Non-domestic buildings contribute 20% of the UK’s annual carbon emissions. A contribution exacerbated by its ageing stock of which only 7% is considered new-build. Consequently, the government has ...set regulations to decrease the amount of energy take-up by buildings which currently favour deep energy retrofitting analysis for decision-making and demonstrating compliance. Due to the size and complexity of non-domestic buildings, identifying optimal retrofit packages can be very challenging. The need for effective decision-making has led to the wide adoption of artificial intelligence in the retrofit strategy design process. However, the vast retrofit solution space and high time-complexity of energy simulations inhibit artificial intelligence’s application. This paper presents an energy performance prediction model for non-domestic buildings supported by machine learning. The aim of the model is to provide a rapid energy performance estimation engine for assisting multi-objective optimisation of non-domestic buildings energy retrofit planning. The study lays out the process of model development from the investigation of requirements and feature extraction to the application on a case study. It employs sensitivity analysis methods to evaluate the effectiveness of the feature set in covering retrofit technologies. The machine learning model which is optimised using advanced evolutionary algorithms provide a robust and reliable tool for building analysts enabling them to meaningfully explore the expanding solution space. The model is evaluated by assessing three thousand retrofit variations of a case study building, achieving a root mean square error of 1.02 kgCO2∕m2×year equal to 1.7% of error.
•Addressed impracticality of optimisation methods in supporting deep energy retrofit.•A machine learning model to calculate non-domestic buildings’ energy performance.•Identified essential features of non-domestic buildings affecting energy performance.•TOptimised the model by tuning hyperparameters using an evolutionary algorithm.•Evaluated model performance by scoring thousands of variations in a sample building.
•EU policy efforts on energy efficiency in buildings stared in the 1970s in response to the oil crisis.•The first comprehensive EU policy was the SAVE directive in 1992, introducing policy actions ...still relevant today.•A major step forward was the Energy Performance of Buildings Directive in 2002 and its subsequent amendments.•Mandatory energy performance standards are progressively converging towards near zero energy buildings.•Additional policies and financing are needed for the full decarbonisation of the building stock.
The reduction of energy demand in buildings through the adoption of energy efficiency policy is a key pillar of the European Union (EU) climate and energy strategy. Energy efficiency first emerged in the EU energy policy agenda in the 1970s and was progressively transformed with shifting global and EU energy and climate policies and priorities. The paper offers a review of EU energy policies spanning over the last half century with a focus on policy instruments to encourage measures on energy efficiency in new and existing buildings. Starting from early policies set by the EU in response to the Oil Embargo in the 1973, the paper discusses the impact of EU policies in stimulating energy efficiency improvements in the building sector ranging from the SAVE Directive to the recently 2018 updated Energy Performance of Buildings Directive and Energy Efficiency Directive. The review explores the progress made over the last 50 years in addressing energy efficiency in buildings and highlights successes as well as remaining challenges. It discusses the impact of political priorities in reshaping how energy efficiency is addressed by EU policymakers, leading to a holistic approach to buildings, and provides insights and suggestions on how to further exploit the EU potential to save energy from buildings.
Urban planners, local authorities, and energy policymakers often develop strategic sustainable energy plans for the urban building stock in order to minimize overall energy consumption and emissions. ...Planning at such scales could be informed by building stock modeling using existing building data and Geographic Information System-based mapping. However, implementing these processes involves several issues, namely, data availability, data inconsistency, data scalability, data integration, geocoding, and data privacy. This research addresses the aforementioned information challenges by proposing a generalized integrated methodology that implements bottom-up, data-driven, and spatial modeling approaches for multi-scale Geographic Information System mapping of building energy modeling. This study uses the Irish building stock to map building energy performance at multiple scales. The generalized data-driven methodology uses approximately 650,000 Irish Energy Performance Certificates buildings data to predict more than 2 million buildings’ energy performance. In this case, the approach delivers a prediction accuracy of 88% using deep learning algorithms. These prediction results are then used for spatial modeling at multiple scales from the individual building level to a national level. Furthermore, these maps are coupled with available spatial resources (social, economic, or environmental data) for energy planning, analysis, and support decision-making. The modeling results identify clusters of buildings that have a significant potential for energy savings within any specific region. Geographic Information System-based modeling aids stakeholders in identifying priority areas for implementing energy efficiency measures. Furthermore, the stakeholders could target local communities for retrofit campaigns, which would enhance the implementation of sustainable energy policy decisions.
•Evaluation of existing approaches for GIS-based building energy and data modeling.•Generalized methodology to predict building energy performance on a large scale.•Data-driven approaches for GIS-based building energy modeling.•Formulated GIS maps identify areas with energy savings potential.•The study facilitates energy planning, analysis, and supports decision-making.
•Predicting annual building energy performance for 25,000 residential buildings.•Introduction of QLattice designed for prediction performance and explainability.•Comparing novel QLattice with XGB, ...ANN, MLR, SVR.•QLattice exhibits promising results regarding prediction performance.•QLattice is more explainable than most established machine learning algorithms.
