Total Building Energy Consumption Research Articles

A Janus Spectrally Selective Glazing Toward All-Season Energy-Efficient Windows.

Windows offer the most promising avenue for mitigating energy consumption and reducing greenhouse gas emissions. However, the balance between comfortable natural lighting and all-season energy savings is often neglected in extensive explorations of energy-efficient windows. Herein, a Janus glazing is proposed that enables the switch of passive radiative cooling and heating under the precondition of conveying sufficient natural light. Measurement results indicate that the Janus window maintains a visible transmittance of 0.47, while possesses a near-infrared (NIR) reflectivity/absorptivity of 0.75/0.71 and a mid-infrared (MIR) emissivity of 0.94/0.13 for the cooling and heating modes, respectively. As demonstrated by the outdoor test, the Janus window realizes a reduction of 7.1°C for room cooling and an increase of 0.4°C for room heating compared with commercial low-e window, potentially conserving 13%-53% of the total building energy consumption across China. Meanwhile, attributed to the photothermal effect, the Janus window can elevate the surface temperature by 6.1°C compared with the low-e window, which can effectively reduce fogging occurrences on the window surface for ensuring sunlight entrance in the cold-weather conditions. This strategy offers novel prospects for enhancing energy efficiency in diverse applications, including architectural windows, greenhouse cultivation, photovoltaic generation, etc.

Full-Scale Comparison of Two Envelope Systems for Lightweight Wooden Framing in Cold Climates

Residential homes and apartments’ cooling and heating needs account for 63% of total building energy consumption. Improvements in the properties of building envelopes are among the best ways to reduce their energy consumption. The project’s general objective was to compare the performance of externally insulated and traditional envelopes of light wooden frame buildings at full scale. Two houses were constructed and equipped with relative humidity sensors and temperature probes to assess the physical properties of the building envelope. The first house was built according to the conventional method (insulation between the studs), and the second house was built according to the method with the insulation outside the wall (also known as the perfect wall). The results showed that external insulation effectively mitigates internal condensation risks by relocating dew points to the exterior surface, thereby enhancing structural durability and thermal stability. Thermographic imaging confirmed reduced thermal bridging and improved thermal performance in the externally insulated walls. Overall, this study supports, with a full-scale experiment, the adoption of external insulation as a viable strategy for enhancing energy efficiency, thermal comfort, and durability in residential buildings.

A study on the enhancement of energy efficiency and indoor environment through the integration of solar photovoltaic modules in daylighting louver systems

The global energy demand is predicted to increase significantly, with a strong link between energy consumption and CO2 emissions. Lighting energy accounts for a substantial proportion of total energy consumption in buildings, with the potential to be reduced using daylighting louvers. Despite some drawbacks, integrating solar photovoltaic modules with louvers could enhance energy efficiency while addressing the increasing demand for renewable energy systems in new buildings. Therefore, this study explores the potential benefits of integrating solar photovoltaic (PV) modules into a daylighting louver system to simultaneously reduce lighting, cooling, and heating loads and generate solar power. The performance of the proposed louver system was experimentally compared to a conventional building-integrated photovoltaic (BIPV) system installed on a window. The daylighting louver system demonstrated significant improvements in indoor illumination and occupants’ experience compared to the BIPV system. Furthermore, the indoor air temperature in the space with the louver system increased by about 5 degrees compared to the BIPV system, indicating its contribution to heating load reduction. The power generation performance of the louver system reached up to 65 % of the BIPV system, with a total cumulative electricity generation of 64 %. The results suggest that the daylighting louver system can be expanded to enhance its efficiency and address the increasing demand for renewable energy system installations in new buildings. Future studies should investigate the potential of 2-axis or 3-axis louvers to further improve the system’s efficiency.

