Loads In Residential Buildings Research Articles

Predicting hourly heating load in residential buildings using a hybrid SSA–CNN–SVM approach

This study proposes a hybrid prediction model using sparrow search algorithm (SSA) to optimize the convolutional neural network (CNN) and support vector machine (SVM), in order to perform accurate prediction of secondary supply temperature (Ts2). The historical operation data of Weifang residential building thermal station was adopted and reasonable data preprocessing was performed to suppress the interference of abnormal data. The input variables of the prediction model were screened using the correlation analysis method, taking the influence of the hysteresis effect into consideration. The SSA–CNN–SVM model was then developed for prediction. The performance of the model was evaluated by the root mean square error, mean absolute error, mean absolute percentage error (MAPE), and absolute value of relative error of each time step. The results obtained demonstrated that the SSA–CNN–SVM model has high prediction accuracy. The MAPE values of the two heat exchange stations were between 2.28 % and 2.4 %. The indoor temperature significantly affected the prediction accuracy of Ts2. After the introduction of the indoor temperature, the MAPE of the predicted values of the hybrid model was reduced by 0.35 %. The maximum reduction in MAPE of the SSA–CNN–SVM model was 1.5 % compared with other prediction models.

Least-cost solutions to household energy supply decarbonisation in temperate and sub-tropical climates

Decarbonisation of building energy supply is key to achieving current targets of greenhouse gas emission reduction. However, the least-cost, net-zero supply of electrical and thermal loads in residential buildings is affected by building type, local climate and grid emissions intensity and is subject to uncertain future energy prices. This work investigated a typical detached house and an apartment in two climates – temperate and sub-tropical – in Australia. Least-cost optimisation of the technology mixes required to serve building energy loads was undertaken, including a range of appliances powered by electricity, natural gas and hydrogen and the use of distributed energy resourced, notably rooftop solar and residential battery energy storage. Solutions were investigated with increasingly stringent greenhouse gas emission abatement constraints and a range of future prices for electricity and hydrogen, demonstrating: i) progressive electrification is the likely cheapest pathway to net-zero emissions for the two building types studied; ii) should grid decarbonisation lag the abatement constraint applied to the homes, a net-zero dwelling is likely unachievable and the deepest achievable abatement is very expensive; and iii) network-delivered hydrogen may be optimal in a subset of buildings with limited distributed energy resources potential and more peaky heating and hot water demands. In such cases, bio-methane or even synthetic methane may also be preferred. Through significant adoption of distributed energy resources, results suggest an affordable route to deep (i.e. > 50 %) abatement for homeowners that relies less on grid emissions and, beyond the Australian case study, can be extended to a significant proportion of dwellings in other countries.

Impact of future climate change on energy consumption in residential buildings: A case study for representative cities in Japan

This study examines the impact of future climate change on energy consumption in residential buildings in Japan, taking into account both the current and future typical meteorological year (TMY) database. TMY data is widely used in the building sector for energy performance assessments, system sizing, and optimization. To investigate the impact of current and future TMY databases on energy consumption of buildings, the study predicts the cooling and heating loads of residential buildings in four cities of Japan under the current (2020 ver.) and future (2086 ver.) TMY databases. Results show that the use of future TMY database leads to significant changes in air-conditioning heat loads of residential buildings in Japan. It finds that the annual cooling load in residential buildings of four cites of Japan increases by approximately 12% for Tokyo, approximately 9% for Toyohashi, approximately 8% for Osaka, and approximately 7% for Nagoya, respectively, however the annual heating load decreases by approximately 8% for Tokyo, approximately 9% for Toyohashi, approximately 6% for Osaka, and approximately 5% for Nagoya, respectively, compared to the current TMY database. This finding suggests that climate change will have a significant impact on future building energy consumption, and proposes energy-efficient building design as a solution to mitigate the impact of climate change on building energy consumption.

