Deep Learning for Multivariate Prediction of Building Energy Performance of Residential Buildings

In the quest to minimize energy waste,the energy performance of buildings(EPB)has been a focus because building appliances,such as heating,ventilation,and air conditioning,consume the highest energy.Therefore,effective design and planning for estimating heating load(HL)and cooling load(CL)for energy saving have become paramount.In this vein,efforts have been made to predict the HL and CL using a univariate approach.However,this approach necessitates two models for learning HL and CL,requiring more computational time.Moreover,the one-dimensional(1D)convolutional neural network(CNN)has gained popularity due to its nominal computa-tional complexity,high performance,and low-cost hardware requirement.In this paper,we formulate the prediction as a multivariate regression problem in which the HL and CL are simultaneously predicted using the 1D CNN.Considering the building shape characteristics,one kernel size is adopted to create the receptive fields of the 1D CNN to extract the feature maps,a dense layer to interpret the maps,and an output layer with two neurons to predict the two real-valued responses,HL and CL.As the 1D data are not affected by excessive parameters,the pooling layer is not applied in this implementation.Besides,the use of pooling has been questioned by recent studies.The performance of the proposed model displays a comparative advantage over existing models in terms of the mean squared error(MSE).Thus,the proposed model is effective for EPB prediction because it reduces computational time and significantly lowers the MSE.

Construction of building energy conservation incentive policies under government regulation: Based on the subjects' behavior analysis

Building energy efficiency is a long-term strategy to achieve sustainable development, but the inconsistencies of main interests during the implementation lead to the need for government regulation in building energy conservation. Implementation of building energy efficiency of government regulation covers three aspects of construction and involves relevant participators, so the paper analyzes interests and roles of the related subjects in building energy saving, explore the motivations and its conversion mechanism of each player, and dissect the game relationship of associated earnings of developers' and consumers' behaviors selection under government control. Finally, the paper proposes basic requirements of building incentive policies for related subjects under government control to regulate the main behaviors of subjects in building energy efficient buildings and achieve energy efficiency goals and balance of all parties' benefits.

Supply and demand subject behavior of building energy efficiency in market fostering

Consumers and developers are the market transaction subjects which drive the development of building energy efficiency market. High energy prices, unreasonable heating system, information asymmetry of building energy suppress demand of energy efficiency construction; high technical risk and construction cost, nonstandard market restrict the supply of energy efficiency construction. To promote the development of building energy efficiency, we must set up effective incentive policies for both sides of the market transaction, improve the supervisory system, promote the technological progress, build the information sharing platform, so as to achieve the purpose of cultivating and improving the building energy efficiency market system, regulating the behavior of supply and demand subject, building the mutually beneficial and cooperative partnership, and realizing the balance of interests.

Efficiency-based Pareto Optimization of Building Energy Consumption and Thermal Comfort:A Case Study of a Residential Building in Bushehr,Iran

In Iran,the intensity of energy consumption in the building sector is almost 3 times the world average,and due to the consumption of fossil fuels as the main source of energy in this sector,as well as the lack of optimal design of buildings,it has led to excessive release of toxic gases into the environment.This research develops an efficient approach for the simulation-oriented Pareto optimization(SOPO)of building energy efficiency to assist engineers in optimal building design in early design phases.To this end,EnergyPlus,as one of the most powerful and well-known whole-building simulation programs,is combined with the Multi-objective Ant Colony Optimization(MOACO)algorithm through the JAVA programming language.As a result,the capabilities of JAVA programming are added to EnergyPlus without the use of other plugins and third parties.To evaluate the effectiveness of the developed method,it was performed on a residential building located in the hot and semi-arid region of Iran.To obtain the optimum configuration of the building under investigation,the building rotation,window-to-wall ratio,tilt angle of shading device,depth of shading device,color of the external walls,area of solar collector,tilt angle of solar collector,rotation of solar collector,cooling and heating setpoints of heating,ventilation,and air conditioning(HVAC)system are chosen as decision variables.Further,the building energy consumption(BEC),solar collector efficiency(SCE),and predicted percentage of dissatisfied(PPD)index as a measure of the occupants'thermal comfort level are chosen as the objective functions.The single-objective optimization(SO)and Pareto optimization(PO)are performed.The obtained results are compared to the initial values of the basic model.The optimization results depict that the PO provides optimal solutions more reliable than those obtained by the SOs,owing to the lower value of the deviation index.Moreover,the optimal solutions extracted through the PO are depicted in the form of Pareto fronts.Eventually,the Linear Programming Technique for Multidimensional Analysis of Preference(LINMAP)technique as one of the well-known multi-criteria decision-making(MCDM)methods is utilized to adopt the optimum building configuration from the set of Pareto optimal solutions.Further,the results of PO show that although BEC increases from 136 GJ to 140 GJ,PPD significantly decreases from 26%to 8%and SCE significantly increases from 16%to 25%.The introduced SOPO method suggests an effective and practical approach to obtain optimal solutions during the building design phase and provides an opportunity for building engineers to have a better picture of the range of options for decision-making.In addition,the method presented in this study can be applied to different types of buildings in different climates.

