Building Load Research Articles

Multi-Scale Building Load Forecasting Without Relying on Weather Forecast Data: A Temporal Convolutional Network, Long Short-Term Memory Network, and Self-Attention Mechanism Approach

Accurate load forecasting is of vital importance for improving the energy utilization efficiency and economic profitability of intelligent buildings. However, load forecasting is restricted in the popularization and application of conventional load forecasting techniques due to the great difficulty in obtaining numerical weather prediction data at the hourly level and the requirement to conduct predictions on multiple time scales. Under the condition of lacking meteorological forecast data, this paper proposes to utilize a temporal convolutional network (TCN) to extract the coupled spatial features among multivariate loads. The reconstructed features are then input into the long short-term memory (LSTM) neural network to achieve the extraction of load time features. Subsequently, the self-attention mechanism is employed to strengthen the model’s ability to extract feature information. Finally, load forecasting is carried out through a fully connected network, and a multi-time scale prediction model for building multivariate loads based on TCN–LSTM–self-attention is constructed. Taking a hospital building as an example, this paper predicts the cooling, heating, and electrical loads of the hospital for the next 1 h, 1 day, and 1 week. The experimental results show that on multiple time scales, the TCN–LSTM–self-attention prediction model proposed in this paper is more accurate than the LSTM, CNN-LSTM, and TCN-LSTM models. Especially in the task of predicting cooling, heating, and electrical loads on a 1-week scale, the model proposed in this paper achieves improvements of 16.58%, 6.77%, and 3.87%, respectively, in the RMSE indicator compared with the TCN-LSTM model.

Energy efficient green building design utlilising renewable energy and low-carbon development technologies

The core issue these days is to reduce carbon dioxide (CO2) emission and prevent the hole in the ozone layer. Numerous emerging environmental crises successfully tackled by coordinated global efforts in the past few years. Despite this, the present climate emergency is a much more serious threat than anything we have ever encountered and requires much more action consequently. Today, more attention is paid on green buildings in the society, which will make the use of sustainable buildings for the entire life cycle a necessity for future generations. Hence, this paper proposes a novel design model of an energy-efficient residential green building with low carbon emissions to maintain the health and enhances the productivity and living standards of inhabitants. Green building technology is utilized to enhance energy efficiency and lower carbon emissions. This design considers green, recyclable, and eco-friendly building materials, which are beneficial for human health and comply with relevant Indian standards and building codes. This building design proposes renewable energy sources (RES) integrated with the power grid, although RES powers most of the load of the green building. The proposed green building design shows effective results, i.e., building energy consumption has reduced by 50.54%, total energy consumption cost has reduced by 57.41%, and CO2 emission per month has reduced by 50.54%. In addition, stormwater-harvesting system is proposed to collect 54322.23 litres of rainwater annually, which helps in water conservation and contributes to improving the groundwater level. The proposed solid waste management plan has contributed to the achievement of regional and national Sustainable Development Goals (SDGs). Finally, there are some suggestions to promote the use of green buildings for sustainable development.

Determination of estimated electrical loads of charging infrastructure for electric vehicles integrated into electrical installations of residential and public buildings

RELEVANCE. The research aims to improve the regulatory framework governing the procedure for determining the estimated load of public buildings when integrating charging infrastructure for electric vehicles into the electrical installations of these buildings. THE PURPOSE. Determination of the schedule of electricity consumption, the coefficient of simultaneity and non-coincidence of maximums of the charging infrastructure for electric vehicles, with subsequent development of proposals for updating SP 256.1325800.2016 "Electrical installations of residential and public buildings. Design and installation rules" in terms of the methodology for determining the estimated load of public buildings when integrating charging infrastructure for electric vehicles into the electrical installations of the said buildings. METHODS. In achieving this goal, experimental, mathematical and statistical methods were used. RESULTS. A methodology for determining the coefficients of simultaneity and non-coincidence of maximums of electric vehicle charging stations has been developed, and their numerical values have been obtained depending on the type, power, and combination of simultaneously operating charging station connectors. Proposals have been developed for amending SP 256.1325800.2016 "Electrical installations of residential and public buildings. Design and installation rules" in terms of the methodology for determining the estimated electrical loads of the charging infrastructure for electric vehicles integrated into electrical installations of public buildings. CONCLUSION. The development of a methodology for calculating electrical loads simultaneously with the development of demand factors, simultaneity and the coefficient of mismatch of maximums of charging infrastructure for electric vehicles integrated into public buildings will contribute to the optimization of costs for technological connection to electrical networks.

