Optimization Of Building Energy Performance Research Articles

BIM-supported automatic energy performance analysis for green building design using explainable machine learning and multi-objective optimization

Supported by the combination of the advanced BIM technique with intelligent algorithms, this paper develops a systematic framework using explainable machine learning and multi-objective optimization to realize the automatic prediction and optimization of building energy performance towards the sustainable development goal. There are three critical parts incorporated, including the DesignBuilder simulation, BO-LGBM (Bayesian optimization-LightGBM) and an explainable method SHAP (SHapley Additive explanation)-based prediction and explanation of building energy performance, and AGE-MOEA algorithm-based multi-objective optimization (MOO) under sources of uncertainty. It has been verified in a case study for green building design. Results show that: (1) The predictive BO-LGBM model can make a highly precise prediction in agreement with the simulation data, reaching up the R2 larger than 93.4% and MAPE smaller than 2.13%. From the SHAP calculation, features related to the HAVC (Heating Ventilation and Air Conditioning) system tend to contribute more to affecting the prediction results. (2) The AGE-MOEA-based optimization can identify a set of Pareto optimal solutions in simultaneously minimizing the building energy consumption, CO2 emission, and indoor thermal discomfort degree, arriving at the highest optimization rate of 13.43% under proper adjustment of certain features. (3) In the MOO task, the consideration of model and data uncertainty by prediction intervals and Monte-Carlo simulation can further increase the optimization rate by around 4.0% than the deterministic scenario, resulting in more desired strategies in optimizing the green building performance. In short, this paper enriches the area of green building development. For one thing, it raises the transparency and interpretability of machine learning to make the prediction more convincing. For another, it efficiently determines the passive and active design solutions along with the detailed profile of influential factors for green building design.

Optimization of building energy performance through passive design measures in the Mediterranean climate

This paper presents a numerical study combining different passive measures to improve the energy efficiency of a building. These measures include night ventilation and physical design such as building materials, thermal insulation as well as window configuration combined with winter and summer solar shading. The study focuses on a basic classroom prototype that complies with the Algerian buildings. It took the city of Constantine in Algeria as a case study for the warm temperate climate of the Mediterranean regions. The results show that adopting such passive measures reduces the building's energy demand from 67.5 to 15.7 kWh/m2 for heating and from 7.7 to 5.7 kWh/m2 for cooling. This leads to an annual reduction of 53.8 kWh/m2, or an energy saving of 72% per year. Furthermore, CO2 emissions were reduced by 72% passing then from 1772 to 499 kg/year. Thus, a correlative reduction between energy demand and carbon footprint is observed. The economic analysis shows that life cycle costs are influenced by energy prices in different countries and that the profitability of these measures strongly depends on whether these prices are subsidised or not.

A GP-Based Hierarchical Objectives Decision-Making Method for Building Energy Efficiency Optimization

Building energy efficiency, which is critical in reducing environmental impact, has become one of the most important objectives of building designs. In order to precisely express the goals of building designs, and help decision makers estimate the ultimate performance of design schemes in advance when searching for the optimal building design, the Goal Programming Model (GPM) is introduced in this study to provide a solution for explicit design objective delivery and multi-stakeholder involved decision-making support. In this proposed method, EnergyPlusTM works as a simulation engine to search for the relationship between design parameter combinations and building energy consumption. Simultaneously, Genetic Algorithm (GA) is used to improve the efficiency of overall building energy performance optimization by processing multiple iterations. A case study with five possible design scenarios was dedicated in this study to implement the proposed optimization method, and the optimization results verified the capacity of the established GP-based optimization method to satisfy various design requirements for decision makers and/or stakeholders, especially in facing the hierarchical objectives with different priorities. In this case, the envelope-related variables, including the exterior wall and window, serve as optimization objectives. The optimization is carried out under the ideal air conditioning system, considering different energy usage patterns. Meanwhile, comparing with the vague and restricted expression of objectives in multi-objective optimization, the proposed GP-based optimization method provides explicit trade-off relationships among various objectives for designers, which improves the practical value of the optimized designs, so as to ensure the project success and facilitate the development of green buildings.

