An intelligent approach to assessing the effect of building occupancy on building cooling load prediction

Building cooling load prediction is one of the key factors in the success of energy-saving measures. Many computational models available in the industry have been developed from either forward or inverse modeling approaches. However, these models usually require extensive computer resources and lengthy computation. This paper discusses the use of the multi-layer perceptron (MLP) model, one of the artificial neural network (ANN) models widely adopted in engineering applications, to estimate the cooling load of a building. The training samples used include weather data obtained from the Hong Kong Observatory and building-related data acquired from an existing prestigious commercial building in Hong Kong that houses a mega complex and operates 24 h a day. The paper also discusses the practical difficulties encountered in acquiring building-related data. In contrast to other studies that use ANN models to predict building cooling load, this paper includes the building occupancy rate as one of the input parameters used to determine building cooling load. The results demonstrate that the building occupancy rate plays a critical role in building cooling load prediction and significantly improves predictive accuracy.     

New artificial neural network prediction method for electrical consumption forecasting based on building end-uses

Due to the current high energy prices it is essential to find ways to take advantage of new energy resources and enable consumers to better understand their load curve. This understanding will help to improve customer flexibility and their ability to respond to price or other signals from the electricity market. In this scenario, one of the most important steps is to carry out an accurate calculation of the expected consumption curve, i.e. the baseline. Subsequently, with a proper baseline, customers can participate in demand response programs and verify performed actions. This paper presents an artificial neural network (ANN) method for short-term prediction of total power consumption in buildings with several independent processes. This problem has been widely discussed in recent literature but a new point of view is proposed. The method is based on two fundamental features: total consumption forecast based on independent processes of the considered load or end-uses; and an adequate selection of the training data set in order to simplify the ANN architecture. Validation of the method has been performed with the prediction of the whole consumption expressed as 96 active energy quarter-hourly values of the Universitat Politècnica de València, a commercial customer consuming 11,500 kW.     

Energy performance optimization of radiant slab cooling using building simulation and field measurements

Few field studies of energy performance of radiant cooling systems have been undertaken. A recently constructed 17,500 m² building with a multi-floor radiant slab cooling system in the tower was investigated through simulation calibrated with measured building energy use and meteorological data. For the very cold, dry region where the building was located, it was found that a typical floor of the tower would have had 30% lower annual energy use with a conventional variable air volume system than with the as-built radiant cooling-variable air volume combination. This was due to (1) simultaneous heating and cooling by the existing radiant cooling and air systems, (2) the large amount of free cooling possible in this climate, and (3) suboptimal control settings. If these issues were remedied and combined with improved envelope and a dedicated outdoor air system with exhaust air heat recovery, a typical floor could achieve annual energy use 80% lower than a typical floor of the existing building HVAC system. This shows that radiant thermal control can make a significant contribution to energy-efficiency, but only if the building design and operating practices complement the strengths of the radiant system.     

Comparison between detailed model simulation and artificial neural network for forecasting building energy consumption

There are several ways to attempt to model a building and its heat gains from external sources as well as internal ones in order to evaluate a proper operation, audit retrofit actions, and forecast energy consumption. Different techniques, varying from simple regression to models that are based on physical principles, can be used for simulation. A frequent hypothesis for all these models is that the input variables should be based on realistic data when they are available, otherwise the evaluation of energy consumption might be highly under or over estimated.In this paper, a comparison is made between a simple model based on artificial neural network (ANN) and a model that is based on physical principles (EnergyPlus) as an auditing and predicting tool in order to forecast building energy consumption. The Administration Building of the University of São Paulo is used as a case study. The building energy consumption profiles are collected as well as the campus meteorological data.Results show that both models are suitable for energy consumption forecast. Additionally, a parametric analysis is carried out for the considered building on EnergyPlus in order to evaluate the influence of several parameters such as the building profile occupation and weather data on such forecasting.     