Effects of side ratio on wind load characteristics on high-rise building

This study investigates the impact of varying side ratios (SR) on wind loads in high-rise buildings using wind tunnel tests and large eddy simulations. It assesses surface wind load by analyzing static three-component force coefficients and shape factors across different SRs. The results show that the model with D/B = 0.5 exhibits the largest mean and r.m.s drag forces, while the model with square cross section (D/B = 1) experiences the lowest torque. Meanwhile, the model with D/B = 0.5 reveals strong vertical but relatively weak horizontal wind pressure correlation. In addition, models with large SRs exhibit altered wind pressure mechanisms due to the occurrence of flow reattachment and secondary separation, resulting in lower side-surface correlation compared to small SR models.

Large Eddy Simulation of Flow Around Twin Tower Buildings in Tandem Arrangements with Upstream Corner Modification

The aerodynamic performance of twin tall buildings immersed in the atmospheric boundary layer was numerically investigated by adopting the spatial-averaged large eddy simulation (LES) method. This study focused on the effects of corner cutting and chamfering. The buildings were both square and sectional with a width-to-height ratio of 1:6, and were arranged in a tandem configuration with a spacing ratio of 2.0. The corner-cutting and chamfering measures were only applied to the upstream cylinder, with a corner modification rate of 10%. To generate the turbulent inflow boundary condition (IBC) for LES, steady-state equilibrium IBC expressions were introduced into the vortex method, which were implemented in the commercial code Ansys Fluent. The present simulation method and solution parameters were first verified by comparing the simulated wind field and the wind pressure distribution on a single tall building with those of the wind tunnel test. The influences of the corner-cutting and chamfering measures on the wind load of the tandem buildings were then comparatively studied concerning the statistical values of their aerodynamic force coefficients and wind pressure coefficients. The influence mechanism was analyzed based on the simulated time-averaged flow field and the instantaneous vortex structure around the buildings. The results indicated that upstream corner-cutting and chamfering measures can induce a diffusion angle shift in the separated shear flow from the leading edge of the upstream building, thus affecting the separation and reattachment of the separated upstream flow on the downstream building. Among the measures studied, upstream corner cutting is more effective in reducing wind pressure and aerodynamic force coefficients.

Benchmarking a Novel Particle Swarm Optimization Dynamic Model Versus HOMER in Optimally Sizing Grid-Integrated Hybrid PV–Hydrogen Energy Systems

This paper presents the development of an Artificial Intelligence (AI)-based integrated dynamic hybrid PV-H2 energy system model together with a reflective comparative analysis of its performance versus that of the commercially available HOMER software. In this paper, a novel Particle Swarm Optimization (PSO) dynamic system model is developed by integrating a PSO algorithm with a precise dynamic hybrid PV-H2 energy system model that is developed to accurately simulate the hybrid system by considering the dynamic behaviour of its individual system components. The developed novel model allows consideration of the dynamic behaviour of the hybrid PV-H2 energy system while optimizing its sizing within grid-connected buildings to minimize the levelized cost of energy and maintain energy management across the hybrid system components and the grid in feeding the building load demands. The developed model was applied on a case-study grid-connected building to allow benchmarking of its results versus those from HOMER. Benchmarking showed that the developed model’s optimal sizing results as well as the corresponding levelized cost of energy closely match those from HOMER. In terms of energy management, the benchmarking results showed that the strategy implemented within the developed model allows maximization of the green energy supply to the building, thus aligning with the net-zero energy transition target, while the one implemented in HOMER is based on minimizing the levelized cost of energy regardless of the green energy supply to the building. Another privilege revealed by benchmarking is that the developed model allows a more realistic quantification of the hydrogen output from the electrolyser because it considers the dynamic behaviour of the electrolyser in response to the varying PV input, and also allows a more realistic quantification of the electricity output from the fuel cell because it considers the dynamic behaviour of the fuel cell in response to the varying hydrogen levels stored in the tank.