Circuit categorization approach of office building energy consumption based on data features for energy-saving diagnosis

Energy-saving in office buildings is crucial. Research on data-driven diagnostics of building energy consumption is pivotal. The emergence and development of itemized electricity platforms have expanded the scope of diagnosis from total building energy consumption to individual electrical equipment. However current studies rarely address the characteristics of sub-circuits. This paper highlights the importance of recognizing the features of electrical equipment sub-circuits based on historical energy consumption data by examining various aspects of energy use in office buildings, including electrical consumption disaggregation, equipment operational strategies, sub-item consumption proportion, and sub-circuit composition. A circuit categorization approach in office buildings by features analysis of historical data is innovatively proposed. Operational conditions, time series stationarity, and correlations with factors affecting energy consumption are considered in historical data feature analysis. The method categorizes the electric circuits into 5 categories with typical features based on the ADF-KPSS co-test and Spearman correlation analysis. The rationality and validity of the circuit categorization method were verified with actual building data in case studies. On this basis, an interpretable energy consumption anomaly diagnosis method based on the categorization results is proposed. The circuit categorization approach explores how to further investigate the typical features of sub-circuits, and provides new directions for subsequent building operation and maintenance(O&M) research, including energy consumption diagnostics. Additionally, it offers decision support for building managers for O&M evaluation from an interpretable perspective.

Building energy consumption analysis and measures: a case study from an administration building in Chengdu, China

With the peak of carbon dioxide emissions and carbon neutrality, China is placing greater emphasis on energy expenditure. Office buildings occupy a prominent position in building energy consumption, which is one of the main energy consumption areas. Taking an administration building in Chengdu as an example, this article simulates the building energy consumption based on Design Builder software, examines the variables influencing energy consumption, and suggests energy-saving strategies combined with fresh ideas for sustainable architectural design. The results showed that the modeling building was a high-energy-consuming building, with an energy consumption of 724,857.59 kWh, and a unit area energy consumption of 288.17 kWh/m2 in Chengdu. For energy conservation and emission reduction, this article proposes the following three energy-saving measures. The first is to apply heat recovery technology for air conditioning systems. The second is photovoltaic glass, which provides partial electricity demand for buildings and reduces dependence on traditional energy sources. The third is roof greening, which utilizes the plants to purify the air and beautify the environment. The results showed that the heat recovery technology in air conditioning systems reduced the total energy consumption of buildings from 642144.04 kWh/m2 to 502937.83 kWh/m2, photovoltaic glass reduced 552243.87 kWh/m2, and roof greening reduced to 635947.35 kWh/m2. All of these have good energy-saving and emission reduction effects. The above three strategies not only help reduce building energy consumption, but also provide substantial support for China to achieve carbon neutrality.

A turbulent flow topology optimization method for diverging tee resistance reduction

The resistance of local components in piping and duct systems significantly affects the energy consumption of fans and pumps, accounting for 40–60 % of the total building energy consumption. In this paper, an improved topology optimization method for variable density turbulent flow is proposed to design a low-resistance diverging tee structure in piping and duct systems. The advantages of the improved optimization method over the traditional method are analyzed using finite element numerical simulation, and the applicability of the proposed method is verified in the Reynolds number range of 0.6 × 105–2.6 × 105. In order to ensure the resistance reduction effect of the topology diverging tee under multiple operating conditions, the local resistance coefficients under nine flow ratios were simulated and calculated using the finite volume method. The results show that the topology diverging tee can significantly reduce the resistance. Compared with the traditional tee, the maximum resistance reduction rates in the straight-through direction and branch direction reached 63 % and 59 %, respectively. In addition, the intensity of secondary flow in five downstream sections was analyzed based on the dimensionless parameter Se. Finally, the actual resistance reduction effect of the topology diverging tee was experimentally verified. The optimization method and analysis results proposed in this study can provide a reference for the optimal design of pipelines with low resistance in energy-saving operation of buildings and in engineering fields such as petroleum and chemical industries.