The global building sector is responsible for nearly 40% of total carbon emissions, offering great potential to move closer to set climate goals. Energy performance certificates designed to increase the energy efficiency of buildings require accurate predictions of building energy performance. With significant advances in information and communication technology, data-driven methods have been introduced into building energy performance research demonstrating high computational efficiency and prediction performance. However, most studies focus on prediction performance without considering the potential of explainable artificial intelligence. To bridge this gap, the novel QLattice algorithm, designed to satisfy both aspects, is applied to a dataset of over 25,000 German residential buildings for predicting annual building energy performance. The prediction performance, computation time, and explainability of the QLattice is compared to the established machine learning algorithms artificial neural network, support vector regression, extreme gradient boosting, and multiple-linear regression in a case study, variable importance analyzed, and appropriate applications proposed. The results show quite strongly that the QLattice should be further considered in the research of energy performance certificates and may be a potential alternative to established machine learning algorithms for other prediction tasks in energy research.
Achieving carbon neutrality by 2050 requires evaluating and retrofitting existing buildings. However, despite the numerous studies on energy analytics, they usually focus on energy consumption ...patterns and motifs rather than encompassing various energy usage characteristics. This study proposes a novel symbolic hierarchical clustering for building energy analytics at the city level. It utilizes change-point model (CPM) parameters to represent building energy usage, performance, occupant behavioral characteristics. The clustering method based on the CPM parameters defines energy performance signatures (EPS) for determining their energy characteristics and as symbolic data transformation. In a case study conducted in Gangwon, South Korea, five different energy performance signatures (EPSs 1–5) showing their unique energy characteristics were determined for commercial buildings. EPS1 to 3 were classified as signatures with good performance (65.5% of all buildings) while EPS4 and 5 were classified as signatures with bad performance (34.5%). Using this EPS symbolic data, an EPS map was visualized and analyzed from various perspectives. For example, buildings that showed a continuous or overall decline in envelope performance over five years were among the oldest buildings (construction completion date closer to 1978; 7.9%). Despite poor envelope performance, buildings with lower energy usage showed a tendency for occupants to delay heating (28.4%). The proposed method can contribute to the data-driven building energy analytics in providing detailed insights into energy usage patterns, building energy performance, and occupant behavioral characteristics at the city level. The effectiveness of open-source energy data for urban building energy analysis would be improved through the proposed method.
Display omitted
•Energy performance signature (EPS)-based clustering is proposed for urban building energy analysis.•A combined data-driven five-parameter change-point model and clustering using symbolically transformed data are proposed.•A case study is conducted to analyze energy usage characteristics of commercial buildings in Gangwon, South Korea.•The EPS map from the proposed method provides information on the change in envelope performance, energy consumption pattern, and occupant behavior.
•Use of thermal default values in energy performance certification exaggerates benefits of energy-led refurbishments.•Energy consumption is potentially overestimated by 22% in Irish post-building ...regulation dwellings.•Energy consumption is potentially overestimated by 70% in Irish pre-building regulation dwellings.•A calculation procedure is derived to obtain a realistic energy refurbishment payback when using thermal default values.
Energy Performance Certificates (EPCs), are issued when dwellings are constructed, sold or leased in the EU, are the foremost source of information on the energy performance of the EU’s building stock. Where the cost of obtaining the required data is prohibitive, EPC assessors use nationally applicable default-values. To avoid wrongly-higher EPC ratings for all existing dwellings, a standardised thermal bridging transmittance coefficient (Y-value) is typically adopted together with worst-case overall heat loss coefficients (U-values). These default U-values for roofs, walls and floors are drawn from building codes and regulations applicable at time of construction. Many older dwellings have undergone significant building fabric upgrades. Therefore, default U-values are considerably higher than the real U-values of those upgraded houses. This causes a systematic ‘default effect’ error in large national EPC datasets. For the dataset considered thermal default use overestimates potential primary energy savings from upgrading by 22% and by 70% in dwellings built before after and before thermal building regulations respectively. A methodology has been developed that derives from an EPC dataset, a method for calculating a realistic energy-improvement payback when use of pessimistic default U-values is unavoidable.
•Establishes generalisable methodology to create a stock model from EPC datasets.•Renders transparent; process of characterising reference dwellings from an EPC dataset.•Data created can be used as ...inputs to determine cost-optimal energy refurbishments.•Presents data as required formerly by EU Commission Delegated Regulation No 244/2012.•Largely default-free characterisation based on large high quality empirical dataset.