An improved transfer learning strategy for short-term cross-building energy prediction usingdata incremental

The available modelling data shortage issue makes it difficult to guarantee the performance of data-driven building energy prediction(BEP)models for both the newly built buildings and existing information-poor buildings.Both knowledge transfer learning(KTL)and data incremental learning(DIL)can address the data shortage issue of such buildings.For new building scenarios with continuous data accumulation,the performance of BEP models has not been fully investigated considering the data accumulation dynamics.DIL,which can learn dynamic features from accumulated data adapting to the developing trend of new building time-series data and extend BEP model's knowledge,has been rarely studied.Previous studies have shown that the performance of KTL models trained with fixed data can be further improved in scenarios with dynamically changing data.Hence,this study proposes an improved transfer learning cross-BEP strategy continuously updated using the coarse data incremental(CDI)manner.The hybrid KTL-DIL strategy(LSTM-DANN-CDI)uses domain adversarial neural network(DANN)for KLT and long short-term memory(LSTM)as the Baseline BEP model.Performance evaluation is conducted to systematically qualify the effectiveness and applicability of KTL and improved KTL-DIL.Real-world data from six-type 36 buildings of six types are adopted to evaluate the performance of KTL and KTL-DIL in data-driven BEP tasks considering factors like the model increment time interval,the available target and source building data volumes.Compared with LSTM,results indicate that KTL(LSTM-DANN)and the proposed KTL-DIL(LSTM-DANN-CDI)can significantly improve the BEP performance for new buildings with limited data.Compared with the pure KTL strategy LSTM-DANN,the improved KTL-DIL strategy LSTM-DANN-CDI has better prediction performance with an average performance improvement ratio of 60%.

Generative pre-trained transformers(GPT)-based automated data mining for building energy management:Advantages,limitations and the future

Advanced data mining methods have shown a promising capacity in building energy management.However,in the past decade,such methods are rarely applied in practice,since they highly rely on users to customize solutions according to the characteristics of target building energy systems.Hence,the major barrier is that the practical applications of such methods remain laborious.It is necessary to enable computers to have the human-like ability to solve data mining tasks.Generative pre-trained transformers(GPT)might be capable of addressing this issue,as some GPT models such as GPT-3.5 and GPT-4 have shown powerful abilities on interaction with humans,code generation,and inference with common sense and domain knowledge.This study explores the potential of the most advanced GPT model(GPT-4)in three data mining scenarios of building energy management,i.e.,energy load prediction,fault diagnosis,and anomaly detection.A performance evaluation framework is proposed to verify the capabilities of GPT-4 on generating energy load prediction codes,diagnosing device faults,and detecting abnormal system operation patterns.It is demonstrated that GPT-4 can automatically solve most of the data mining tasks in this domain,which overcomes the barrier of practical applications of data mining methods in this domain.In the exploration of GPT-4,its advantages and limitations are also discussed comprehensively for revealing future research directions in this domain.