Proposing hybrid prediction approaches with the integration of machine learning models and metaheuristic algorithms to forecast the cooling and heating load of buildings

Accurate prediction of heating and cooling loads in residential buildings is crucial for both researchers and practitioners. This study employs advanced forecasting techniques, utilizing support vector regression and extreme gradient boosting methods, enhanced by state-of-the-art metaheuristic algorithms. The metaheuristic optimizers applied include the Satin Bowerbird Optimizer, Ant Lion Optimizer, Artificial Ecosystem-Based Optimizer, Slime Mold Optimizer, Moth-Flame Optimizer, and Particle Swarm Optimizer. These optimizers are strategically used to refine the forecasting models, optimizing their parameters for increased precision. To evaluate the models, a suite of statistical indices is used, including mean square error, root mean square error, Mean Absolute Percentage Error, Mean Absolute Error, Relative Absolute Error, coefficient of correlation, Coefficient of Determination, and Normalized Mean Square Error. This comprehensive analysis assesses the effectiveness of the forecasting methods. The study's findings highlight that the combination of the Satin Bowerbird Optimizer and extreme gradient boosting is particularly effective, achieving high coefficients of determination for cooling and heating load predictions (0.95826 and 0.938048, respectively). This hybrid algorithm shows remarkable performance, with minimal error values and consistent convergence across various datasets. In summary, this research underscores the efficiency of integrating sophisticated machine learning models with metaheuristic optimization techniques, particularly identifying a potent hybrid algorithm for the accurate prediction of heating and cooling loads in residential buildings.

AI-based KNN Approaches for Predicting Cooling Loads in Residential Buildings

AI-based KNN Approaches for Predicting Cooling Loads in Residential Buildings

Sizing and energy management of standalone hybrid renewable energy systems based on economic predictive control

This paper aims to design and run a standalone hybrid renewable energy System (HRES) feeding residential building load. The suggested HRES encompasses photovoltaic panels and wind turbines as energy sources, combined with a hydrogen subsystem and a bank of batteries for energy storage. The meteorological input data includes irradiance, temperature, and wind speed for four seasonal weeks. These data sets are collected for a rural site situated in the town of Ras Munif, northern Jordan. The load profiles characterize a selected benchmark residential building. Consequently, a bi-level mixed integer nonlinear programming (BMINLP) problem is formulated to incorporate the designing problem with the energy management process. The upper level represents the sizing problem, while the lower level problem denotes the energy management strategy (EMS). Each problem has its independent objective function, constraints, and optimization variables. The EMS is an economic-based single objective optimization problem expressed as a mixed integer linear programming (MILP) problem. On the contrary, a mixed integer nonlinear programming (MINLP) approach frames the sizing problem to optimize a techno-economic-based multi-objective function. The interaction between the two problems is that the lower problem is an embedded constraint of the upper problem. Moreover, the candidate solutions from the upper problem are treated as fixed parameters in the lower problem. A multi-objective genetic algorithm is used to execute the overall problem by the MATLAB toolbox. The technical and economic performance parameters, including the investment cost, maintenance, operating costs, and others, are assessed based on the best findings. The key finding demonstrates that the summer week has the lowest total cost and energy loss factor, with around 132,000 $ and 0, respectively. Furthermore, the findings reveal that the entire system's energy loss factor for each sample period is less than 0.0009. This value is substantially less than the permitted limit of 0.01.

Predictive analysis of Low power DC loads in Residential Buildings

There has been a constant rise in use of loads powered from direct current (DC) among the residential loads. In the traditional Alternating Current (AC) grid voltage undergoes conversion multiple times before it reaches the loads requiring DC, which leads to substantial power loss in the converters. Implementation of a DC grid in the residential buildings can reduce the losses caused due to the conversions. The paper presents a prediction model for domestic low power DC loads which can be powered from a battery. The data of usage of the load as well as the data of the parameters on which the load usage is dependent on was collected over a period of a year. This data was fed to a Random forest-based machine learning algorithm to predict the usage of the loads in future. The state of charge (SOC) of the battery used to power the loads was compared with the load prediction to decide whether the load can be powered from the available power in the battery or not. This allowed the system to decide in real time on the source to be used to power the DC loads and providing the users a choice to change the load usage time in order to prevent power from being drawn from the AC grid.