Multi-objective optimization of rural residential envelopes in cold regions of China based on performance and economic efficiency

Building envelope renovation solutions are critical to building performance and post-renovation economics. Building renovation is easier to carry out if the impacts of building envelope renovation solutions on building performance and post-renovation economic efficiency can be foreseen and a more sustainable and efficient renovation design can be achieved. This paper explores the optimal design of building envelope renovation using genetic optimization algorithms and statistical analysis methods, taking the performance of the renovated building and the economic efficiency of the renovation solution as the starting points. In Qingdao, a cold region of China, a survey was carried out on typical rural areas in seven regions. The selected design variables include the external wall and roof insulation material type(TWall, TRoof), external wall and roof insulation thickness(δWall, δRoof), type of window construction(TWc), and area radio of the window to the wall(WWR). Minimization of total building energy consumption(E) and renovation cost(COSTRE) and after renovation maximization of the combined incremental cost-benefit ratio over a 20-year life cycle(CICBR20-year life-cycle), effective natural daylighting illuminance(UDI), and percentage of time spent in indoor comfort(PTC) were considered in the optimization of the envelope. The results show that in cold regions, different envelope renovation solutions affect the optimization objectives to different degrees; changing the south-facing window-to-wall ratio(S_WWR) has a bigger effect on E, PTC, and UDI; and choosing different TRoof has a bigger effect on COSTRE and CICBR20-year life-cycle. Renovation of the selected typical rural residence with the optimal solution results in an energy-saving rate(Re) of 53.08 %, an increase of 940.86 h/year in annual indoor comfort hours(HIC) and 377.00 h/year in annual effective natural lighting hours(HUDI).

Load prediction and energy efficiency improvement of steelmaking waste heat centralized heating systems under mild climate in China

HVAC energy consumption accounts for more than 50 % of the total building energy consumption globally and using industrial waste heat has huge potential for energy savings in central heating systems. Under the background of the use of renewable energy and the gradual rise of central heating in mild climate areas in China, it is worth paying attention to the problem of excessive energy consumption caused by the inaccurate load prediction of central heating systems when the ambient temperature changes. L City, Guizhou Province, is the first city with central heating in southern China. The temperature variation during winter in L City can manifest the climatic characteristics of a mild region. Therefore, based on the operational data of the steel waste heat central heating system in L City, Guizhou Province, China, during the heating season of 2022–2023, this study discusses the load prediction and energy-saving optimization strategy of the central heating system in a mild climate. SketchUp was used to conduct 3D modeling of the actual buildings in the heating area and TRNSYS was imported to simulate the system load. The difference between the heating load forecast and the actual operating data was analyzed in detail by using the calculation results. Based on the simulation results, the waste heat utilization strategy was adjusted and the influence of different heating schemes on the pump energy consumption under different load demands was discussed. The results reveal that based on the temperature change rule, the accurate load prediction can lead to a 28.64 % saving of the system energy. Concerning system energy consumption, by adjusting the water flow and choosing the large and small pump system, the energy saving amounts to 39.48 % compared with the traditional single-pump system. Meanwhile, in the transition season when the heating demand is less than 20 MW, the adjusted heating scheme can achieve a 38.5 % saving based on the constant flow scheme and a 5.4 % saving based on the constant temperature difference scheme. This article provides a scientific energy-saving solution for heating in mild climates using industrial waste heat, not only reducing energy consumption but also providing an important reference for the energy-saving renovation of heating systems in similar areas.

The impact of urban dry island on building energy consumption is overlooked compared to urban heat island in cold climate

A large number of literature reveals the impact of urban heat island on building energy consumption, however, the urban dry island impact on the energy demand is very limited. This study aimed to determine the urban–rural disparities in temperature (ΔT) and relative humidity (ΔRH) on sensible and latent heat loads (SHL, LHL) in a large city belonging to the cold climate zone of China. The results showed that apparent ΔT and ΔRH existed between the urban and rural areas, with higher T and lower RH in the urban area compared with those in the rural counterpart. The ΔT of the heating period (1.37 ℃) is far higher than that of the cooling period (0.45 ℃), whereas the ΔRH is almost same in the heating and cooling periods (−9 % vs −8 %). Due to the effect of ΔT, the urban SHL of office building was averagely lower 15.1 % than that in the rural area during the heating period, but only higher 4.6 % in the urban area compared with the rural area in the cooling period. By contrast, the decrease extent of LHL of office building between urban and rural areas in the cooling period (58.7 %) extremely exceeds the increase of LHL in the heating period (6.7 %) due to the ΔRH impact. Negative significant relationships between ΔT and the change of SHL from urban to rural areas, as well as between ΔRH and the change of LHL were found during the heating period, but being positive significant relationships during the cooling period. This study reveals that, in the cold climate zone, the LHL has large contribution to the total energy consumption of buildings, especially the LHL during the cooling period in urban area is much lower than that of the surrounding rural area, highlighting the need to fully consider the LHL in the design and operation of air-conditioning system. In addition, this study shows the potential for improving energy efficiency of other building types or other cities in the cold climate zone by considering the UDI effect.