Evaluation of building energy demand forecast models using multi-attribute decision making approach

With the existence of several conventional and advanced building thermal energy demand forecast models to improve the energy efficiency of buildings,it is hard to find an appropriate,convenient,and efficient model.Evaluations based on statistical indexes(MAE,RMSE,MAPE,etc.)that characterize the accuracy of the forecasts do not help in the identification of the efficient building thermal energy demand forecast tool since they do not reflect the efforts entailed in implementation of the forecast model,i.e.,data collection to production/use phase.Hence,this work presents a Gini Index based Measurement of Alternatives and Ranking according to COmpromise Solution(GI-MARCOS),a hybrid Multi Attribute Decision Making(MADM)approach for the identification of the most efficient building energy demand forecast tool.GI-MARCOS employs(i)GI based objective weight method:assigns meaningful objective weights to the attributes in four phases(1:pre-processing,2:implementation,3:post-processing,and 4:use phase)thereby avoiding unnecessary biases in the expert’s opinion on weights and applicable to domains where there is a lack of domain expertise,and(ii)MARCOS:provides a robust and reliable ranking of alternatives in a dynamic environment.A case study with three alternatives evaluated over three to six attributes in four phases of implementation(pre-processing,implementation,post-processing and use)reveals that the use of GI-MARCOS improved the accuracy of alternatives MLR and BM by 6%and 13%,respectively.Moreover,additional validations state that(i)MLR performs best in Phase 1 and 2,while ANN performs best in Phase 3 and 4 with BM providing a mediocre performance in all four phases,(ii)sensitivity analysis:provides robust ranking with interchange of weights across phases and attributes,and(iii)rank correlation:ranks produce by GI-MARCOS has a high correlation with GRA(0.999),COPRAS(0.9786),and ARAS(0.9775).

Electrochromism-induced adaptive fresh air pre-handling system for building energy saving

Building fresh air supply needs to meet certain regulations and fit people’s ever-growing indoor air quality de-mand.However,fresh air handling requires huge energy consumption that goes against the goal of net-zero energy buildings.Thus,in this work,an adaptive fresh air pre-handling system is designed to reduce the cool-ing and heating loads of HVAC system.The sky-facing surface of the system uses electrochromic mechanism to manipulate the optical properties and thus make full use of solar energy(solar heating)and deep space cold source(radiative cooling)by switching between heating and cooling modes.In the cooling mode,the sky-facing surface shows a transmittance of down to zero,while the reflectance is high at 0.89 on average.In the heating mode,the electrochromic glass is highly transparent,allowing the sunlight to reach the solar heat absorber.To obtain the energy-saving potential under different climates,six cities were selected from various climate regions in China.Results show that the adaptive fresh air pre-handling system can be effective in up to 55.4%time of a year.The maximum energy-saving ratios for medium office,warehouse,and single-family house can reach up to 11.52%,26.62%,and 18.29%,respectively.In addition,the system shows multi-climate adaptability and broad application scenarios,making it a potential solution to building energy saving.

Multi-Time Scale Optimal Scheduling of a Photovoltaic Energy Storage Building System Based on Model Predictive Control

Building emission reduction is an important way to achieve China’s carbon peaking and carbon neutrality goals.Aiming at the problem of low carbon economic operation of a photovoltaic energy storage building system,a multi-time scale optimal scheduling strategy based on model predictive control(MPC)is proposed under the consideration of load optimization.First,load optimization is achieved by controlling the charging time of electric vehicles as well as adjusting the air conditioning operation temperature,and the photovoltaic energy storage building system model is constructed to propose a day-ahead scheduling strategy with the lowest daily operation cost.Second,considering inter-day to intra-day source-load prediction error,an intraday rolling optimal scheduling strategy based on MPC is proposed that dynamically corrects the day-ahead dispatch results to stabilize system power fluctuations and promote photovoltaic consumption.Finally,taking an office building on a summer work day as an example,the effectiveness of the proposed scheduling strategy is verified.The results of the example show that the strategy reduces the total operating cost of the photovoltaic energy storage building system by 17.11%,improves the carbon emission reduction by 7.99%,and the photovoltaic consumption rate reaches 98.57%,improving the system’s low-carbon and economic performance.

