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.

Optimizing building retrofit through data analytics:A study of multi-objective optimization and surrogate models derived from energy performance certificates

The building stock is responsible for a large share of global energy consumption and greenhouse gas emissions,therefore,it is critical to promote building retrofit to achieve the proposed carbon and energy neutrality goals.One of the policies implemented in recent years was the Energy Performance Certificate(EPC)policy,which proposes building stock benchmarking to identify buildings that require rehabilitation.However,research shows that these mechanisms fail to engage stakeholders in the retrofit process because it is widely seen as a mandatory and complex bureaucracy.This study makes use of an EPC database to integrate machine learning techniques with multi-objective optimization and develop an interface capable of(1)predicting a building’s,or household’s,energy needs;and(2)providing the user with optimum retrofit solutions,costs,and return on investment.The goal is to provide an open-source,easy-to-use interface that guides the user in the building retrofit process.The energy and EPC prediction models show a coefficient of determination(R2)of 0.84 and 0.79,and the optimization results for one case study EPC with a 2000€budget limit inÉvora,Portugal,show decreases of up to 60%in energy needs and return on investments of up to 7 in 3 years.

A Study on the Evaluation of Heating and Cooling Energy Efficiency in Residential Buildings for Climatic Zones of Turkey

In Turkey, most of the common type projects of mass production residential buildings are being developed and constructed by TOK1 （Housing Development Administration of Turkey）. These buildings, in which energy efficient approach has been disregarded for years, cause to gradually increase on heating and cooling energy consumptions. In regards to national economics, it is essential to evaluate energy efficiency and to develop suggestions to decrease energy consumptions in residential buildings. To achieve appropriate solutions, cost evaluation also becomes necessary. Therefore, this paper aims to introduce a study which serves the purpose of producing a choice of energy efficient solutions in order to reduce energy consumptions and energy cost. In this study, different heating and cooling energy efficient scenarios have been developed for a selected residential building, constructed by TOKI, for climatic zones of Turkey. For each scenario, energy simulations have been executed by means of the simulation program--DesignBuilder, the user-friendly visual interface of EnergyPlus, and cost analysis has been carried out by using the net present value and discounted payback period method. As a result, energy and cost effective solutions have been presented and discussed for different climatic zones.

Energy Performance versus Indoor Environment QualitymNon-traditional Form of Elementary Schools Renovation in Terms of Slovak Republic

The content of contribution is to analyse suggested renovation of school building in term of energy performance and indoor environment quality. There were three selected variants of possible reno ration of school building. At first, it was installation of equipment for heat recovery into existing mechanical ventilation system. There were further evaluated possibilities how to use glass atrium or ground air-heat exchanger in mechanical ventilation system. These suggested variants were analysed in field of energy performance, namely in term of impacts on heat demand for space heating in order to keep required parameters of indoor environment quality according to standard STN EN 15251 （operative temperature, relative air humidity, air change rate）. The analysis was elaborated by using energy simulation tool Design Builder in order to evaluate yearlong operation of buildings.

A whole-building data-driven fault detection and diagnosis approach for public buildings in hot climate regions

Fault detection and diagnosis(FDD)approaches comprise three main pillars:model-based,knowledge-based,and data-driven strategies.Data-driven approaches prioritise operational data and do not necessitate in-depth understanding of the system’s background;yet,significant amounts of data is required,which often poses challenges to researchers.Since simulated data is inexpensive and can run numerous faults types with varying severities and time periods,it has been used in data-driven FDD analysis.However,the majority of FDD approaches are implemented at the system level of buildings.However,most buildings have numerous systems with distinct features.Furthermore,using individualised system-level analysis makes it difficult to see system-to-system relationships.Currently,there is a significant underrepresentation of research that investigate the applications of FDD models under whole-building scenarios,so as to identify a wider range of energy consumption related faults in buildings.Furthermore,since data-driven approaches significantly depend on the quantities of training data,it becomes challenging to diagnose faults that have limited features.As a result,this study diagnoses numerous building systems faults,including single and simultaneous faults with limited features.This is implemented within the context of the whole-building energy performance of religious buildings in hot climatic areas,employing data-driven FDD methodologies.Various multi-class classification approaches were investigated to classify both the normal condition and faulty classes.Furthermore,feature extraction methodologies were compared to quantify their potential for improving the diagnosis.In addition to the classification evaluation metrics,one-way ANOVA and Tukey-Kramer tests were implemented to examine the significance of the reported performance differences.RF classifier obtained highest classification accuracy during validation and testing with about 90%,indicating a promising performance in whole-building faults analysis.The adoption of feature extraction techniques did not improve classification performance,thereby emphasising that some classifiers may perform better with high-dimensional datasets.

