Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Buildings”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 793 records · Page 44

A machine learning method of modern urban building energy modeling: A case study of Chicago

Urban-scale building energy modeling is vital for urban planning. However, it can be challenging to assimilate reliable non-geometry building data for urban-scale modeling without extensive investment. Here, this study introduces a novel approach to developing modern urban-scale building energy stock data using geographic information systems and machine learning algorithms without necessarily requiring pre-supplied non-geometric metadata. The proposed framework integrates building footprint and height data to estimate gross floor areas, and matches each building to a pool of candidate records from ComStock or ResStock—filtered to the same county and ranked by geometric similarity—demonstrate a proof-of-concept case study in Chicago for predicting energy use intensity (EUI) using scalable datasets. The model achieved a mean bias error (MBE) of 0.08 kWh/m² and root mean square error (RMSE) of 14.84 kWh/m² under full metadata input for EUI prediction. With only location inputs, the model captured 69.2 % of EUI within predicted ranges. These results demonstrate the model’s potential to support early-stage urban planning, identify candidates for energy-efficient retrofits. By removing the dependency on detailed pre-surveys or extensive building metadata, the approach overcomes a key barrier in traditional urban-scale building energy modeling, illustrating a pathway toward broader and more cost-effective application, though further multi-city validation and improved treatment of pre-1925 buildings are needed.

Energy Use Intensity↗

Datasets of a Multizone Office Building under Different HVAC System Operation Scenarios

Abstract This study provides an open-source dataset of the measured weather data, building indoor data, and system data under the different test settings. The test building is the two-story Flexible Research Platform building at the US Department of Energy’s Oak Ridge National Laboratory, in Oak Ridge, Tennessee. Four heating tests and three cooling tests were conducted. The 1-min interval of weather, building indoor data, and system data from each test setting are provided. Actual weather data were collected from a weather station installed on the roof. This paper describes information on the test building and installed sensors, data collection method, and data validation. The provided dataset can be employed to understand HVAC system conditions and building indoor conditions under different HVAC system operations and the performance of building envelope without HVAC system operation using free-floating test data. Additionally, it can be used for empirical validation of the building energy modelling engine.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Corporate Delivery of a Global Smart Buildings Program

Buildings account for about 40 percent of the total energy consumption in the U.S. and emit approximately one third of greenhouse gas emissions. But they also offer tremendous potential for achieving significant greenhouse gas reductions with the right savings strategies. With an increasing amount of data from buildings and advanced computational and analytical abilities, buildings can be made “smart” to optimize energy consumption and occupant comfort. Smart buildings are often characterized as having a high degree of data and system integration, connectivity and control, as well as the advanced use of data analytics. These “smarts” can enable up to 10–20% savings in a building, and help ensure that they persist over time. In 2009, Microsoft Corporation launched the Energy-Smart Buildings (ESB) program with a vision to improve building operations services, security and accessibility in services, and new tenant applications and services that improve productivity and optimize energy use. The ESB program focused on fault diagnostics, advanced analytics and new organizational processes and practices to support their operational integration. In addition to the ESB program, Microsoft undertook capital improvement projects that made effective use of a utility incentive program and lab consolidations over the same duration. The ESB program began with a pilot at Microsoft's Puget Sound campus that identified significant savings of up to 6–10% in the 13 pilot buildings. The success of the pilot led to a global deployment of the program. Between 2009 and 2015, there was a 23.7% reduction in annual electricity consumption (kWh) at the Puget Sound campus with 18.5% of that resulting from the ESB and lab consolidations. This article provides the results of research conducted to assess the best-practice strategies that Microsoft implemented to achieve these savings, including the fault diagnostic routines that are the foundation of the ESB program and organizational change management practices. It also presents the process that was adopted to scale the ESB program globally. We conclude with recommendations for how these successes can be generalized and replicated by other corporate enterprises.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Development of building energy asset rating using stock modelling in the USA

The US Building Energy Asset Score helps building stakeholders quickly gain insight into the efficiency of building systems (envelope, electrical and mechanical systems). A robust, easy-to-understand 10-point scoring system was developed to facilitate an unbiased comparison of similar building types across the country. The Asset Score does not rely on a database or specific building baselines to establish a rating. Rather, distributions of energy use intensity (EUI) for various building use types were constructed using Latin hypercube sampling and converted to a series of stepped linear scales to score buildings. A score is calculated based on the modelled source EUI after adjusting for climate. A web-based scoring tool, which incorporates an analytical engine and a simulation engine, was developed to standardize energy modelling and reduce implementation cost. This paper discusses the methodology used to perform several hundred thousand building simulation runs and develop the scoring scales.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