人工智能新技术在智能建筑中的应用研究

本文分析了人工智能新技术的应用,指出当前引入人工智能技术实现建筑系统智能控制与管理已成为可能。     

An artificial intelligence-based method to efficiently bring CFD to building simulation

A computational procedure known as co-simulation has been proposed in the literature as a possibility to extend the capabilities and improve the accuracy of building performance simulation (BPS) tools. Basically, the strategy relies on the data exchanging between the BPS and a specialized software, where specific physical phenomena are simulated more accurately thanks to a more complex model, where advanced physics are taken into account. Among many possibilities where this technique can be employed, one could mention airflow, three-dimensional heat transfer or detailed HVAC systems simulation, which are commonly simplified in BPS tools. When considering complex models available in specialized software, the main issue of the co-simulation technique is the considerable computational effort demanded. This paper proposes a new methodology for time-consuming simulations with the purpose of challenging this particular issue. For a specific physical phenomenon, the approach consists of designing a new model, called prediction model, capable to provide results, as close as possible to the ones provided by the complex model, with a lower computational run time. The synthesis of the prediction model is based on artificial intelligence, being the main novelty of the paper. Basically, the prediction model is built by means of a learning procedure, using the input and output data of co-simulation where the complex model is being used to simulate the physics. Then the synthesized prediction model replaces the complex model with the purpose of reducing significantly the computational burden with a small impact on the accuracy of the results. Technically speaking, the learning phase is performed using a machine learning technique, and the model investigated here is based on a recurrent neural network model and its features and performance are investigated on a case study, where a single-zone house with a triangular prism-shaped attic model is co-simulated with both CFX (CFD tool) and Domus (BPS tool) programs. Promising results lead to the conclusion that the proposed strategy enables to bring the accuracy of advanced physics to the building simulation field – using prediction models – with a much reduced computational cost. In addition, re-simulations might be run solely with the already designed prediction model, demanding computer run times even lower than the ones required by the lumped models available in the BPS tool.     

A green roof model for building energy simulation programs

A physically based model of the energy balance of a vegetated rooftop has been developed and integrated into the EnergyPlus building energy simulation program. This green roof module allows the energy modeler to explore green roof design options including growing media thermal properties and depth, and vegetation characteristics such as plant type, height and leaf area index. The model has been tested successfully using observations from a monitored green roof in Florida. A preliminary set of parametric tests has been conducted on prototypical 4000 m² office buildings in Chicago IL and Houston TX. These tests focus on evaluating the role of growing media depth, irrigation, and vegetation density (leaf area index) on both natural gas and electricity consumption. Building energy consumption was found to vary significantly in response to variations in these parameters. Further, this response depended significantly on building location (climate). Hence, it is evident that the green roof simulation tool presented here can serve a valuable role in informing green roof design decisions.     

Application of artificial neural networks for predicting the cuttability of rocks by drag tools

Many models have previously been developed for predicting specific cutting energy (SE), being the measure of rock cuttability, from intact rock properties employing conventional multiple linear or nonlinear regression techniques. Artificial neural networks (ANN) also have a great potential in building such models. This paper is concerned with the application of ANN for the prediction of cuttability of rocks from their intact properties. For that purpose, data obtained from three different projects were subjected to statistical analyses using MATLAB. Principal components analysis together with the scatterplots of SE against intact rock properties were employed to select the predictors for SE models. Results of the principal components analysis have shown that the most of the variance in the data set can be explained by three principal components. Principal component with the highest variance is weighted mainly on the uniaxial compressive strength (UCS), Brazilian tensile strength (BTS), static modulus of elasticity (Elasticity), and cone indenter hardness (CI), which were regarded as the independent variables driving the data set. Three predictive models for SE were developed employing above independent variables by multiple nonlinear regression with forward stepwise method and ANN, respectively. Neural networks were developed for two different numbers of hidden neurons in the hidden layer. Goodness of the fit measures revealed that ANN models fitted the data as accurately as multiple nonlinear regression model, indicating the usefulness of artificial neural networks in predicting rock cuttability.     

Modelling TBM performance with artificial neural networks

Assessing TBM performance is an important parameter for the successful accomplishment of a tunnelling project. This paper presents an attempt to model the advance rate of tunnelling with respect to the geological and geotechnical site conditions. The model developed for this particular task is implemented through the use of an artificial neural network (ANN) that allows the identification and understanding of both the way and the extent that the involved parameters affect the tunnelling process. The model described in the paper is customised for the construction of an interstation section of the Athens metro tunnels, where the ANN generalisations provided precise estimations regarding the anticipated advance rate.     