Multi-objective optimization of thermochromic glazing based on daylight and energy performance evaluation

Many efforts have been detected to investigate thermochromic(TC)glazing for improving building energy saving,while only a few approaches for daylight performance analysis.In this study,the performance of TC glazing is investigated based on multi-objective optimization for minimizing energy demand while maximizing daylight availability.The effects of five parameters including transition temperature,solar transmittance in clear state,solar transmittance modulation ability,luminous transmittance in clear state,and luminous modulation ability on the building energy consumption and useful daylighting illuminance(UDI_(300-3000))are examined.Linear Programming Technique for Multi-dimensional Analysis of Preference(LINMAP)is used for the decision-making of Pareto frontier.This research aims to explore the ideal thermochromic glazing by considering the daylight and energy performance of a typical office room,taking the weather condition of Xiamen,China as an example.Although it is impossible to achieve both optimal values of energy consumption and UDI_(300-3000)simultaneously,the proposed multi-objective optimization method could still provide low energy consumption with sufficient daylight.The non-dominated sorting of Pareto optimal solution(POS)demonstrated that the optimum building energy consumption and UDI_(300-3000)for single glazed windows are 46.64 kWh/m^(2)and 70.92%,respectively,while the values for double glazed windows are 44.40 kWh/m^(2)and 71.88%,respectively.The selected hypothetical TC windows can improve the building energy and daylighting performance simultaneously when compared with traditional clear single and double glazed windows.The presented framework provides a multi-objective optimization method to determine the most suitable TC glazing technologies for designers and architects during the design and retrofit procedure.

Evaluating diverse patterns of occupant behavior regarding control-based activities in energy performance simulation

Simulation is recognized as an effective tool for building energy performance assessment during design or retrofit processes. Nevertheless, simulation models yield deviating outcomes from the actual building performance and a significant portion of this deviation originates from the dynamic nature of occupant behavior. Literature on occupant behavior indicates that occupant behavior is not integrated into building energy performance assessment procedures with appropriate resolution, instead they are accepted as assumed and fixed data sets that usually represent the presence of occupants. This study attempts to evaluate the effect of diverse patterns of occupant behavior on energy performance simulation for office buildings. Diverse levels of sensitivity of occupant behavior on control-based activities such as using lighting apparatus, adjusting thermostat settings, and presence in space are employed through three diverse occupant behavior patterns. These occupancy patterns are correlated with three identical office spaces simulated within a conceptual office building. EDSL Tas is used to run building energy performance simulations. Effects of occupant behavior patterns on simulation outcomes are compared for five sample winter and summer workdays, with respect to heating and cooling loads. Results present findings on how diversity of occupancy profiles influences the consumption outcomes.

Low Energy Certificate——An exploration on optimization and evaluation of energy-efficient building envelope

Energy saving is the crucial task of green architecture,energy-saving design and evaluation should be interactive.Low Energy Certificate(LEC),an interactive computer program for energy efficiency and certification of building envelope,is briefly introduced in this paper in aspects of certification standards,procedure,methods etc.Through the evaluation report of Innovation-pavilion PoI features,reference values of LEC are presented.

Do green roofs really provide significant energy saving in a Mediterranean climate? Critical evaluation based on different case studies

Green roofs represent a growing technology that is spreading increasingly and rapidly throughout the building sector.The latest national and international regulations are promoting their application for refurbishments and new buildings to increase the energy efficiency of the building stock.In recent years,vegetative coverings have been studied to demonstrate their multiple benefits,such as the reduction of the urban heat island phenomenon and the increase in the albedo of cities.On the contrary,this study aims to verify the actual benefit of applying a green roof on a sloped cover compared with installing a highly insulated tiled roof.The EnergyPlus tool has been used to perform dynamic analyses,which has allowed to understand the behavior of two different stratigraphies in accordance with weather conditions,rain,and irrigation profiles.Results have shown that the installation of a green roof cannot always be considered the best solution for reducing building energy consumption,especially if compared with a classic highly insulated clay tile roof.In terms of summer air conditioning,the maximum saving is 0.72 kWh/m2.The presence of water in the soil has also been proven a crucial factor.

To Promote Green Buildings in China: Lessons from the USA and EU

Buildings have contributed to the energy shortage, pollution and global climate change. To promote green buildings is the way access to the sustainable development. Currently, China has issued some regulations and systems to boost the green building. However, problems lie in China and the systems are not effective. USA and EU have rich experiences and fairly sophisticated legislation and policies to develop green building. China may get some lessens from these countries. This paper will make an overview of legal framework and main system of green building in China, then, analyses some important legal systems and typical case related green building in the USA and EU. Further, problems were pointed out in the China based on the comparative analysis of these countries. Lastly, according to the condition in China and lessons from USA and EU, this paper will put some suggests to promote green building, such as, take some measures to enhance the awareness of the stakeholders, create multi- incentive tools and so on.