A hardware-in-the-loop (HIL) testbed for cyber-physical energy systems in smart commercial buildings

In recent years, there has been a growing trend toward the development of smart buildings that rely on cyber-physical systems (CPS) to optimize occupant comfort, safety, and energy efficiency. To ensure the reliable and efficient operation of CPS with designed control strategies, it is important to evaluate their performance under various scenarios before deploying them in the real world. This is where a Hardware-in-the-loop (HIL) testbed designed for studying sensor and control-related studies in smart buildings can be highly valuable. With the growing threat of cyber-attacks and physical faults targeting smart buildings, it is essential to ensure the security of building operations. A HIL testbed can emulate cyber-attack and physical fault scenarios, allowing researchers to develop and test threat detection and mitigation algorithms. This enables researchers to identify potential issues and optimize the algorithms in a safe and controlled environment before they are deployed in real-world settings, reducing the risk of failures that can negatively impact occupant comfort, safety, and energy efficiency. Therefore, this paper developed a HIL testbed designed for cyber-physical energy systems (e.g. buildings automation system (BAS)) in smart commercial buildings. The HIL testbed is comprised of a real-time building and Heating, Ventilation, and Air-Conditioning (HVAC) emulator using Modelica-based dynamic models, a set of BAS controllers, and a BAS computer server. The data generation capability of the HIL testbed is demonstrated by tracking normal and faulty operating data in the BAS, as well as monitoring detailed network traffic in the local BAS network. Here, this study further demonstrates the HIL testbed’s capability by conducting case studies on real-time physical fault and cyber-attack experiments using a Department of Energy (DOE) prototype commercial building. It is anticipated that the fully functional HIL testbed will be utilized for a variety of sensor and control-related studies, including but not limited to testing, developing, validating of different HVAC control strategies, fault detection & diagnosis, energy monitoring and analysis, cyber security study, etc.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Assessing the performance of global thermostat adjustment in commercial buildings for load shifting demand response

Abstract Efficiently leveraging new sources of flexibility is critical to mitigating load balancing challenges posed by variable renewable resources. The thermal inertia of commercial buildings allows us to shift their power consumption on minute to hourly timescales to provide demand response to the grid while maintaining occupant comfort. Global thermostat adjustment (GTA) provides a readily available and scalable approach for implementing load shifting demand response using commercial heating, ventilation, and air conditioning (HVAC) systems, since it leverages the inherent sophistication of modern building automation systems. However, there is an incomplete understanding of GTA’s performance for this purpose and its impact on building systems and occupant comfort. In this paper, we explore the performance of GTA by analyzing results from nearly nine hundred experiments on eight university campus buildings in Michigan and North Carolina. Using GTA, we manipulate each building’s thermostat setpoints causing the building to shift its power consumption with respect to its baseline. We quantify the magnitude of HVAC power response, energy use of HVAC subsystems, and impact on occupant comfort. Finally, we connect our experimental results with power system operation using an optimization model that coordinates GTA actions across a large collection of grid-interactive efficient buildings (GEBs) to reduce high ramp rates on the grid and mitigate renewable energy curtailment. Overall, our work finds that the impacts on HVAC subsystems are often complex, and may result in additional energy being consumed by fans and terminal reheat. These effects must be considered when using GTA for load shifting. Additionally, we demonstrate that occupant comfort, as assessed by indoor temperature and humidity, can be maintained during GTA events. From a societal perspective, our modeling work finds that the additional renewable energy that can be integrated through the use of GTA strategies eclipses any additional energy consumed by buildings.