A Hyper Parametrized Deep Learning Model for Analyzing Heating and Cooling Loads in Energy Efficient Buildings

The huge increase in energy consumption in recent decades, has made it cumbersome to anticipate energy usage in the residential sector. However, despite substantial advancements in computation and simulation, the modelling of residential building energy use is still in need of improvement for efficient and reliable solutions. To this end, the overarching objective of this research study is to construct a self-adaptive model (HBO-DL) for predicting the amounts of heating and cooling loads in residential buildings. The developed HBO-DL model is envisioned on coupling Bayesian optimization with deep learning neural network. Five statistical metrics of mean absolute percentage error (MAPE), root mean squared error (RMSE), root mean squared logarithmic error (RMSLE), mean absolute error (MAE) and normalized root mean squared error (NRMSE), are leveraged to measure and test the accuracies of the developed HBO-DL. Analytical results explicated that the developed HBO-DL model can endorse informed decision-making and foster energy conservation in built environment.

Analysis of Cooling Load Characteristics in Chinese Residential Districts for HVAC System Design

Energy consumption in residential buildings accounts for a large portion of global energy use. Understanding residential building load characteristics is important in both the design and technical suitability analysis of residential air conditioning systems in terms of energy efficiency and carbon reduction. However, most current research mainly focuses on the load characteristics of individual buildings and not on the variation in load characteristics of building aggregation. In addition, the load characteristics of building aggregations vary with the building scale; however, most studies have compared those of buildings under a certain scale, and the change with the increase in building scale is still unclear. The main purpose of this study is to explore load characteristic differences among residential buildings of different scales and the impacts of those differences on HVAC system design. Based on the monitoring data collected in a residential district in Zhengzhou, China, we analyzed the load characteristics among different households and combinations of different numbers of households from the variation in peak load, total consumption and load distribution, as well as the daily load volatility. We indicate that the load characteristics of heating, ventilation and air conditioning systems of different scales should be considered in the design and operation stage.

Forecasting heating and cooling loads in residential buildings using machine learning: a comparative study of techniques and influential indicators

Residential buildings are a significant source of energy consumption and greenhouse gas emissions, making it crucial to accurately predict their energy demand for reducing their environmental impact. In this study, machine-learning techniques such as linear regression, decision tree classification, logistic regression, and neural networks were applied to forecast the heating and cooling loads of 12 different building types using their area and height attributes. The correlation coefficient was utilized to assign weights to the predictors in linear regression, and the models’ performance was evaluated using metrics such as equations of R2, MAE, and RMSE. The decision tree technique demonstrated the highest accuracy of 98.96% and 93.24% for predicting heating and cooling loads, respectively, among the classification methods. Notably, the cooling load prediction was more accurate than the heating load prediction. The height and area of the roof and floor, along with the relative compactness of the building, were identified as the most influential factors in the heating and cooling loads. These findings have significant implications for optimizing energy efficiency in residential buildings and mitigating their impact on climate change.

Impacts of UHI on Heating and Cooling Loads in Residential Buildings in Cities of Different Sizes in Beijing–Tianjin–Hebei Region in China