Building electrical load forecasting with occupancy data based on wireless sensing

Building electrical load forecasting, as a necessary foundation for building energy management, is of great significance for building energy efficiency and sustainable urban development. However, the accuracy of forecasting can hardly be guaranteed due to the stochastic nature of occupant behavior. To overcome this challenge, this paper proposes a data fusion-based building electrical load forecasting method with occupancy data obtained by wireless sensing technology. Firstly, a wireless sensing scheme is developed, which utilizes pre-existing wireless devices within the building energy management system (BEMS), offering a cost-effective means of obtaining occupancy information without violating occupant privacy. Moreover, to estimate the pattern of occupant behavior in the entire building, an improved stacked sparse auto-encoder (ISSAE) model is developed, which involves unsupervised feature fusion from information sources of varying significance. Finally, to cope with the time-varying and strongly fluctuating building load, a multi-source data fusion forecasting model based on the ensemble deep random vector functional link (edRVFL) is proposed. This model integrates the contributions of the latest accuracy and diversity through the ranking-based dynamic integration strategy. The effectiveness of the proposed method is validated in a commercial building. The experimental results demonstrate that, compared with the load forecasting scheme without occupancy information, the proposed method can improve the forecasting accuracy on RMSE and MAPE by 13.21% and 14.97%, respectively, while cost-effectiveness and privacy are ensured.

Analysis of the Creep Curve Reinforced Concrete Beams in Eurocode 2 via the Three-Parameter Model

Creep is characterized by progressive deformation that occurs in concrete structures when exposed to constant loads during their operation. Factors such as air humidity, temperature, the initial consistency of the concrete, and the strength of the concrete after curing are decisive for the advancement of this phenomenon and the resulting deformation over time. In reinforced concrete beams, these deformations can increase the final deflection corresponding to the serviceability limit state, as well as cause the failure of the system at the ultimate limit state. The three-parameter model is suitable for describing the viscoelastic nature of many solids and is frequently used to study the phenomenon in various scientific fields. In this work, the creep model could be considered in two ways: first, the mathematical model for creep predicted by Eurocode 2 (European Standard EN 1992-1-1), and second, a three-parameter viscoelastic model whose parameters are adjusted to match the results obtained with the use of Eurocode. A three-parameter mathematical model was developed to accurately represent the creep curve of Eurocode 2 using computational modeling. In this context, this study seeks to understand the effects of creep in reinforced concrete structures through numerical modeling using a three-parameter model of a simply supported beam designed for usual building loads. A basic literature review on creep in concrete structures was conducted, followed by a structural analysis at different times during the commonly accepted life expectancy of these structural systems. In the simulation, the three-parameter model was used as an alternative to the creep calculation prescribed in Annex B of EUROCODE 2. During the analysis process, curves representing the investigated phenomenon were generated, considering different ambient temperature values, with the results presented in the form of graphs and tables. The adopted structural element was a rectangular reinforced concrete beam, simply supported at the ends. The adopted load was uniformly distributed. With this, it was possible to assess the displacements over time, enabling the evaluation of creep deformations at different stages of time under the influence of temperature and ambient humidity.

