results indicated that the core@VO2 nanoparticle coating possessed a maximum solar modulation ability of 27.6%, luminous transmittance of 48.15%, and maximum emissivity modulation ability of 16.7%. Compared with traditional low-e coatings, the maximum energy-saving efficiency increased by 7.36%. This study provides valuable insights for enhancing the energy efficiency of thermochromic smart window coatings.

Novel STAttention GraphWaveNet model for residential household appliance prediction and energy structure optimization

The multifaceted challenge of carbon dioxide (CO2) emissions during building operations, construction, and material production perpetuates energy shortages and climate adversities. Urgent imperatives underscore the need for effective energy reduction and carbon mitigation, driving the building sector toward a paradigm shift in clean, low-carbon evolution. However, the complex multidimensional and nonlinear characteristics of influencing factors of building energy consumption make it difficult in precisely understanding the spatial and temporal relationships between the features in the predictive modeling of buildings. Therefore, a novel Graph Wavenet (GWN) based on the spatio-temporal attention fusion mechanism (STA-GWN) is proposed for spatio-temporal graph prediction modeling of structures, which can capture hidden spatial relationships using an adaptive dependency matrix. To overcome the drawbacks of standard predefined adjacency matrices and their inability to capture faraway dependencies, a spatio-temporal attention fusion mechanism is introduced to extract latent spatio-temporal features dynamically. By combining extracted features, building energy consumption can be predicted more precisely. Moreover, the proposed model becomes more interpretable, making it easier to reveal how spatio-temporal features relate to building energy consumption. Lastly, the proposed method is applied to energy conservation and emission reduction in the building industry. A predictive model for electrical energy consumption during two public datasets with an operational phase of buildings is established to analyze and optimize energy utilization in residential structures that rely on electricity. The experimental results demonstrate that the STA-GWN model surpasses other deep learning methods in terms of prediction accuracy and robustness. Moreover, the proposed model can offer optimal solutions for building energy processes, reducing approximately 201.44 kg (Kg) and 64.08 Kg of CO2 emissions in the appliances energy prediction dataset and the individual-household-electric-power-consumption (IHEPC) dataset, respectively.