The heating and cooling energy consumption levels of urban buildings account for a large and rapidly growing proportion of the total end-use energy consumption of society. The urban heat island (UHI) effect is an important factor influencing the spatiotemporal variations in the heating and cooling energy consumption levels of buildings. However, there is a lack of research on the impact of the UHI on the heating and cooling energy consumption of buildings in cities of different sizes in the Beijing–Tianjin–Hebei urban agglomeration, which is the most urbanized region in northern China. We selected rural reference stations using the remote sensing method, and applied an hourly data set from automatic weather stations, to examine the impact of the UHI on the typical residential building heating and cooling loads in three cities of varied sizes in the Beijing–Tianjin–Hebei urban agglomeration through building energy simulation. The main conclusions were as follows. As the UHI intensity (UHII) increased, the heating load difference between urban and rural areas decreased, while the cooling load difference between urban and rural areas increased in the cities. The average daily heating loads in the urban areas of Beijing, Tianjin, and Shijiazhuang were 8.14, 10.71, and 2.79% lower than those in their rural areas, respectively, while the average daily cooling loads in the urban areas were 6.88, 6.70, and 0.27% higher than those in their rural areas, respectively. Moreover, the absolute hourly load differences between urban and rural areas were significantly larger during the heating periods than during the cooling periods, with the former characterized by being strong at night and weak during the day. During the peak energy load period, the contribution of the UHI to the peak load of residential buildings varied between the cities. During the stable high-load period, from 18:00 to 07:00 the next day in the heating periods (from 18:00 to 05:00 the next day in the cooling periods), the hourly loads in the urban areas of Beijing, Tianjin, and Shijiazhuang were 3.15 (2.48), 3.88 (1.51), and 1.07% (1.09%) lower (higher) than those in their rural areas, respectively. Our analysis highlights the necessity to differentiate the energy supplies for the heating and cooling of urban buildings in different sized cities in the region.

Evaluation of climate change effects on residential building cooling and heating demands in New Zealand: implications for energy efficiency standards and building codes

PurposeClimate change reports from New Zealand claim that climate change will impact some cities such as Auckland from a heating-dominated to a cooling-dominated climate. The benefits and risks of climate change on buildings' thermal performance are still unknown. This paper examines the impacts of climate change on the energy performance of residential buildings in New Zealand and provides insight into changes in trends in energy consumption by quantifying the impacts of climate change.Design/methodology/approachThe present paper used a downscaling method to generate weather data for three locations in New Zealand: Auckland, Wellington and Christchurch. The weather data sets were applied to the energy simulation of a residential case study as a reference building using a validated building energy analysis tool (EnergyPlus).FindingsThe result indicated that in Wellington and Christchurch, heating would be the major thermal load of residential buildings, while in Auckland, the main thermal load will change from heating to cooling in future years. The revised R-values for the building code will affect the pattern of dominant heating and cooling demands in buildings in Auckland in the future, while in Wellington and Christchurch, the heating load will be higher than the cooling load.Originality/valueThe findings of this study gave a broader insight into the risks and opportunities of climate change for the thermal performance of buildings. The results established the significance of considering climate change in energy performance analysis to inform the appropriate building codes for the design of residential buildings to avoid future costly changes to buildings.

Impact assessment of climate change on energy performance and thermal load of residential buildings in New Zealand

While it is evident that climate change will have an impact on the energy demand for heating and cooling in buildings, the exact extent of this impact is not yet fully understood. Quantification of future cooling and heating need in buildings provides a basis for taking appropriate measures for building climate change adaptation. The focus of this study is to examine how future climate change scenarios will impact the heating and cooling of residential buildings across different climatic regions in New Zealand. The future weather data under changing climate were generated for six climatic zones of New Zealand employing the statistical downscaling method. The study used various climate change scenarios, which represent concentration pathways (RCPs), to generate weather data. Specifically, the RCP8.5 and RCP4.5 scenarios were employed in the building performance simulations for different prototypes of residential buildings. The results showed there would be a significant change in the thermal performance of residential buildings, with a noticeable increase in cooling load and a decrease in heating load. These changes include a maximum thermal load change of 3 kWh/m2 in Auckland by 2090, 2.7 kWh/m2 in Hamilton, 8.3 kWh/m2 in Wellington, 4.2 kWh/m2 in Rotorua, 11 kWh/m2 in Christchurch, and 11.6 kWh/m2 in Queenstown. The warmer climatic zones are expected to change from a heating dominated to a cooling-dominated zone. The results indicated the importance of considering present and future climatic conditions in design and establishing a foundation for actions for the resilience of buildings to climate change.