Enhanced methodology for disaggregating space heating and domestic hot water heat loads of buildings in district heating networks

Enhanced methodology for disaggregating space heating and domestic hot water heat loads of buildings in district heating networks

A hybrid prediction model for heating load of buildings within residential communities considering occupancy rates

A hybrid prediction model for heating load of buildings within residential communities considering occupancy rates

Thermal performance of a double-layer pipe-embedded phase change wall system in wood structures coupled with solar energy

In this study, we propose a dual-layer, pipe-embedded phase change wall system for wooden structures that integrates sky radiation cooling and solar heat collection for cross-seasonal operation. This system harnesses renewable energy and reduces the operational energy consumption of buildings. The primary focus of this study is the performance improving of the system during winter conditions. In winter, the system captures solar energy for daytime indoor heating and load reduction and stores excess heat in phase-change material (PCM) embedded within the wooden wallboard. The stored heat is then released at night to further reduce building loads. To assess the thermal performance of the proposed wall system under winter conditions, experiments were conducted across four different scenarios and a reference system was established for comparative analysis. The results indicate that the proposed wall system significantly improves the indoor thermal environment. Specifically, this integration increased the average indoor air temperature by 6.0 °C compared to the reference system and substantially increased the temperature of the wallboard. The inclusion of PCM notably enhanced the thermal performance by reducing nighttime heat loss. Consequently, the average indoor temperature in systems equipped with PCM-enhanced wallboards was 3.0 °C higher than that in the reference system.

A hybrid predictive model with an error-trigger adjusting method of thermal load in super-high buildings

The precise prediction of thermal load has consistently garnered attention owing to its significant impact on energy conservation in buildings. The methodologies employed primarily concentrate on modeling within steady-state conditions, utilizing time-series data or mechanism model on fixed parameters. However, given the pronounced time-varying and multifaceted disturbance characteristics associated with building loads, current approaches exhibit constrained efficacy in addressing abrupt fluctuations in demand load and managing data noise. This limitation consequently undermines the accuracy of predictions. This paper proposes a novel hybrid model and an error-trigger adjusting strategy for predicting the thermal load in super-high buildings. The model is constructed by combining a thermodynamic model and an error cancellation model. The former, derived from an examination of the variations of material and energy in buildings, is proposed in the form of an approximate resistance-capacitance structure. The latter is developed using a wavelet threshold denoising technique, in conjunction with a convolutional neural network and a long short-term memory network. A self-adaptive state transition algorithm has been proposed, which relies on dynamically adjusting factors within the feasible region to optimize the selection of unknown parameters in the thermodynamic model. To enhance the flexibility of the hybrid model in effectively respond to the intricacies and fluctuations within the thermal conditions of buildings, an error-trigger adaptive updating strategy and a parameter calibration method based on sensitivity analysis are established. The real-world application results demonstrate the effectiveness of the presented hybrid model and the adjusting strategy.

Optimizing heating efficiency: The role of sunspace geometry

Solar energy stands out among renewable energy sources due to its efficiency and ease of application, making it a preferred option. It can be utilized through both active and passive systems, significantly reducing heating costs. Sunspaces, a type of passive heating system, not only provide additional usable spaces but also decrease the heating load of buildings. However, studies and market applications indicate that the roof slopes of sunspaces are generally not significantly varied. Additionally, the depth of the sunspace is often determined based on the area of use, which can limit the full utilization of its energy potential. In this study, the impact of sunspace geometry on energy savings was investigated. A scaled model of a detached house with a sunspace was created in Istanbul, and measurements were taken in an open field during winter conditions. Parameters such as indoor and outdoor temperature, humidity, wind speed, and solar energy were examined. This house model was then simulated using TRNSYS software, and the results were compared with experimental data. After confirming that accurate results could be obtained with the computer model, different roof slopes and room depths of the sunspace were simulated. The results determined the effects of roof slope and room depth on energy consumption. Consequently, it became possible to better harness solar energy in sunspaces and reduce heating costs.