Multi-objective optimization of building energy performance and indoor thermal comfort by combining artificial neural networks and metaheuristic algorithms

During the last few years, multi-objective optimization processes have become one of the main challenges for energy efficiency in buildings. In this work, a new efficient multi-objective optimization method, based on the Building Performance Optimization (BPO) technique, has been developed to improve the indoor thermal comfort and energy performance of residential buildings, i.e. a Moroccan ground floor + first floor (GFFF) house located in Marrakech region (5th climatic zone according to the Thermal Building Code in Morocco). The most influential design variables have been well explored in order to find the optimal trade-off between these two objectives. Indeed, this technique is based on the integration of Artificial Neural Networks (ANNs), in particular Multilayer Feedforward Neural Networks (MFNN), coupled with the most commonly used metaheuristic algorithms, i.e. Non-dominated Sorting Genetic Algorithm (NSGA-II), Multi-Objective Particle Swarm Optimization (MOPSO) and Multi-Objective Genetic Algorithm (MOGA), in order to minimize computation time as much as possible. The TRNSYS software was used to establish the various dynamic thermal simulations required to create the database, from which the ANNs were able to set up their learning. The results show that this methodology is being used successfully, leading to different proposed solutions in terms of building envelope design. However, only the solutions using MOPSO are finally retained, as they have shown the greatest desired performance compared to the others. Thus, the thermal needs, particularly those for heating and cooling, have been significantly reduced to 74.52% of the total, while improving the indoor thermal comfort by 4.32% compared to the base design. Finally, we strongly recommend this methodology to the different actors in this field, including designers, engineers, architects, engineering offices, etc., when several objectives need to be contrasted while simultaneously considering several design variables.

Effect of urban built form and density on building energy performance in temperate climates

Urban built form and density are crucial parameters for the optimization of building energy performance. However, a cohesive framework which correlates building energy with urban built form and density is lacking, with no unified agreement on the concept of urban density. This study establishes the subtle interrelationships between urban built forms, density and building energy performance using two density indicators, specifically, site coverage and plot ratio. This paper initially considers geometrical variables of four customary urban built forms to investigate their relationship with the density indicators. Energy analyses are performed on the geometrical models representing residential buildings using the City of London as an example of a temperate climate. Annual building energy demands of pavilion, terrace, court and tunnel-court forms are calculated. The findings are used to produce a heat map of energy intensity on the Form Signature graphs. Results show that high-rise buildings with greater plan depths achieve higher energy efficiency. Moreover, it is shown that greater cut-off angles correspond to higher energy demands under temperate climatic conditions. An energy indicator, termed Energy Equity is introduced which represents the ratio between PV energy generation installed on roofs with respect to the total energy demand of the building. Further analyses show that by considering energy demand and PV energy generation simultaneously, low-rise buildings with greater plan depths provide improved energy performance. A comparative analysis of the energy performance of different built forms with similar geometric parameters demonstrates that the tunnel-court and the pavilion built forms provide the best and worst energy performance, respectively. However, when constraining density whilst changing other geometric parameters, this converse is true. Finally, the study illustrates that the same density for the same built form can be achieved by different combinations of geometric parameters that certainly affects energy performance of buildings. Graphic display of the analysis results provide urban planning guidelines that represent the database of major findings of this study. It can be used by designers, planners and architects to identify the most energy-efficient built form and density for promoting more sustainable cities.