A review of validation methods for building energy modeling programs

Building energy simulation analysis plays an important supporting role in the conservation of building energy.Since the early 1980s,researchers have focused on the development and validation of building energy modeling programs(BEMPs)and have basically formed a set of systematic validation methods for BEMPs,mainly including analytical,comparative,and empirical methods.Based on related papers in this field,this study systematically analyzed the application status of validation methods for BEMPs from three aspects,namely,sources of validation cases,comparison parameters,and evaluation indicators.The applicability and characteristics of the three methods in different validation fields and different development stages of BEMPs were summarized.Guidance were proposed for researchers to choose more suitable validation methods and evaluation indicators.In addition,the current development trend of BEMPs and the challenges faced by validation methods were investigated,as well as the existing progress of current validation methods under this trend was analyzed.Subsequently,the development direction of the validation method was clarified.

Influence of urban morphological factors on building energy consumption combined with photovoltaic potential: A case study of residential blocks in central China

Studies on urban energy have been growing in interest,and past research has mostly been focused on studies of urban solar potential or urban building energy consumption independently.However,holistic research on the combination of urban building energy consumption and solar potential at the urban block-scale is required in order to minimize energy use and maximize solar power generation simultaneously.The aim of this study is to comprehensively evaluate the impact of urban morphological factors on photovoltaic(PV)potential and building energy consumption.Firstly,58 residential blocks were classified into 6 categories by k-means clustering.Secondly,3 energy performance factors,which include the energy use intensity(EUI),the energy use intensity combined with PV potential(EUI-PV),and photovoltaic substitution rate(PSR)were calculated for these blocks.The study found that the EUI of the Small Length&High Height blocks was the lowest at around 30 kWh/(m^(2)·y),while the EUI-PV of the Small Length&Low Height blocks was the lowest at around 4.45 kWh/(m^(2)·y),and their PSR was the highest at 87%.Regression modelling was carried out,and the study concluded that the EUI of residential blocks was mainly affected by shape factor,building density and floor area ratio,while EUI-PV and PSR were mainly affected by height and sky view factor.In this study,the results and developed methodology are helpful to provide recommendations and strategies for sustainable planning of residential blocks in central China.

Using urban building energy modeling to quantify the energy performance of residential buildings under climate change

The building sector is facing a challenge in achieving carbon neutrality due to climate change and urbanization.Urban building energy modeling(UBEM)is an effective method to understand the energy use of building stocks at an urban scale and evaluate retrofit scenarios against future weather variations,supporting the implementation of carbon emission reduction policies.Currently,most studies focus on the energy performance of archetype buildings under climate change,which is hard to obtain refined results for individual buildings when scaling up to an urban area.Therefore,this study integrates future weather data with an UBEM approach to assess the impacts of climate change on the energy performance of urban areas,by taking two urban neighborhoods comprising 483 buildings in Geneva,Switzerland as case studies.In this regard,GIS datasets and Swiss building norms were collected to develop an archetype library.The building heating energy consumption was calculated by the UBEM tool—AutoBPS,which was then calibrated against annual metered data.A rapid UBEM calibration method was applied to achieve a percentage error of 2.7%.The calibrated models were then used to assess the impacts of climate change using four future weather datasets out of Shared Socioeconomic Pathways(SSP1-2.6,SSP2-4.5,SSP3-7.0,and SSP5-8.5).The results showed a decrease of 22%–31%and 21%–29%for heating energy consumption,an increase of 113%–173%and 95%–144%for cooling energy consumption in the two neighborhoods by 2050.The average annual heating intensity dropped from 81 kWh/m^(2) in the current typical climate to 57 kWh/m^(2) in the SSP5-8.5,while the cooling intensity rose from 12 kWh/m^(2) to 32 kWh/m^(2).The overall envelope system upgrade reduced the average heating and cooling energy consumption by 41.7%and 18.6%,respectively,in the SSP scenarios.The spatial and temporal distribution of energy consumption change can provide valuable information for future urban energy planning against climate change.

