Building Energy Efficiency Assessment Research Articles

Physics-informed ensemble learning with residual modeling for enhanced building energy prediction

Accurate modeling of building energy use is important to support a diverse spectrum of its downstream applications, such as building energy efficiency assessment, resilience analysis, smart control, etc. As mainstream approaches of building energy modeling, physics-based modeling builds on different fidelities of physics rules yet are usually compromised in modeling accuracy due to insufficiency of physics rules to capture real-world dynamics and incomplete input information. Data-driven approaches are computationally efficient, but black box (uninterpretable) in nature. For improved modeling of building energy use, this work proposes a physics-informed ensemble learning approach in building energy prediction through residual modeling. Specifically, we first analyze the components of building energy use data. Evidence suggests that the building energy use data can be decomposed into physics-driven part, occupant-driven part, and white noise. Second, high-fidelity physics-based building models (EnergyPlus) and low-fidelity ones (RC models) are developed to capture the physics-driven part while time series methods are explored as the residual modeling approach to capture the occupant-driven discrepancies between physics-based simulation and measured building energy use (i.e., residuals). Finally, the physics-informed ensemble learning is proposed to integrate physics-based and data-driven models for enhanced accuracy and robustness of building energy modeling. Results demonstrate 40–90% increase of accuracy between modeling and field observations compared to traditional physics-based modeling methods. Moreover, when the training dataset size is small, the proposed ensemble model overperforms the pure data-driven models, demonstrating its higher robustness in extrapolation scenarios. This work makes fundamental contributions to the development of convergent modeling approaches in the building modeling field.

Building energy efficiency assessment base on predict-center criterion under diversified conditions

With the rapid expanding of urban economy and population, how to reduce the energy consumption and improve energy efficiency of public buildings has become a key issue for energy conservation and urban development. However, due to the diversity of building usage condition, energy consumption data often has problems with nonlinearity, outliers, and diversity, which greatly reduce the accuracy of energy consumption prediction and energy conservation assessment. To overcome the above drawbacks, a regression prediction model of building energy consumption is designed, which cluster the same type of data characteristics to form a subset of equipment through Gaussian mixture clustering, and design the specific normalized adaptive loss function to determine the optimal control parameters of regression model. Furthermore, a novel predict-center energy efficiency evaluation criterion is proposed, and the cumulative distribution pattern is further statistically analyzed. Finally, the energy benchmark evaluation framework is proposed to determine the energy efficiency evaluation grade. Through comparative experimental analysis, it can be seen that the proposed prediction model can adapt to different types of building data, and have better prediction accuracy and convergence speed. The consistency and robustness of the benchmark evaluation framework and method are optimal.

Evidence-based numerical building model enhancement and building energy efficiency evaluation in the case of Morocco

This paper presents a framework for numerical building validation enhancement based on detailed building specifications from in-situ measurements and evidence-based validation assessment undertaken on a detached sustainable lightweight building in a semi-arid climate. The validation process has been undergone in a set of controlled experiments – a free-float period, and steady-state internal temperatures. The validation was conducted for a complete year with a 1-min time step for the hourly indoor temperature and the variable refrigerant flow (VRF) energy consumption. The initial baseline model was improved by three series of validation steps per three different field measurements including thermal transmittance, glazing thermal and optical properties, and airtightness. Then, the accurate and validated model was used for building energy efficiency assessment in 12 regions of Morocco. This study aims to assess the effect of accurate building characteristics values on the numerical model enhancement. The initial CV(RMSE) and NMBE have improved respectively from 14.58 % and −11.23 %–7.85 % and 1.86 % for the indoor temperature. Besides, from 31.17 % to 14.37 %–20.57 % and 9.77 % for energy consumption. The findings demonstrate that the lightweight construction with the use of a variable refrigerant flow system could be energy efficient in the southern regions of Morocco.