Effective wall structures with use of flax straw concretes

The modern building technologies are technologies of green construction, near zero-energy and active buildings with bioclimatic design, optimized energy consumption and CO2 emissions. Prospective enclosing structures of such buildings are structures using available, low cost, and environmentally friendly materials based on plant raw materials. In this paper the evaluation of technical solutions of wall enclosing structures using flax concrete based on lime binder with a density of 300-350 kg/m3 was carried out, taking into account their heating and cooling loads in residential buildings. It is shown that the provision of the necessary indicators of the external walls of energy-efficient buildings is achieved by using multilayer structures with a heat-insulating layer of flax straw concrete or a single-layer structures made from flax straw concrete in frame construction technology.

DeepEdge-NILM: A case study of non-intrusive load monitoring edge device in commercial building

Non-intrusive load monitoring (NILM) has become an emerging technology in the energy sector for its effectiveness in the energy disaggregation of individual loads from the measured aggregated energy in main power supply of building. NILM has also evolved gradually over the past few decades, due to the significant advancements in artificial intelligence (AI), embedded/edge devices, and internet of things (IoT). From the review of literature, we observed that most of the NILM systems were only capable of monitoring different loads and it fails to detect and disaggregate the energy consumption of similar loads effectively. Further, most of works in the literature were focused on improving the performance of energy disaggregation of different loads in residential buildings and very limited works have been carried out for the similar loads in NILM system. Therefore, there is a necessity to study and evaluate the state of the art NILM algorithms for similar loads in real case scenarios for effective implementation in the commercial and industrial buildings. In this paper, we present a case study of the developed DeepEdge-NILM device which has been installed in a commercial building (office environment), where multiple similar and identical air conditioners (AC's) are used in the monitoring environment. A deep learning framework, Long Short-Term Memory (LSTM) has been implemented on the new set of features which comprises of electrical features and intrinsic features derived from the basic electric features using geometric mean for capturing the signature of similar loads effectively. From our case study, we observed that the performance of the deployed NILM system outperforms the baseline systems that have been developed using basic electrical features significantly. Finally, the limitations and future scope of the NILM edge device in the commercial buildings are also discussed.

The impact of PV panels on cooling and heating loads of residential buildings in a humid subtropical climate zone

Installing photovoltaic (PV) panels on the roofs of homes may reduce dependence on the electrical grid and lead to net-zero energy production. Climate patterns and a building’s structural system can significantly affect how much energy the structure uses. This investigation is aimed to focus on the shading effect of solar panels on the uninsulated roof of a residential building to investigate the output of combining architectural buildings with renewable energy systems. The PV system was modelled as a shading device using building simulation software (Design Builder) to calculate the monthly reduction and increase in heating and cooling loads for the rooftop in a humid subtropical climate zone. The results showed that the cooling loads were decreased by 290 kWh/year (almost 5%) and heating by almost 30 kWh/year. The findings showed the importance of renewable energy in tackling climate change and reducing the housing energy requirements for sustainable development.

Prediction of heating and cooling loads based on light gradient boosting machine algorithms

Machine learning models have been widely used to study the prediction of heating and cooling loads in residential buildings. However, most of these methods use the default hyperparameters, resulting in inaccurate prediction accuracy. In this work, based on hyperparametric optimization algorithms of random search (Random), grid search (Grid), covariance matrix adaptive evolution strategy (CMA-ES), and tree-structured parzen estimator (TPE), were combined with the light gradient boosting machine (LightGBM) model, to construct four hybrid models (Random-LightGBM, Grid-LightGBM, CMA-ES-LightGBM and TPE-LightGBM) for improved prediction accuracy of heating and cooling loads. The LightGBM model was trained using a dataset consisting of building features, cooling set points, and occupant behavior parameters. Feature selection was performed by a random forest-based feature selection method, which determines the input features of the load prediction model. The TPE- LightGBM model achieved the best prediction accuracy among all proposed models with a root mean square error (RMSE) of 0.2714, mean absolute error (MAE) of 0.1416, coefficient of determination (R2) of 0.9981, and mean absolute percentage error (MAPE) of 0.4699% for heating load prediction, and RMSE of 0.1901, MAE of 0.1394, R2 of 0.9924, and MAPE of 2.3509% for cooling load prediction. The proposed TPE-LightGBM model provides an efficient strategy for predicting heating and cooling loads, which can provide better energy efficiency measures at the early design stages of residential buildings.