Application of artificial intelligence to rock mechanics: An overview

Different artificial intelligence(AI)methods have been applied to various aspects of rock mechanics,but the fact that none of these methods have been used as a standard implies that doubt as to their generality and validity still exists.For this,a literature review of application of AI to the field of rock mechanics is presented.Comprehensive studies of the researches published in the top journals relative to the fields of rock mechanics,computer applications in engineering,and the textbooks were conducted.The performances of the AI methods that have been used in rock mechanics applications were evaluated.The literature review shows that AI methods have successfully been used to solve various problems in the rock mechanics field and they performed better than the traditional empirical,mathematical or statistical methods.However,their practical applicability is still an issue of concern as many of the existing AI models require some level of expertise before they can be used,because they are not in the form of tractable mathematical equations.Thus some advanced AI methods are still yet to be explored.The limited availability of dataset for the AI simulations is also identified as a major problem.The solutions to the identified problems and the possible future research focus were proposed in the study subsequently.     

A new methodology towards determining building performance under modified outdoor conditions

Great efforts have been made to establish the influence of the urban climate upon the energy consumption of buildings. While many scientific articles present measured data of increased energy consumption due to building surroundings, this paper aims to present a straightforward methodology for the assessment of building performance under modified outdoor conditions. Designers and urban planners should benefit from the results of this paper in their evaluation of proposals to decrease building energy consumption. A number of examples are discussed in order to illustrate the methodology outlined.     

Uncertainty analysis in building performance simulation for design support

Building performance simulation (BPS) has the potential to provide relevant design information by indicating directions for design solutions. A major challenge in simulation tools is how to deal with difficulties through large variety of parameters and complexity of factors such as non-linearity, discreteness, and uncertainty.The purpose of uncertainty and sensitivity analysis can be described as identifying uncertainties in input and output of a system or simulation tool [1], [2] and [3].In practice uncertainty and sensitivity analysis have many additional benefits including: (1) With the help of parameter screening it enables the simplification of a model [4]. (2) It allows the analysis of the robustness of a model [5]. (3) It makes aware of unexpected sensitivities that may lead to errors and/or wrong specifications (quality assurance) [6], [7], [8], [9] and [10]. (4) By changing the input of the parameters and showing the effect on the outcome of a model, it provides a “what-if analysis” (decision support). [11].In this paper a case study is performed based on an office building with respect to various building performance parameters. Uncertainty analysis (UA) is carried out and implications for the results considering energy consumption and thermal comfort are demonstrated and elaborated. The added value and usefulness of the integration of UA in BPS is shown.     

An instructional design for building energy simulation e-learning: an interdisciplinary approach

This article describes the development of a new instructional design (ISD) to promote building energy simulation (BES) education. The study is based upon education fundamentals combined with computer-based learning and hypermedia to enable the development of a BES-based distance learning system. Some cognitive tools are established such as: (i) an interdisciplinary knowledge tree of BES that can be used by professionals with different backgrounds; (ii) a hypermedia navigational aid to understand the simulation software, called the BES tool graphic organizer; (iii) a concept map with an overview of building energy performance and (iv) a cooperative problem-based learning (CPBL) environment. Furthermore, the paper also brings an analysis of the students’ comprehension – from a course applied across Brazil – by means of concept network graphs from text mining provided by the CPBL environment, showing a significant potential to develop interdisciplinary e-learning related to building energy efficiency.     

Integrated simulation through the source-code coupling of component models from a modular simulation environment into a comprehensive building performance simulation tool

No single building performance simulation program contains sufficient capabilities and flexibility to fully respond to the full complexity of modern building design and analysis. Consequently, considerable efforts and advances have been made to facilitate the integrated use of multiple simulation tools to provide more extensive modelling capabilities. The research reported in this article has made a contribution towards the goal of integrated simulation by focusing on the internal coupling of component models from a modular simulation environment into a comprehensive building performance simulation tool. A flexible and extensible facility has been designed and developed to enable the use of HVAC component models (TYPEs) from the TRNSYS simulation program within the ESP-r simulation platform. With this, the source code for any number of TRNSYS TYPEs can be compiled with the ESP-r source code to produce an integrated simulation tool that possesses greater capabilities than either simulation program alone.     