Building energy efficiency and COVID-19 infection risk:Lessons from office room management

To prevent COVID-19 outbreaks,many indoor environments are increasing the volume of fresh air and running air conditioning systems at maximum power.However,it is essential to consider the comfort of indoor occupants and energy consumption simultaneously when controlling the spread of infection.In this study,we simulated the energy consumption of a three-storey office building for postgraduate students and teachers at a university in Beijing.Based on an improved Wells-Riley model,we established an infection risk-energy consumption model considering non-pharmaceutical interventions and human comfort.The infection risk and building energy efficiency under different room occupancy rates on weekdays and at weekends,during different seasons were then evaluated.Energy consumption,based on the real hourly room occupancy rate during weekdays was 43%–55%lower than energy consumption when dynamic room occupancy rate was not considered.If all people wear masks indoors,the total energy consumption could be reduced by 32%–45%and the proportion of energy used for ventilation for epidemic prevention and control could be reduced by 22%–36%during all seasons.When only graduate students wear masks in rooms with a high occupancy,total energy consumption can be reduced by 15%–25%.After optimization,compared with the strict epidemic prevention and control strategy(the effective reproductive number Rt=1 in all rooms),energy consumption during weekdays(weekends)in winter,summer and transition seasons,can be reduced by 45%(74%),43%(69%),and 55%(78%),respectively.The results of this study provide a scientific basis for policies on epidemic prevention and control,carbon emission peak and neutrality,and Healthy China 2030.

Normalized urban heat island (UHI) indicators: Classifying the temporal variation of UHI for building energy simulation (BES) applications

Despite known effects of urban heat island(UHI)on building energy consumption such as increased cooling energy demand,typical building energy simulation(BES)practices lack a standardized approach to incorporate UHI into building energy predictions.The seasonal and diurnal variation of UHI makes the task of incorporating UHI into BES an especially challenging task,often limited by the availability of detailed hourly temperature data at building location.This paper addresses the temporal variation of UHI by deriving four normalized UHI indicators that can successfully capture the seasonal and diurnal variation of UHI.The accuracy of these indicators was established across four climate types including hot and humid(Miami,FL),hot and dry(Los Angeles,CA),cold and dry(Denver,CO),and cold and humid(Chicago,IL),and three building types including office,hospital,and apartments.These four indicators are mean summer daytime UHI,mean summer nighttime UHI,mean winter daytime UHI,and mean winter nighttime UHI,which can accurately predict cooling,heating,and annual energy consumption with mean relative error of less than 1%.Not only do these indicators simplify the application of UHI to BES but also,they provide a new paradigm for UHI data collection,storage,and usage,specifically for the purpose of BES.

Impact of occupant autonomy on satisfaction and building energy efficiency

The philosophy of building energy management is going through a paradigm change from traditional,often inefficient,user-controlled systems to one that is centrally automated with the aid of IoT-enabled technologies.In this context,occupants’perceived control and building automation may seem to be in conflict.The inquiry of this study is rooted in a proposition that while building automation and centralized control systems are assumed to provide indoor comfort and conserve energy use,limiting occupants’control over their work environment may result in dissatisfaction,and in turn decrease productivity.For assessing this hypothesis,data from the post-occupancy evaluation survey of a smart building in a university in Australia was used to analyze the relationships between perceived control,satisfaction,and perceived productivity.Using structural equation modeling,we have found a positive direct effect of occupants’perceived control on overall satisfaction with their working area.Meanwhile,perceived control exerts an influence on perceived productivity through satisfaction.Furthermore,a field experiment conducted in the same building revealed the potential impact that occupant controllability can have on energy saving.We changed the default light settings from automatic on-and-offto manual-on and automatic-off,letting occupants choose themselves whether to switch the light on or not.Interestingly,about half of the participants usually kept the lights off,preferring daylight in their rooms.This also resulted in a reduction in lighting electricity use by 17.8%without any upfront investment and major technical modification.These findings emphasize the important role of perceived control on occupant satisfaction and productivity,as well as on the energy-saving potential of the user-in-the-loop automation of buildings.

Safe operation of online learning data driven model predictive control of building energy systems

Model predictive control is a promising approach to reduce the CO 2 emissions in the building sector.However,the vast modeling effort hampers the widescale practical application.Here,data-driven process models,like artificial neural networks,are well-suited to automatize the modeling.However,the underlying data set strongly determines the quality and reliability of artificial neural networks.In general,the validity domain of a machine learning model is limited to the data that was used to train it.Predictions based on system states outside that domain,so-called extrapolations,are unreliable and can negatively influence the control quality.We present a safe operation approach combined with online learning to deal with extrapolation in data-driven model predictive control.Here,the k-nearest neighbor algorithm is used to detect extrapolation to switch to a robust fallback controller.By continuously retraining the artificial neural networks during operation,we successively increase the validity domain of the artificial neural networks and the control quality.We apply the approach to control a building energy system provided by the BOPTEST framework.We compare controllers based on two data sets,one with extensive system excitation and one with baseline operation.The system is controlled to a fixed temperature set point in baseline operation.Therefore,the artificial neural networks trained on this data set tend to extrapolate in other operating points.We show that safe operation in combination with online learning significantly improves performance.