Research on Non-Intrusive Load Disaggregation Technology Based on VMD–Nyströmformer–BiTCN

Non-intrusive load disaggregation is a technique that monitors the total electrical load of an entire building or household. It uses a single power metering device to measure the total load. Then, it employs algorithms to break it down into the individual usage of different electrical devices. To address issues in load disaggregation models such as long training times, feature interference caused by the activation of other loads, and accuracy deficiencies caused by behavioral interference from users’ electricity usage habits, this paper proposes a VMD–Nyströmformer–BiTCN network architecture. The variational mode decomposition (VMD) filters the raw power data, reducing errors caused by noise and enhancing the accuracy of decomposing the load. A deep learning network utilizes a modified attention model, Nyströmformer, to reduce feature entanglement and accuracy degradation caused by habitual behavior interference during load disaggregation, while ensuring precise accuracy and improving network operational speed. The training network uses a bidirectional temporal convolutional network (BiTCN) and incorporates a residual network to expand the receptive field, allowing it to receive longer load sequence data and acquire more effective load information, thereby improving the disaggregation effectiveness for target appliances.

Multi-period optimal scheduling of building loads based on accurate virtual battery model

Optimal building load scheduling is assuming a pivotal role in enhancing stability and promoting sustainability in the modern energy sector. However, it is significantly challenging to balance diverse energy demands and grid services while adhering to the aggregate flexibility of a varied collection of buildings. This paper presents a novel multi-period optimal scheduling (MOS) for thermostatically controlled loads (TCLs) in buildings to simultaneously provide multiple grid services to enhance energy efficiency and grid reliability, utilizing an accurate virtual battery (VB) model to represent the aggregate flexibility of TCLs. First, a VB model that accurately captures the aggregate flexibility of TCLs with heterogeneous parameters is derived, featuring a novel selection of the self-discharging rate. The accuracy of the model is also proved. Subsequently, the MOS framework is developed for a collection of heterogeneous TCLs to optimally balance diverse energy and grid service demand based on the derived VB model. Margin reserves are introduced to address uncertainty, enabling more reliable scheduling within the MOS framework. The efficacy of the proposed VB model and the MOS framework is demonstrated through case studies.

An energy saving potential evaluation method of a pipe-embedded wall integrated with natural energies

Pipe-embedded wall (PEWall) can be integrated with various natural energies to significantly reduce building load and energy consumption. However, a general method for quickly assessing the energy-saving potential of such different systems is currently lacking. To address this gap, a novel evaluation method based on revised degree hour is presented. This method focuses on the determination of main parameters essential for accurate assessment. The proposed method is validated by comparing its results with that of a reference model, demonstrating good accuracy. Case study is conducted to evaluate the energy saving potentials of the PEWall with the ground source heat exchanger (GSHE), the cooling tower (CT) and the solar energy collector (SEC) in Wuhan, a hot summer and cold winter climate region. The evaluation results show that, the energy savings of the PEWall-GSHE system for cooling and heating can reach 6.51 kWh/m2 and 2.79 kWh/m2 respectively, demonstrating good energy saving potential. For the PEWall-SEC system, the energy saving for heating is 3.98 kWh/m2 which is acceptable. For the PEWall-CT system, a limited energy saving for cooling of 1.22 kWh/m2 is presented. In conclusion, this evaluation method can effectively assess the energy-saving potentials of the PEWall with different natural energies.

Deep-learning-based multi-timescale load forecasting in buildings: opportunities and challenges from research to deployment

Electricity load forecasting for buildings and campuses is becoming increasingly important as the penetration of distributed energy resources (DERs) grows. Efficient operation and dispatch of DERs require reasonably accurate predictions of future energy consumption in order to conduct near-real-time optimized dispatch of on-site generation and storage assets. Electric utilities have traditionally performed load forecasting for load pockets spanning large geographic areas, and therefore, forecasting has not been a common practice by buildings and campus operators. Given the growing trends of research and prototyping in the grid-interactive efficient buildings domain, characteristics beyond simple algorithm forecast accuracy are important in determining the algorithm’s true utility for smart buildings. Other characteristics include the overall design of the deployed architecture and the operational efficiency of the forecasting system. In this work, we present a deep-learning-based load forecasting system that predicts the building load at 1-hour intervals for 18 hours in the future. We also discuss challenges associated with the real-time deployment of such systems as well as the research opportunities presented by a fully functional forecasting system that has been developed within the National Renewable Energy Laboratory’s Intelligent Campus program.