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.

Design, preparation, and property analysis of metal/dielectric multilayer film with wavelength selectivity

Metal/dielectric multilayer films have important applications in energy-saving glass, stealth materials, solar energy utilization and other fields. In the current study, the thickness of each layer of TiO2/Ag/TiO2/Ag/TiO2 film is optimized. The effects of the number of metal/dielectric multilayer films and the incident light angle on their optical properties were investigated. The TiO2/Ag/TiO2/Ag/TiO2 film was prepared by electron beam evaporation coating technology, and their reflectance and transmittance were measured. The measurement results show that the visible light transmittance (380–780 nm) of the film can achieve 68.7%, and the infrared reflectance (780–2500 nm) can reach 95.9%. Compared with the traditional dielectric/metal/dielectric three-layer film, the visible light transmittance of the film is higher, and the solar infrared reflectance is greatly improved. In the solar radiation band (280–2500 nm), the average error between the experimental reflectance and transmittance and the theoretical prediction results is less than 0.03. The distribution of electric and magnetic fields inside the film was simulated by finite-difference time-domain method. The simulation results show that the high visible light transmittance is due to the interference resonance of electromagnetic waves inside the film. Taking Shanghai as an example, under our calculation conditions, compared with ordinary SiO2 glass, TiO2/Ag/TiO2/Ag/TiO2 film can reduce the total energy consumption of buildings by 14.3% and refrigeration energy consumption by 17.2%.

Modelling building HVAC control strategies using a deep reinforcement learning approach

Heating, ventilation, and air-conditioning (HVAC) systems are responsible for a considerable proportion of total building energy consumption but are also vital for improved indoor temperature comfort, indoor air quality and well-being of building occupants. Thus, developing control strategies for HVAC systems is critical for the total life cycle of any building projects. Particularly, HVAC and building operations are not stationary but are filled with fuelled by environmental dynamisms and unexpected disruptions such as users' activities, weather conditions, occupancy rate, and operation of machinery and systems. This research aims to develop and propose a strategic control learning framework for HVAC systems using the deep reinforcement learning (DRL) approach. The results show that the proposed Phasic Policy Gradient (PPG) based method is more adaptive to changes in real building's environments. Notably, PPG performs better and more reliable than the conventional method for HVAC control optimization with about 2-14% in energy consumption reduction and indoor temperature comfort enhancement, along with a 66% faster convergence rate. Overall, our findings demonstrate that our proposed DRL approach is less resource intensive and much easier than the conventional approach in deriving solutions for HVAC control optimization driven by energy efficiency and indoor temperature comfort.

A comprehensive investigation of zeolite/polyurea cooling coating on concrete for building energy conservation