A new method of evaluating energy efficiency of public buildings in China

Traditional building energy evaluation methods usually adopt a single energy use indicator as the benchmark. However, such single-indicator based methods often lead to a paradox that switching off building service equipment or systems is equivalent to energy saving. To avoid such paradox for a more pragmatic and comprehensive evaluation of building energy use, this paper aims to establish a robust evaluation model of the operational energy efficiency for public buildings by coupling the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation (FCE). Firstly, 23 quantitative indexes and 7 qualitative indexes are extracted from existing building energy codes/standards in the input-output perspective of energy performance evaluations for public buildings. The AHP is then used to determine the weight of each index based on a proposed index correction method, which extends the range of applicability of the index system. Finally, a three-level comprehensive evaluation model is established for the operational energy efficiency of public buildings. Furthermore, a case study is conducted on a typical office building to validate the evaluation results with the proposed model. The case building achieves an overall score of 84.9 at a “Good” level, and corresponding recommendations are made for further improving building performance indexes. The proposed method is of great significance to developing building energy efficiency assessment systems and guidelines in China and over the world.

Streamlining building energy efficiency assessment through integration of uncertainty analysis and full scale energy simulations

Asset Score is a standardized rating system and tool for assessing a building's energy-related systems in the United States. The web-based tool models building energy use under standard operating conditions to rate the energy efficiency of the as-built building systems and enable level comparisons of building assets. With basic characteristics entered by users, the tool creates simplified EnergyPlus building models to support the rating analysis. However, even with a reduced set of model inputs, data collection remains a challenge and the commercial building market demands a more simplified entry point to the rating system. This paper discusses a hybrid method that combines regression models with real-time simulations to allow users to enter as few as seven building parameters to quickly assess the building energy performance prior to a full-scale analysis. Built upon large-scale building stock simulations, a random forest approach was used to develop a set of regression models for various building use types. The majority of the Asset Score tool inputs were sampled extensively and fed into the regression models. These were combined with inferred inputs and user-defined uncertainty levels to create a distribution of possible energy use intensities for the building and its Preview score. With additional user inputs, the regression model can be transferred to an energy model for a full-scale energy simulation. The streamlined Asset Score Preview assessment provides an easy entry point to a full Asset Score assessment. It also enables users who manage a large number of buildings to screen and prioritize buildings that can benefit most from a more detailed evaluation and possible energy efficiency upgrades without intensive data collection.

City-wide Building Energy Efficiency Assessment Using EPC Data

The Energy Performance Certificate (EPC) requirements in Europe have provided rich data of energy efficiency status of individual buildings at scale, allowing appropriate assessments to be carried out without the need of conducting additional surveys. By 2012, the EPC data in England and Wales in the UK has reached a coverage of up to 45% of the entire building stock (DECC 2014), and the number of new certificates added every year is over 1 million. The work presented here seeks to understand the potential of using such dataset to deliver systematic analysis of energy efficiency of buildings at a city scale. This study utilises all EPC datasets available for the city of Southampton, UK, and developed an automatic geographic-referencing methodology so the EPC data can be integrated onto geographic information systems (GIS). Such methodology allows large quantity of EPC data to be analysed spatially, facilitating the assessment of energy performance of different regions in a city. The results show clearly areas in the city that have the lowest or highest level of performance in terms of buildings’ energy efficiency, and revealed the impact of certain building intervention measures (such insulation, double glazing) on the energy consumption within the considered buildings. The analyses show that factors such as the existence of high streets and new building developments have significant influence on the energy efficiency in the city where these are present. The geographic-referencing methodology developed in this study has the potential to be utilised in a wide range of subjects, bridging the current gap of data availability, allowing building related datasets to be incorporated with GIS analysis.