Mathematical modeling of gas-phase mass transfer in hydrous materials for a total heat exchange ventilator

Total heat exchange ventilation systems are effective in achieving energy savings by reducing the ventilation load in buildings, while maintaining a certain amount of fresh outdoor air intake. As the system's elemental materials exchange both latent and sensible heat, hydrophilic chemical compounds may be exchanged simultaneously. Proper control of the exchange of hazardous chemicals and pollutants via these heat exchange elements is an important issue in the development of total heat exchange ventilation systems. In this respect, the development of a numerical model that facilitates repeated sensitivity analysis is important in the development of a new total heat exchanger that has high heat exchange efficiency and suppresses the exchange of polluting chemicals. This study proposes new hygrothermal and chemical compound transfer models for paper-based hydrous materials, which are the main components of total heat exchangers in indoor ventilation systems. Through a series of numerical analyses and experimental measurements, the prediction accuracy of the mathematical model was compared with experimental results for the gas transfer rate in hydrous materials and a building-sized total heat exchanger. The results demonstrated that an increase in water content in hydrous material has a significant impact on the permeability of water-soluble gases, with NH3 and HCHO permeability coefficients increasing by factors of 250 and 20 respectively. Conversely, for low-solubility gases such as CO2, the permeability coefficient only slightly increased at low humidity and remained largely unaffected thereafter. These findings contribute to the advancement of more efficient and safer total heat exchange ventilation systems.

Experimental investigation of thermal performance of ground source heat pump system for summer and monsoon seasons of Himalayan region of India: A case study

In the present experimental research work examines the thermal interactions of borehole heat exchangers on the ground side and psychrometric process involved inside the room during cooling mode operation using a ground source heat pump system (GSHP). An experimental facility of 17.5 kW cooling capacity GSHP system, consisting of five parallelly connected double U-tube borehole heat exchangers fitter with a commercially available heat pump system has been employed. The experiments were performed during peak summer and monsoon (rainy) seasons for space cooling applications for 45 hours of continuous operation in a city located in the Himalayan range of India. Analysis of results obtained indicate that during the summer season the hourly heat rejected to the ground is maximum for peak weather conditions due to high cooling load demand on the user side. On increasing the building load (increase in ambient temperature), there is a slight decrease in COPsys in both the seasons. During heavy rain season, the latent cooling load increases up to 1.5 times of the sensible cooling load. The average value of sensible heat factor is found to be 0.6 for the case of the peak summer season and 0.51 for the rainy season.

Prediction of building cooling load: an innovative design for GA-SVM and IG-SVM system for the estimation of hourly precision and computational fluctuation range

ABSTRACT Anticipating the loads that buildings will bear is a crucial strategy in the pursuit of energy efficiency and the reduction of emissions. In this paper, we introduce an interactive and comprehensive joint prediction model, specifically crafted to elevate the precision of forecasts related to building loads. The resultant Genetic Algorithm-Support Vector Machine (GA-SVM) prediction model is put into action to provide hourly predictions of cooling loads for buildings. In scenarios where the prediction of building cooling load (BCL) fluctuations becomes imperative, especially in the face of extreme weather conditions, the information granulation (IG) method is employed. The findings of this validation process unveil significant improvements. The coefficient of variation of root mean square error (CV-RMSE) and mean absolute percentage error (MAPE) for the GA-SVM model are reduced by 58.85% and 68.04%, respectively, when compared to the conventional SVM model. Furthermore, in a comparative analysis against three widely utilized prediction models, the SVM model demonstrates a reduction in CV-RMSE and MAPE ranging from 2.04% to 68.04%. The application of the joint prediction model showcases impressive results, with R 2 values ranging from 97.27% to 99.68%, MAPE ranging from 2.59% to 2.84%, and CV-RMSE ranging from only 0.0249 to 0.0319.