Passive daytime radiative cooling (PDRC) materials are beneficial to energy conservation and emission reduction of buildings. Currently, the design of PDRC coatings for exterior walls and roofs of buildings places excessive emphasis on improving the solar reflectance (Rs) and infrared emissivity (Ei) of the coating, while neglecting other important properties of building coatings, such as adhesion, waterproofness, corrosion resistance, and weather resistance. To address these deficiencies, this work developed a (calcined zeolite)/polyurea (CZ/PU) PDRC coating with excellent comprehensive performance for building exterior walls and roofs, using CZ and PU as raw materials. The CZ/PU coating is prepared using a method that is completely consistent with existing paint production and construction techniques, and can be applied to large-area building surfaces at scale. The Rs of the CZ/PU coating is 97.4 %, and the Ei is 94.4 %. Under direct sunlight in summer, the CZ/PU coating achieved significant PDRC effects under both adiabatic conditions (using test equipment to reduce heat conduction and convection) and natural conditions. The corresponding radiative cooling temperatures are 14.9 °C and 4.4 °C, respectively. In addition, the CZ/PU coating also exhibits excellent water resistance, reducing the capillary water absorption rate of a cement block by 78 %. In addition, the adhesion strength of the CZ/PU coating to the substrate reached the highest rating (rating 0). In particular, the optical properties, radiative cooling function, water absorption, and adhesion force of the CZ/PU coating showed ultra high stability in ultraviolet aging experiments. Energy consumption simulations show that the average energy saving efficiency of the CZ/PU coating on the annual total building energy consumption of ten typical Chinese cities is as high as 13.3 %. The CZ/PU-based coating developed in this work comprehensively considers various issues that may be faced in the practical application of radiative cooling architectural exterior wall coatings, providing an experimental foundation for promoting the application of radiative cooling coatings in buildings.

Nearly Zero-Energy Building Load Forecasts through the Competition of Four Machine Learning Techniques

Heating, ventilation and air conditioning (HVAC) systems account for approximately 50% of the total energy consumption in buildings. Advanced control and optimal operation, seen as key technologies in reducing the energy consumption of HVAC systems, indispensably rely on an accurate prediction of the building’s heating/cooling load. Therefore, the goal of this research is to develop a model capable of making such accurate predictions. To streamline the process, this study employs sensitivity and correlation analysis for feature selection, thereby eliminating redundant parameters, and addressing distortion problems caused by multicollinearity among input parameters. Four model identification methods including multivariate polynomial regression (MPR), support vector regression (SVR), multilayer perceptron (MLP), and extreme gradient boosting (XGBoost) are implemented in parallel to extract value from diverse building datasets. These models are trained and selected autonomously based on statistical performance criteria. The prediction models were deployed in a nearly zero-energy office building, and the impacts of feature selection, training set size, and real-world uncertainty factors were analyzed and compared. The results showed that feature selection considerably improved prediction accuracy while reducing model dimensionality. The research also recognized that prediction accuracy during model deployment can be influenced significantly by factors like personnel mobility during holidays and weather forecast uncertainties. Additionally, for nearly zero-energy buildings, the thermal inertia of the building itself can considerably impact prediction accuracy in certain scenarios.

A mechanical–optical coupling design on solar and thermal radiation modulation for thermoregulation

A multi-layer structure was designed to achieve mechanical deformation-induced solar and thermal radiation synchronous modulation, which can achieve dynamic thermoregulation and save the total energy consumption in buildings.

An energy-saving design method for residential building group based on convolutional neural network

Current building energy saving methods mainly focus on the individual building, seldom focus on the building group. Different from the energy saving design method which takes the individual building as the object, the energy saving design of building group also needs to consider the influence of microclimate on building energy consumption, because microclimate is the boundary condition for building energy consumption calculation. The purpose of this study is to investigate the influence of the building group form and geometric factors on the energy consumption of residential buildings in Beijing. First, this study developed a complex plane generator based on convolutional neural network (CNN), and used the generator to extract and classify the plane of residential buildings in Beijing, and generate three standard residential building models. Secondly, the microclimate conditions of the three standard models in summer and winter were calculated by ENVI-met, and the energy consumption of individual building with different geometric form was calculated by DesignBuilder. Based on the above simulation results, the influence of group forms and geometric factors on microclimate and the influence of geometric form on energy consumption of individual building were quantified, and the influence law of group forms and geometric factors on energy consumption of buildings was revealed. The obtained law can be used to quickly estimate the change of total building energy consumption when the group form or geometric factor changes at the initial stage of the design of residential buildings.