Occupant presence and behavior: A major issue for building energy performance simulation and assessment

The building sector in the world is responsible for nearly 36% of the final energy consumption and nearly 40% of total direct and indirect CO2 emissions. Reducing buildings energy consumption is an absolute necessity, and one of the most efficient methods is the estimation and optimization of building energy performance. One of the significant factors affecting the building energy performance is the occupant behavior. Recently, there has been growing interest in the occupant behavior field. Within the framework of this context, different methods have been proposed and developed especially when the traditional methods, such as interview and survey, are not efficient and sufficient to analyze and to predict the occupant behavior with better accuracy. This research provides a comprehensive characterization of the occupant behavior through, a review of current approaches for occupant behavior analysis. The main key issues and drivers affecting the energy behavior of habitants identified on the literature were synthetized and presented. Furthermore, the paper highlights the necessity of including the energy feedback programs as a main key in the topic of occupants, in order to integrate them in the building performance process.This research is a part of a European project H2020 “Holistic Energy and Architectural Retrofit Toolkit (HEART)”.

Multi-objective optimization of building energy performance using a particle swarm optimizer with less control parameters

Good energy performance is very important for decreasing the consumption of energy-intensive buildings. This paper studies a new multi-objective evolutionary approach to optimize the building energy performance. Firstly, the problem is modeled as two-objective optimization functions, i.e., minimizing the energy consumption and maximizing the comfort level. Next, a new solving algorithm based on bare-bones particle swarm optimization is developed. In the algorithm, an improved update strategy with adaptive perturbation is proposed to overcome the disadvantage of easily local convergence of the traditional algorithm. The algorithm deletes control parameters including inertia weight and acceleration coefficients from the traditional algorithm, showing the advantage of easy-to-use. Applying the proposed algorithm into several buildings located in China, experiment result shows that the proposed algorithm can obtain good non-dominated solutions, which is obviously better than that of those compared algorithms. The uncomfortable hours of the proposed algorithm on part cases reduce 11.82%, but its energy consumption only increases 1.74%. All indicate that the proposed algorithm is a powerful tool for optimizing building energy preference.

Building energy performance optimization towards net zero energy building using passive solution technologies and building information modeling at design phase

Building energy performance optimization towards net zero energy building using passive solution technologies and building information modeling at design phase

Ensemble Learning Model-Based Test Workbench for the Optimization of Building Energy Performance and Occupant Comfort

Buildings consume tremendous energy for the improvement of living and working conditions. Control of daylight-artificial light has the potential to improve energy performance and occupant comfort in buildings. This research proposes an intelligent generalized ensemble learning technique to develop a novel control strategy for Venetian-blind positioning (up-down movement with static slat angle of 45°) of different window orientations. The proposed model helps to maintain occupant comfort and energy saving in a commercial building. The performance of the ensemble learning approach compared against Gaussian process regression, support vector regression and artificial neural network using conventional statistical indicators. Finally, the proposed data-driven model implemented in a real-time Labview-myRIO platform for the experimental validation. The data-driven model is compared with the baseline model and with the uncontrolled blind condition in terms of daylight glare, and energy consumption of lighting and air-conditioning system in the building. The data-driven model is derived using two years of data collected from a fuzzy-based daylight-artificial light integrated scheme. The blind position providing reduced energy consumption and daylight glare along with setpoint illuminance and temperature are validated. A high dynamic range image with EVALGLARE software used to verify the visual comfort based on daylight glare probability. While evaluating the overall energy savings, the ensemble learning model consumes 17% less power than the uncontrolled system and 15% less power than the baseline system. Here, though we are not controlling the air-conditioning system, the experimental validation confirmed that the air-conditioning system significantly reduces its energy consumption.

Occupant behaviour: a major issue for building energy performance

The building sector in the world is responsible for nearly 36% of the final energy consumption and nearly 40% of total direct and indirect CO2 emissions. One of the most efficient strategies to reduce the energy consumption in buildings is the estimation and optimization of building energy performance. According to the International Energy Agency IEA-EBC[1], several factors influence the energy performance of buildings; one of the significant factors is the occupant behavior. Recently, there has been growing interest in this field. In this context, different methods have been proposed and developed especially when the traditional methods such as interview and survey are not efficient and sufficient to analyze and to predict the occupant behavior with better accuracy. The main objective of this study is to provide a clear definition of the occupant behavior, a review of current approaches to analyze the occupant behavior and presentation of our research that proposes the possibility of including the occupants as a part of the problem and a solution to the problem. This research is a part of a European project H2020 “Holistic Energy and Architectural Retrofit Toolkit (HEART)”.