Stacking Ensemble Learning-Based Load Identification Considering Feature Fusion by Cyber-Physical Approach

Nonintrusive load monitoring (NILM) methods considering multiple representative features can improve load identification. However, these existing methods assemble all features into one classifier, which easily causes overfitting and increases the computational complexity during the training process. To tackle these problems, this article proposes a novel stacking ensemble learning (SEL)-based load identification framework considering physical and cyber feature descriptors (CFDs), which can nicely fuse features by integrating different types of features into corresponding classifiers of the SEL model. The proposed framework includes two main parts: 1) comprehensive features are constructed based on a physical feature descriptor (PFD) and a CFD to fully explore the representative feature space and 2) the SEL model is developed to enhance the mutual complementary ability of different features and increase the variability of base classifiers. To evaluate the effectiveness of the proposed method, experiments are conducted on a public dataset. Numerical evaluations for residential building loads show that the proposed method significantly improves the identification performance and outperforms prior methods.

Calculation of specific electrical loads of residential buildings based on actual measurements

Updating the development of specific electrical loads of residential buildings of clusters 1 (up to 5 floors) and 2 (6-11 floors) based on actual measurements (with amendments to the Code of Rules 256.1325800.2016 "Electrical installations of residential and public buildings. Design and installation rules") contributes reducing the cost of technological connection in residential construction, as well as reducing the actual unused "locked power" at the same time as reducing electricity losses in power transformers. In the course of the study, an analysis has been made of the actual electrical loads of residential buildings in Moscow for the periods from November 1 to November 30, 2021 and from December 25, 2021 to January 31, 2022. The number of the studied sample for cluster 1 is 91 houses, for cluster 2 - 58 houses. When determining the maximum specific power of a sample set of multi-apartment residential buildings in Moscow in clusters 1 and 2, an average value and a confidence interval have been established, which "covers" the average of the general population with a probability of 95 %; a comparative analysis of the actual specific electrical loads of a residential building with the loads given in the Code of Rules has been carried out. Based on the results of statistical processing of a sample of multi-apartment buildings in clusters 1 and 2, the dependence of the maximum specific power on the number of apartments in a residential building has been determined with a trend line that clearly illustrates the trend in the studied dependence.

Feasibility of Harris Hawks Optimization in Combination with Fuzzy Inference System Predicting Heating Load Energy Inside Buildings

Heating and cooling systems account for a considerable portion of the energy consumed for domestic reasons in Europe. Burning fossil fuels is the main way to produce this energy, which has a detrimental effect on the environment. It is essential to consider a building’s characteristics when determining how much heating and cooling is necessary. As a result, a study of the related buildings’ characteristics, such as the type of cooling and heating systems required for maintaining appropriate indoor air conditions, can help in the design and construction of energy-efficient buildings. Numerous studies have used machine learning to predict cooling and heating systems based on variables that include relative compactness, orientation, overall height, roof area, wall area, surface area, glazing area, and glazing area distribution. Fuzzy logic, however, is not used in any of these methods. In this article, we study a fuzzy logic approach, i.e., HHO−ANFIS (combination of Harris hawks optimization and adaptive neuro-fuzzy interface system), to predict the heating load in residential buildings and investigate the feasibility of this technique in predicting the heating load. Fuzzy techniques obtain perfect results. The analysis results show that the HHO−ANFIS with a population size of 400, the highest value of R2 (0.98709 and 0.98794), and the lowest value of RMSE (0.08769 and 0.08281) in the training and testing dataset, respectively, can predict the heating load with high accuracy. According to the high value of R2 (98%) and low value of RMSE, HHO−ANFIS can be used in predicting the heating load of residential buildings.