Problems of Building Energy Consumption in Rural Schools in Linzhi, Tibet

The energy-saving research of school buildings in villages and towns in the severe cold areas of Linzhi Township has not yet been widely carried out. The energy consumption of schools in villages and towns in the severe cold areas of Linzhi is generally high, and the heating energy consumption in winter accounts for a large proportion of the energy consumption of school buildings. With the promulgation and implementation of energy-saving design standards for public buildings in schools in large and medium-sized cities, energy-saving activities have been carried out. In the severe cold area of Linzhi, there are a large number of buildings in villages and towns, with primary schools in each village, secondary schools and central primary schools in each township. The total energy consumption of village and town school buildings accounts for the majority of the total energy consumption of village and town public buildings. From this, it can be seen that studying the characteristics of village and town school buildings in the severe cold area of Linzhi and researching energy-saving design strategies suitable for their own characteristics based on the characteristics of village and town school buildings in the severe cold area are of great significance for the promotion and application of clean energy in schools in the Linzhi area.

Impact of air-conditioning usage behavior of student groups on air-conditioning load simulation in university dormitories

During summers, air-conditioning (AC) accounts for a large proportion of the total energy consumption of university dormitory buildings, which is influenced by the occupant behavior. To quantitatively analyze the impact of the AC usage behavior of student groups on AC loads, this study regarded students as heterogeneous individuals, and classified them into four categories by taking group identity and individual preferred temperature as classification indicators, as follows: (i) low-group identity and low-preferred temperature, (ii) low-group identity and high-preferred temperature, (iii) high-group identity and low-preferred temperature, and (iv) high-group identity and high-preferred temperature. On this basis, a combined model composed of the student groups’ AC usage behavior simulation and the AC load calculation was developed. Results showed that the subject of low-group identity and low-preferred temperature was most sensitive to changes in indoor temperature. On a typical summer day, the AC load simulation results without considering differences in individual behavior increased by 9.7% compared with those considering differences in individual behavior, and the increased rate declined with the rise in outdoor temperature. Additionally, enhancing students’ group identity could significantly reduce AC loads.

Synthesis of model predictive control based on neural network for energy consumption enhancement in building

The problem addressed in this work is the enhancement of energy efficiency in buildings, primarily focused on heating control. The paper highlights the importance of addressing this challenge, given that HVAC systems are responsible for over 60% of total energy consumption in buildings, making them the largest energy consumers in both the residential and nonresidential sectors. This paper presents a methodology for developing a model predictive control (MPC) system based on artificial neural network (ANN) models, with the aim of improving the energy efficiency of buildings. This approach involves the creation of a training dataset using dynamic thermal simulation tools, enabling the learning of the ANN model that is responsible for predicting future states within an MPC optimization loop. Additionally, the implementation leverages advanced technologies such as Field-Programmable Gate Arrays (FPGAs), specifically the PYNQ board, Wi-Fi modules, and MQTT communication to enhance scalability, deployment, and adaptability. The study evaluates the proposed Neural Network Model Predictive Control (NNMPC) strategy implemented on the PYNQ, reporting a substantial reduction of 38.53% in heating energy consumption in buildings compared to a basic On/Off control approach for 24-hour simulation. This outcome underscores the solutions significant potential for energy savings in building heating systems.

HVAC Load Forecasting Based on the CEEMDAN-Conv1D-BiLSTM-AM Model

Heating, ventilation, and air-conditioning (HVAC) systems consume approximately 60% of the total energy consumption in public buildings, and an effective way to reduce HVAC energy consumption is to provide accurate load forecasting. This paper proposes a load forecasting model CEEMDAN-Conv1D-BiLSTM-AM which combines empirical mode decomposition and neural networks. The load data are decomposed into fifteen sub-sequences using complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN). The neural network inputs consist of the decomposition results and five exogenous variables. The neural networks contain a one-dimensional convolutional layer, a BiLSTM layer, and an attention mechanism layer. The Conv1D is employed to extract deep features from each input variable, while BiLSTM and the attention mechanism layer are used to learn the characteristics of the load time series. The five exogenous variables are selected based on the correlation analysis between external factors and load series, and the number of input steps for the model is determined through autocorrelation analysis of the load series. The performance of CEEMDAN-Conv1D-BiLSTM-AM is compared with that of five other models and the results show that the proposed model has a higher prediction accuracy than other models.