Ravi S. Srinivasan

A review of artificial intelligence based building energy prediction with a focus on ensemble prediction models

Building energy usage prediction plays an important role in building energy management and conservation. Building energy prediction contributes significantly in global energy saving as it can help us to evaluate the building energy efficiency; to conduct building commissioning; and detect and diagnose building system faults. AI based methods are popular owing to its ease of use and high level of accuracy. This paper proposes a detailed review of AI based building energy prediction methods particularly, multiple linear regression, Artificial Neural Networks, and Support Vector Regression. In addition to the previously listed methods, this paper will focus on ensemble prediction models used for building energy prediction. Ensemble models improve the prediction accuracy by integrating several prediction models. The principles, applications, advantages, and limitations of these AI based methods are elaborated in this paper. Additionally, future directions of the research on AI based building energy prediction methods are discussed.

Energy balance framework for net zero energy buildings

Approaching a Net Zero Energy (NZE) building goal based on current definitions is flawed for two principal reasons - they only deal with energy quantities required for operations, and they do not establish a threshold, which ensures that buildings are optimized for reduced consumption before renewable systems are integrated to obtain an energy balance. This paper develops a method to maximize renewable resource use through emergy (spelled with an “m”) analysis. A “Renewable Emergy Balance” (REB) in environ-mental building design is proposed as a tool to maximize renewable resource use through disinvestment of all non-renewable resources that may be substituted with renewable resources. REB buildings attain a high standing by optimizing building construction over their entire life-span from formation-extraction-manufacturing to maintenance and operation, and material reuse at the end of building life-time.

Preliminary research in dynamic-BIM (D-BIM) workbench development

Past and ongoing research efforts toward seamless integration of building design and analysis have established a strong foothold in the building community. Yet, there is lack of seamless connectivity between Building Information Modeling (BIM) and building performance tools. D-BIM Workbench provides an essential framework to conduct integrated building performance assessments within BIM, an environment familiar to all stakeholders. With tighter tool integration within BIM, this open-source Workbench can be tailored to specific analysis such as energy, environmental, and economic impact of buildings. The Workbench, currently under development, will enable on-the-fly simulations of building performance tools to design, operate, and maintain a low/Net Zero Energy (NZE) built environment and beyond. This paper discusses the preliminary research in D-BIM Workbench development such as the Workbench architecture, its open-source environment, and other efforts currently under progress including integration of 3D heat transfer in the Workbench.

Artificial Intelligent Models for Improved Prediction of Residential Space Heating

AbstractUsing artificial intelligence (AI) models, cost effective electricity meter, and easily accessible weather data, this paper discusses a methodology for improved prediction of hourly residential space heating electricity use. Four AI models [back propagation neural network (BPNN), radial basis function neural network (RBFNN), general regression neural network (GRNN), and support vector regression (SVR)] were used for predicting hourly residential heating electricity use. For this study, a typical single-family house was used to obtain the data used for AI prediction models. Results showed SVR’s ability to predict hourly residential heating electricity use was better when compared with other AI models. Furthermore, through comparison of prediction performance in different time periods, additional investigation was conducted to evaluate the effect of dynamic human behaviors on the prediction accuracy of the AI models. Results revealed that dynamic human behaviors have a negative effect on the predict...

GIS-Based Decision Support System for Smart Project Location

In recent years, leading sustainability rating systems have extended the sustainability certification beyond buildings by introducing neighborhood level rating systems. The rationale is that sustainable buildings start with suitable site location and how well they integrate with their neighborhood. This paper discusses a Geographic Information System (GIS) based decision support system that aids owners, developers, and other stakeholders to analyze the project site location and its integration with the neighborhood in a sustainable manner. This decision support system uses four criteria to evaluate the project site location, a) connectivity to existing urban infrastructure; b) integration within current neighborhood; c) connectivity to transportation network; and d) environmental and agricultural land status. After reviewing literature on project site location in relation to neighborhood level sustainability rating systems, this paper discusses the results of preliminary test conducted using a neighborhood case study.