Identifying and weighting indicators of building energy efficiency assessment in Ghana

Ghana a sub-Saharan country has seen relative improvements in some aspects of the economy howbeit the energy supply deficit within the region is a burgeoning problem. In most emerging markets, the building sector is among the sectors increasing most rapidly; and has seen the uptake of building energy efficiency assessment worldwide. In this study a weighting system is developed to form the basis of building energy efficiency assessment tool for Ghana. In achieving this a Delphi-Analytic Hierarchy Process (AHP) framework is presented to analyse building energy indicators. The framework consists of three main steps. Firstly, the identification of various indicators. Secondly the Delphi method is applied and an indicator list of 21 is determined. In the third step, an analytical hierarchy process model has been conducted and the expert Delphi method has been used to obtain weighted list of these identified indicators from professionals and highly informed local experts from government, academic and industry. Results from the AHP revealed that "building design" and "energy efficiency of building facilities" are of top priority to the Ghanaian built environment. It is argued that the development of the weighting system brings about a new appreciation of climate influence on the built environment and its corresponding effect on building energy efficiency measurement. The customized weighting system does not eliminate the socio-economic environment of the region in question but provides the recognition of variables necessary for effective measurement of building energy efficiency.

Developing a Building Energy Efficiency Assessment Tool for Office Buildings in Ghana: Delphic Consultation Approach

Abstract In Ghana, the inability to solve peak demand constraints by finding a balance between reducing demand and increasing supply has resulted in power rationing coupled with erratic electricity supply. Various studies have reported the enormous influence energy assessment tools, contribute to solving building energy demand. However, no building energy standards are in place in Ghana and this is aggravated by lack of data for building energy consumption. As a first step towards developing a building energy efficiency assessment tool this paper aims to identify applicable energy efficient building assessment categories and criteria for the Ghanaian Built environment. As building assessment methods involve multi-dimensional criteria, a consensus based approach is used to conduct the research. Hence, the Delphi technique is selected and conducted in two successive consultation rounds involving professionals and highly informed local experts from academia, government and industry in the domain of building energy assessment methods. The results reveal that international assessment methods are not fully applicable to the Ghana built environment, as reflected in the identification of new energy efficient building assessment criteria. The research is focused in Ghana and similar developing countries grappling with building energy problems. It is expected that findings from the study will provide further directions towards the full development of building energy assessment tool in such regions.

A holistic method to assess building energy efficiency combining D-S theory and the evidential reasoning approach

The assessment of building energy efficiency is one of the most effective measures for reducing building energy consumption. This paper proposes a holistic method (HMEEB) for assessing and certifying energy efficiency of buildings based on the D-S (Dempster-Shafer) theory of evidence and the Evidential Reasoning (ER) approach. HMEEB has three main features: (i) it provides both a method to assess and certify building energy efficiency, and exists as an analytical tool to identify improvement opportunities; (ii) it combines a wealth of information on building energy efficiency assessment, including identification of indicators and a weighting mechanism; and (iii) it provides a method to identify and deal with inherent uncertainties within the assessment procedure. This paper demonstrates the robustness, flexibility and effectiveness of the proposed method, using two examples to assess the energy efficiency of two residential buildings, both located in the ‘Hot Summer and Cold Winter’ zone in China. The proposed certification method provides detailed recommendations for policymakers in the context of carbon emission reduction targets and promoting energy efficiency in the built environment. The method is transferable to other countries and regions, using an indicator weighting system to modify local climatic, economic and social factors.

Weighting indicators of building energy efficiency assessment taking account of experts’ priority

Analytic hierarchy process (Group AHP) is combined with two different methods of assigning experts’ priority to weight indicators in building energy efficiency assessment. One is to assign the experts’ priority averagely, and the other is to use cluster analysis to assign experts’ priority. The results show that, 1) Different expert’s priority assigns result in great different weights of indicators in building energy efficiency assessment, therefore, the method of assigning experts’ priority should be taken into account carefully while weighting indicators of building energy efficiency assessment using Group AHP; 2) Three indicators are found to be overwhelmingly important in residential building energy efficiency assessment in the hot summer and cold winter zone in China. They are ‘Outdoor & indoor shadow’, ‘Heating & air-conditioning facilities’ and ‘Insulation of envelope’; 3) The method combining cluster analysis with Group AHP to weight indicator of building energy efficiency assessment has the advantage of finding overwhelming important indicator, whereas, some less important indicators have a tendency to be ignored. A useful reference is provided for building energy conservation including policy revision and energy efficient residential building design.