Selection criteria for building performance simulation tools: contrasting architects' and engineers' needs

This article summarises a study undertaken to reveal potential challenges and opportunities for using building performance simulation (BPS) tools. The article reviews current trends in building simulation and outlines major criteria for BPS tool selection and evaluation based on analysing users' needs for tools capabilities and requirement specifications. The research is carried out by means of a literature review and two online surveys. The findings are based on an inter-group comparison between architects and engineers. The aim is to rank BPS tool selection criteria and compare 10 state-of-the-art BPS tools in the USA market. Five criteria are composed to stack up against theories and practices of BPS. Based on the experience gained during the survey, suggested criteria are critically reviewed and tested. The final results indicate a wide gap between architects' and engineers' priorities and tool ranking. This gap is discussed and suggestions for improvement of current tools are presented.     

Building typologies as a tool for assessing the energy performance of residential buildings - A case study for the Hellenic building stock

Successful strategies towards minimizing the energy consumption and greenhouse gas emissions attributed to the building sector require knowledge on the energy-related characteristics of the existing building stock. Despite the numerous studies on energy conservation applications in buildings, current knowledge on the energy-related characteristics of the building stock still remains limited. Building typologies can be a useful instrument to facilitate the energy performance assessment of a building stock. This work is based on a harmonised structure for European building typologies (TABULA) developed for residential buildings, but the methodology may be extended to the tertiary sector as well. National typologies are sets of model buildings with characteristic energy-related properties representative of a country's building stock. The model buildings are used as a showcase for demonstrating the energy performance and the potential energy savings from typical and advanced energy conservation measures (ECMs) on the thermal envelope and the heat supply system. The proposed Hellenic residential building typology is presented for the first time along with an assessment of various ECMs that are used for an estimate of the energy performance of building stock in Greece in an effort to meet the 9% indicative national energy savings target by 2016.     

Bridge afflux analysis through arched bridge constrictions using artificial intelligence methods

Although many studies have been carried out for estimating the afflux through modern straight deck bridge constrictions, little attention has been given to medieval arched bridge constrictions. Hydraulic Research Wallingford in the UK (Brown, P.M., 1988 Brown, P. M. 1988. Afflux at arch bridges, Wallingford, , UK: HR Wallingford. Report SR 182 [Google Scholar]. Afflux at arch bridges. Report SR 182. Wallingford, UK: HR Wallingford) recently published a major coverage of both experimental and field afflux data obtained from arched bridge constrictions. The report pointed out that the present day formulas developed for estimating the bridge afflux are inadequate to apply to ancient arched structures. Therefore, this study aimed at developing new afflux methods for arched bridge constrictions using multi-layer perceptrons (MLP) neural networks, radial basis function-based neural networks (RBNN), generalised regression neural networks (GRNN) and adaptive neuro-fuzzy inference system (ANFIS) model. Multiple linear and multiple nonlinear regression analyses were also used for comparison purposes. Mean square errors, mean absolute errors, mean absolute relative errors, average of individual ratios between predicted and actual values, and determination coefficients were used as comparison criteria for the evaluation of model performances. The test results showed that MLP, RBNN, GRNN, and ANFIS models gave reasonable accuracy when applied to both the field and experimental data collected by Hydraulic Research Wallingford.     

The use of normative energy calculation beyond building performance rating

Standardized building performance assessment is best expressed with a so-called normative calculation method, such as defined in the Committee for Standardization/International Organization for Standardization (CEN/ISO) calculation standards. The normative calculation method has advantages of simplicity, transparency, robustness and reproducibility. For systematic energy performance assessment at various scales, i.e. at the unit of analysis of one building up to a large-scale collection of buildings, the authors' group developed the Energy Performance Standard Calculation Toolkit (EPSCT). This toolkit calculates objective indicators of energy performance using either the monthly or hourly calculation method as specified in the CEN/ISO standard for building energy calculation. The toolkit is the foundation for numerous single, medium-scale and large-scale building energy management applications. At the largest level, applications should be able to manage hundreds or thousands of buildings. The paper introduces two novel applications that have the normative calculation at their core: (1) network energy performance modelling and (2) agent-based building stock energy modelling.