Plus Energy Buildings:A Numerical Case Study

The feasibility of Plus Energy Building for a sample relevant case is investigated.After a literature review aimed to identify key aspects of this type of buildings,a preliminary evaluation of the thermal performance of a building constructed using conventional material is presented together with a parametric analysis of the impact of typical influential parameters.Solar domestic hot water(SDHW)and photovoltaic systems(PV)are considered in the study.Numerical simulations indicate that for the examined sample case(Beirut in Lebanon)the total annual energy need of conventional building is 87.1 kWh/y.m^(2).About 49%of energy savings can be achieved by improving the building envelope and installing energy efficient technologies.Moreover,about 90%of energy savings in domestic hot water production can be achieved by installing a SDHW system composed of two solar collectors connected in series.Finally,the addition of a grid connected PV array system can significantly mitigate the energy needs of the building leading to an annual excess of energy.

A real-time abnormal operation pattern detection method for building energy systems based on association rule bases

Expert systems are effective for anomaly detection in building energy systems.However,it is usually inefficient to establish comprehensive rule bases manually for complex building energy systems.Association rule mining is available to accelerate the establishment of the rule bases due to its powerful capability of discovering rules from numerous data.This paper proposes a real-time abnormal operation pattern detection method towards building energy systems.It can benefit from both expert systems and association rule mining.Association rules are utilized to establish association rule bases of abnormal and normal operation patterns.The established rule bases are then utilized to develop an expert system for real-time detection of abnormal operation patterns.The proposed method is applied to an actual chiller plant for evaluating its performance.Results show that 15 types of known abnormal operation patterns and 11 types of unknown abnormal operation patterns are detected successfully by the proposed method.

A review of data mining technologies in building energy systems:Load prediction,pattern identification,fault detection and diagnosis

With the advent of the era of big data,buildings have become not only energy-intensive but also data-intensive.Data mining technologies have been widely utilized to release the values of massive amounts of building operation data with an aim of improving the operation performance of building energy systems.This paper aims at making a comprehensive literature review of the applications of data mining technologies in this domain.In general,data mining technologies can be classified into two categories,i.e.,supervised data mining technologies and unsupervised data mining technologies.In this field,supervised data mining technologies are usually utilized for building energy load prediction and fault detection/diagnosis.And unsupervised data mining technologies are usually utilized for building operation pattern identification and fault detection/diagnosis.Comprehensive discussions are made about the strengths and shortcomings of the data mining-based methods.Based on this review,suggestions for future researches are proposed towards effective and efficient data mining solutions for building energy systems.

Computation and field experiment validation of greenhouse energy load using building energy simulation model

Greenhouse Building Energy Simulation(BES)models were developed to estimate the energy load using TRNSYS(ver.16,University of Wisconsin,USA),a commercial BES program.Validation was conducted based on data recorded during field experiments.The BES greenhouse modeling is reliable,as validation showed 5.2%and 5.5%compared with two field experiments,respectively.As the next step,the heating characteristics of the greenhouses were analyzed to predict the maximum and annual total heating loads based on the greenhouse types and target locations in the Republic of Korea using the validated greenhouse model.The BES-computed results indicated that the annual heating load was greatly affected by the local climate conditions of the target region.The annual heating load of greenhouses located in Chuncheon,the northernmost region,was 44.6%higher than greenhouses in Jeju,the southernmost area among the studied regions.The regression models for prediction of maximum heating load of Venlo type greenhouse and widespan type greenhouse were developed based on the BES computed results to easily predict maximum heating load at field and they explained nearly 95%and 80%of the variance in the data set used,respectively,with the predictor variables.Then a BES model of geothermal energy system was additionally designed and incorporated into the BES greenhouse model.The feasibility of the geothermal energy system for greenhouse was estimated through economic analysis.