Multi-objective optimization of building energy performance and indoor thermal comfort: A new method using artificial bee colony (ABC)

The aim of this paper is to present a powerful simulation-based multi-objective optimization of building energy efficiency and indoor thermal comfort to obtain the optimal solutions of the comfort-energy efficient configurations of building envelope. The optimization method is developed by integrating a multi-objective artificial bee colony (MOABC) optimization algorithm implemented in MATLAB with EnergyPlus building energy simulation tool. The proposed optimization approach is applied to a single office room; and the building parameters, including the room rotation, window size, cooling and heating setpoint temperatures, glazing and wall material properties are considered as decision variables. In the present study, single-objective and multi-objective optimization analyses of the total annual building electricity consumption and the Predicted Percentage of Dissatisfied (PPD) are investigated to bring down the total energy cost as well as the thermal discomfort in four major climate regions of Iran, i.e. temperate, warm-dry, warm-humid and cold ones. In the results part, the achieved optimal solutions are presented in the form of Pareto fronts to reveal the mutual impacts of variables on the building energy consumption and the thermal discomfort. Finally, the ultimate optimum solution on the Pareto fronts are selected by TOPSIS decision-making method and the results of double-objective minimization problem are compared with the single-objective ones as well as the base design. The results of double-objective optimization problem indicate that in different climates, even though the total building electricity consumption increases a bit about 2.9–11.3%, the PPD significantly decreases about 49.1–56.8% compared to the baseline model. In addition, the comparisons of single-objective and double-objective optimization approaches clearly show that multi-objective optimization methods yield more appropriate results respect to the single ones, mainly because of the lower deviation index value from the ideal solution.

Optimization of Building Energy Performance through Passive Design Strategies

Optimization of Building Energy Performance through Passive Design Strategies

Optimization of building energy performance by means of multi-scale analysis – Lessons learned from case studies

The sustainability of the built environment largely depends on its energy and environmental performances. The overall objective, across the different phases of the building life cycle, is to improve building and system performances in terms of economics, comfort, environmental impact and durability.Several modelling methodologies have been developed in order to evaluate the energy performance of buildings. Generally, every modelling methodology responds effectively to some specific tasks, but there exists a lack of integration in particular with respect to the cross-disciplinary role of data. Given the multi-scale and multi-objective nature of the problem of optimization of the energy and environmental performances of the built environment, an appropriate synthesis and integration process in modelling methodologies has to be identified, addressing realistically the uncertainties inherently present in modelling strategies.Visualization and data analysis techniques are successfully used in a wide variety of applications, both in theoretical and applied domains, but questions remains about their robustness, efficiency and applicability to the problems introduced before. The paper aims to analyze critically these topics by means of case studies, showing a possible path to create a multi-scale methodology able to synthesize all the relevant aspects.

Simulation-based model predictive control by the multi-objective optimization of building energy performance and thermal comfort

Efficient HVAC devices are not sufficient to achieve high levels of building energy performance, since the regulation/control strategy plays a fundamental role. This study proposes a simulation-based model predictive control (MPC) procedure, consisting of the multi-objective optimization of operating cost for space conditioning and thermal comfort. The procedure combines EnergyPlus and MATLAB®, in which a genetic algorithm is implemented. The aim is to optimize the hourly set point temperatures with a day-ahead planning horizon, based on forecasts of weather conditions and occupancy profiles. The outcome is the Pareto front, and thus the set of non-dominated solutions, among which the user can choose according to his comfort needs and economic constraints. The critical issue of huge computational time, typical of simulation-based MPC, is overcome by adopting a reliable minimum run period. The procedure can be integrated in building automation systems for achieving a real-time optimized MPC. The methodology is applied to a multi-zone residential building located in the Italian city of Naples, considering a typical day of the heating season. Compared to a standard control strategy, the proposed MPC generates a reduction of operating cost up to 56%, as well as an improvement of thermal comfort.