Average reference dwellings representing a predominant housing typology are defined in this work. Specifying such reference buildings is a prerequisite for (i) calculating cost-optimal energy performance requirements for buildings and building elements and (ii) ensuring valid calculations of national building energy consumption. In the EU, an Energy Performance Certificate (EPC) rating is an assessment of the energy consumption of a dwelling. The use of inappropriate default-values for the building envelope thermal transmittance coefficients (U-values) and standardised thermal bridging transmittance coefficients (Y-values) in the production of EPCs leads to an over-estimation of potential energy savings from interventions in the existing dwelling stock. A methodology is presented for the derivation of simplified default-free inputs to a bottom-up residential cost-optimality energy consumption model from an EPC dataset. 35 reference dwellings (RDs) are employed to appropriately characterise 406,918 dwellings. Use of these RDs enable quantification of (i) the energy saving potential of a predominant housing typology, (ii) the effect of default U-value and standardised Y-value use on the prebound effect in dwellings (iii) overall national building energy consumption.
Display omitted
•Implementation of the EPBD in Southern European countries is analysed.•Italy widely leads the way in scientific production in the field.•Optional application of the standard impedes ...homogeneous progress.•France leads the transposition of European Directives into its national regulation.•A greater number of common objectives with mandatory compliance should be implemented.
The Energy Performance of Buildings Directive covers a broad range of policies and supportive measures designed to help European Union national governments boost energy performance of buildings and improve existing building stock. This review is a comparative study of Southern European countries with respect to their transposition of successive European Directives developed by each Member State through their own regulations and implementations of specific energy performance requirements. The article presents, on the one hand, a complete study of the literature, showing that Italy, Spain and Portugal are the countries that have developed a greater number of articles with content strongly focused on the scope of this work, with Energy and Buildings by far being the reference journal on this topic. On the other hand, conclusions about the applications carried out by each Member State are shown, such as the Directives that were implemented in a reasonable time, although not all countries have done so at the same pace or with the same degree of development. Many of the Southern European countries are not adequately prepared for the correct and effective implementation of nearly zero-energy buildings, and there are still many improvements that should be addressed in the coming years. For these reasons and to increase the effectiveness of the framework Directive, a greater number of common objectives subject to mandatory compliance should be considered. Establishing basic formulas and methodologies while ensuring flexibility for Member States to account for their own unique characteristics is necessary to achieve these common objectives.
•Establishes predominant construction characteristics of Irish dwellings.•Establishes likely U-values of predominant /prevalent composite constructions.•Establishes U-values for use to make EPC ...datasets more representative.•Presents improved data to narrow the thermal energy performance gap.•Makes U-value calculation for predominant constructions transparent and accessible.
Energy Performance Certificates (EPCs) are the foremost source of information on the energy performance of the EU’s building stock. Inherent in all EPC methodologies are trade-offs between reproducibility, accuracy, assessor expertise and costs. During an assessment, where accurate building data acquisition would be excessively invasive or costly, nationally specified default values are used.
Default values are necessarily pessimistic to; avoid a better-than-merited rating, enable homeowners to know the advantage of energetic refurbishment, encourage homeowners to record upgrades informing EPCs, and propel assessors to seek-out information to provide an accurate rating.
This work reviews default U-value use across Europe and the UK before focusing on Ireland’s EPC methodology, finding 1 in 3 entries in the Irish EPC dataset to be characterised on default U-values in 2020, leading to the dataset presenting an overly pessimistic view of the stock, thus lacking validity.
To mitigate the thermal energy performance gap between theoretical rated energy consumption and actual or likely energy consumption arising from the selection of unrealistic default values for parameters; this work reviews the literature to identify and catalogue predominant/prevalent construction characteristics over time and calculates associated U-values that can be substituted for unrealistic defaults, thereby making the EPC dataset more representative and resultant national building energy stock models more robust.
A total of 38 wall (8 predominant) and 4 predominant roof types were characterised finding differences between default and realistic U-values to be as high as 187 %. A generalisable find-and-replace methodology for the Irish EPC database is also proposed.
•PCMs integrated building envelope and equipment in 2004∼2017 are reviewed.•Melting temperature range of PCMs used for envelope is 10∼39°C.•Melting temperature range of PCMs used for equipment is ...−15.4∼77°C.•PCMs’ positive effects on energy saving and thermal comfort are demonstrated.•The existing gaps in the research works are identified and classified as 5 aspects.
Confronted with the crises of the growing resource shortages and continued deterioration of the environment, building energy performance improvement using phase change materials has received much attention in recent years. This review work provides an update on recent developments, 2004∼2017, in phase change materials used to optimize building envelope and equipment. Firstly, a review of building envelope optimization methods by integrating surrounding wall, roof, and floor with phase change materials, is given. This is followed by reporting articles on building equipment optimized with phase change materials to reduce regular energy consumption. Series of air cooling, heating, and ventilation systems coupled with thermal energy storage were comparatively investigated. Finally, the existing gaps in the research works on energy performance improvement with phase change materials were identified, and recommendations offered as authors’ viewpoints in 5 aspects. It was also found that the phase change temperature range of PCMs used was changed from 10∼39°C for envelope to −15.4∼77°C for equipment. We believe this comprehensive review might provide an overview of the analytical tools for scholars, engineers, developers, and policy designers, and shed new light on the designing and performance optimization for PCMs used in building envelope and equipment.