Building energy simulation and parallel computing: opportunities and challenges

Increased focus on energy cost savings and carbon footprint reduction efforts improved the visibility of building energy simulation, which became a mandatory requirement of several building rating systems. Despite developments in building energy simulation algorithms and user interfaces, there are some major challenges associated with building energy simulation; an important one is the computational demands and processing time. In this paper, we analyze the opportunities and challenges associated with this topic while executing a set of 275 parametric energy models simultaneously in EnergyPlus using a High Performance Computing (HPC) cluster. Successful parallel computing implementation of building energy simulations will not only improve the time necessary to get the results and enable scenario development for different design considerations, but also might enable Dynamic-Building Information Modeling (BIM) integration and near real-time decision-making. This paper concludes with the discussions on future directions and opportunities associated with building energy modeling simulations.

Real-Time Simulations Using Learning Algorithms for Immersive Data Visualization in Buildings

Computational Fluid Dynamic (CFD) simulations are used to predict indoor thermal environments and assess their response to specific internal/external conditions. Although computing power has increased exponentially in the past decade, CFD simulations are still time-consuming and their prediction results cannot be used for real-time immersive visualization in buildings. A method that can bypass the time-consuming simulations and generate “acceptable” results will allow such visualization to be constructed. This paper discusses a project that utilizes a supervised Artificial Neural Network (ANN) as a learning algorithm to predict post-processed CFD data to ensure rapid data visualization. To develop a generic learning model for a wide range of spatial configurations, this paper presents a pilot project that utilizes an unsupervised Reinforcement Learning (RL) algorithm. The ANN technique was integrated with an interactive, immersive Augmented Reality (AR) system to interact with and visualize CFD results in buildings. ANN was also evaluated against a linear regression model. Both models were tested and validated with datasets to determine their degree of accuracy. Initial tests, conducted to evaluate the users experience of the system, indicated satisfactory results.

Interactive, immersive visualization for indoor environments: use of augmented reality, human-computer interaction and building simulation

We present an interactive gesture recognition-based, immersive augmented reality system visualizing computational fluid dynamics (CFD) datasets of indoor environments. CFD simulation is used to predict the indoor environments and assess their response to specific internal and external conditions. To enable efficient visualization of CFD datasets in actual-space, an augmented reality system was integrated with a CFD simulation engine. To facilitate efficient data manipulation of the simulated post-processed CFD data and to increase the user-control of the immersive environment, a new intuitive method of human-computer interaction (HCI) has been incorporated. A gesture recognition system was integrated with the augmented reality-CFD structure to transform hand-postural data into a general description of hand-shape, through forward kinematics and computation of hand segment positions and their joint angles. This enabled real-time interactions between users and simulated CFD results in actual-space.

Occupant behavior modeling for smart buildings: a critical review of data acquisition technologies and modeling methodologies

At the outset, there is no question that building energy use is largely influenced by the presence and behavior of occupants. Among other, the key to realize energy use reduction while still maintaining occupant comfort is to seamlessly integrate occupant behavior in energy simulation tools with capabilities that would optimally manage building energy systems. This paper provides an in-depth survey of occupant behavior modeling state-of-the-art technologies employed to gather relevant data and modeling methodologies to reduce energy use. Several novel technologies that have been utilized for data collection are discussed in this paper. For the purposes of this review paper, occupant behavior modeling has been organized based on their underlying methodologies namely, statistical analysis; agent-based models; data mining approaches; and stochastic techniques. After providing a thorough review of state-of-the-art research work in the field of occupant behavior modeling for smart, energy efficient buildings, this paper discusses potential areas of improvement.

Towards the implementation of a 3D heat transfer analysis in dynamic-BIM (dynamic building information modeling) workbench

Energy efficient building design demands a complete understanding of building envelope heat transfer along with airflow behavior. Although existing building energy modeling tools provide 2D heat transfer analysis, they fail to execute full-scale 3D heat transfer analysis and lack proper integration with Building Information Modeling BIM tools. This paper addresses these issues first by developing a BIM-integrated plugin tool to extract building geometry and material information from a 3D building model and then demonstrating a complete 3D heat transfer analysis along with grid generation. This paper discusses the preliminary research work in data extraction from Building Information Modeling (BIM) for performing 3D heat transfer in a seamless manner. This approach will help towards the implementation of a 3D heat transfer in Dynamic-BIM Workbench, an integrative, collaborative, and extensible environment. This Workbench enables integration of domain modeling, simulation, and visualization.