Multi-scale Analysis and Optimization of Building Energy Performance – Lessons Learned from Case Studies

The sustainability of the built environment largely depends on its energy and environmental performances. The overall objective, across the different phases of the building life cycle such as design phase, construction phase, commissioning phase, operation phase and eventually refurbishment phase, is to improve building and system performances in terms of economics, comfort, environmental impact and durability.Numerical simulation tools and optimization methods are needed to properly evaluate all the key performance indicators simultaneously, unveiling the existing gaps and identifying possible synergies and strategies in the performance estimation and decision-making processes for the building life cycle.Further, several modelling methodologies have been developed in order to evaluate the energy performance of buildings. Generally, every modelling methodology responds effectively to some specific tasks, but there exists a lack of integration in the overall optimization process.Given the multi-scale and multi-objective nature of the problem of optimization of the energy and environmental performances of the built environment, subject to economic and comfort constraints, an appropriate synthesis and integration process in modelling methodologies has to be identified, addressing realistically the uncertainties inherently present in every modelling strategy.Data analysis and optimization techniques are successfully used in a wide variety of applications. Although these techniques have proven to be successful in both theoretical and applied domains, questions remains about their applicability for the problems introduced before. These questions involve primarily the robustness and efficiency of solutions procedures and the ability to identify relevant properties and to deal with large quantities of data.The paper aims to analyse critically these topics by means of case studies, showing a possible path to create an integrated methodology able to synthesize all the relevant aspects previously mentioned.

A new methodology for cost-optimal analysis by means of the multi-objective optimization of building energy performance

The recast version of the Energy Performance of Buildings Directive (2010/31/EU) proposes a comparative methodology aimed at defining the energy performance of buildings “with a view to achieving cost-optimal levels”. Really, how can the cost-optimal technologies be detected? Moreover, how can the most proper packages of energy efficiency measures be chosen in order to obtain the cost-optimality? This paper would provide answers to these questions, by proposing a new methodology for the evaluation of the cost-optimality, by means of the multi-objective optimization of energy performance of buildings and indoor thermal comfort. The optimization procedure is developed by means of the coupling between MatLab and EnergyPlus, by implementing a genetic algorithm, and it allows the evaluation of profitable and feasible packages of energy efficiency measures applied to buildings. Then, following the adoption of these packages, the global cost over the lifecycle of the building is calculated, in order to identify the cost-optimal solution. After the presentation of the methodology, the developed method is proposed for the optimization of the energy retrofit of an existing building. Furthermore, the method can be applied also for new architectures, by considering reference buildings.

The “extended building energy hub”: A new method for the simultaneous optimization of energy demand and energy supply in buildings

This article deals with simultaneous optimization of building energy performance from both the building and system design points of view. Most research conducted on building energy demand reduction and energy supply optimization treats the demand and supply aspects separately. First, the demand side parameters are analyzed for a demand reduction and then the most suitable configuration for the primary energy conversion is investigated. The relationship between the building energy demand and supply may not be clearly understood when they are analyzed sequentially instead of simultaneously. This article investigates the potentiality of an integrated building demand-supply energy optimization method that could provide a solution to the building energy efficiency problem. The method is based on the Extended Building Energy Hub (EBEH) concept, which is an evolution of the Building Energy Hub (BEH) method. In the BEH approach, the vector of energy inputs—the energy supply—is related to the vector of energy outputs—the energy demand—by means of a coupling matrix. The coefficients of this matrix are functions of the efficiency of the various energy conversion systems and of the distribution of energy fluxes in the energy converters. In the EBEH method, the demand side building design parameters are also included in a coupling matrix and are evaluated together with primary energy options. In this way, for example, the demand side parameters (U values, window-to-wall ratio, etc.) can be contrasted with the opportunity of using solar energy for the production of electricity, and the optimum configuration can be calculated by maximizing the primary energy savings. The article introduces the basic principles of this approach. A preliminary practical demonstration is also developed through the application of a simplified procedure to a case study of an existing building.