Keskar, Aditya (ORCID:0000000244617980)↗

Building Energy Management Open Source Software

This is the repository for Building Energy Management Open Source Software (BEMOSS), which is an open source operating system that is engineered to improve sensing and control of equipment in small- and medium-sized commercial buildings. BEMOSS offers the following key features: (1) Open source, open architecture – BEMOSS is an open source operating system that is built upon VOLTTRON – a distributed agent platform developed by Pacific Northwest National Laboratory (PNNL). BEMOSS was designed to make it easy for hardware manufacturers to seamlessly interface their devices with BEMOSS. Software developers can also contribute to adding additional BEMOSS functionalities and applications. (2) Plug & play – BEMOSS was designed to automatically discover supported load controllers (including smart thermostats, VAV/RTUs, lighting load controllers and plug load controllers) in commercial buildings. (3) Interoperability – BEMOSS was designed to work with load control devices form different manufacturers that operate on different communication technologies and data exchange protocols. (4) Cost effectiveness – Implementation of BEMOSS deemed to be cost-effective as it was built upon a robust open source platform that can operate on a low-cost single-board computer, such as Odroid. This feature could contribute to its rapid deployment in small- or medium-sized commercial buildings. (5) Scalability and ease of deployment – With its multi-node architecture, BEMOSS provides a distributed architecture where load controllers in a multi-floor and high occupancy building could be monitored and controlled by multiple single-board computers hosting BEMOSS. This makes it possible for a building engineer to deploy BEMOSS in one zone of a building, be comfortable with its operation, and later on expand the deployment to the entire building to make it more energy efficient. (6) Ability to provide local and remote monitoring – BEMOSS provides both local and remote monitoring ability with role-based access control. (7) Security – In addition to built-in security features provided by VOLTTRON, BEMOSS provides enhanced security features, including BEMOSS discovery approval process, encrypted core-to-node communication, thermostat anti-tampering feature and many more. (8) Support from the Advisory Committee – BEMOSS was developed in consultation with an advisory committee from the beginning of the project. BEMOSS advisory committee comprises representatives from 22 organizations from government and industry.

Source record↗

BEEAM (Building Electrical Efficiency Analysis Model) [SWR-20-107]

Modern high-performance buildings exhibit an increasing number of building loads that use direct current (DC) electricity internally, rather than alternating current (AC), due to the advent of low-cost computing and advanced power electronics. Powering DC devices from the AC grid requires AC/DC power conversion, which introduces energy losses and reduces efficiency. As DC loads proliferate, the cumulative wasted energy associated with hundreds of millions of AC/DC converters has become one of the broadest energy savings opportunities in buildings. DC power distribution systems have been proposed as an elegant and transformative solution to the problem of DC devices. In a DC distribution system, the building's wires carry DC electricity, rather than AC; and a few centralized, highly efficient AC/DC converters replace the many smaller, less efficient converters that serve individual DC loads. Unfortunately, the trade-offs associated with DC distribution systems are not well understood. Reported energy savings associated with DC power distribution differ widely and have not been well validated. The Building Electrical Efficiency Analysis Model (BEEAM) is a Modelica library that simulates the efficiency of building electrical distribution systems using harmonic power flow. BEEAM can model a wide variety of building distribution topologies, including three-phase AC, single-phase AC, unipolar DC, bipolar DC, and hybrid networks under both balanced and unbalanced load conditions. BEEAM accurately models power electronic converter losses, provides granular estimates of losses throughout the distribution system, and properly models efficiency at part load conditions. Users can package BEEAM within a functional mockup unit (FMU), enabling co-simulation with other modeling platform, such as EnergyPlus. In summary, BEEAM provides a tool suite for fair and accurate comparison of the efficiency of building electrical distribution systems, including AC, DC, and hybrid systems.

Frank, Stephen↗

Aerial 3D Building Reconstruction from Drone Imagery (A3DBR) v1

This toolkit is composed of several modules for extracting buildings geometrical and thermal characteristics from RGB and thermal imagery captured using a drone. - Building 3D reconstruction module: leverage a photogrammetry software to construct a 3D point cloud from RGB drone imagery, which is then used in conjunction with image processing and geometric methods to extract building footprint and building height (i.e., 3D model of the building). - Windows to wall ratio estimation module: leverage deep learning semantic segmentation modeling to detect windows on 2D drone RGB images. The detected windows are then projected onto the extracted building 3D model (using building 3D reconstruction module) and their area is computed to obtain window to wall ratio estimation. - Thermal anomalies detection module: leverage image processing and machine learning algorithm to detect on 2D drone thermal images potential thermal anomalies within building's facades and roofs.

Granderson, Jessica↗

Towards a Stronger Foundation: Digitizing Commercial Buildings with Brick to Enable Portable Advanced Applications

Most large commercial buildings have digital controls for their heating, ventilation, and air-conditioning (HVAC) and lighting systems with the potential to implement advanced control strategies and data analytics. However, advanced control strategies and data analytics are rarely deployed at scale due to non-standard naming conventions and heterogenous building configurations. Semantic metadata standards, like Brick, show promise to proliferate these applications across many buildings, but they have not been widely adopted by industry due to barriers such as perceived risk and unfamiliarity with the technology. This paper describes the workflow we established and evaluated while using it to develop over ten Brick models of existing buildings. Through this process, we observed that digitizing existing commercial buildings is a cost and labor-intensive effort in which understanding the buildings’ data streams is the major bottleneck. Yet, we conclude this investment is worthwhile since various use case applications such as fault detection and diagnostics, thermal comfort analysis, and HVAC control optimization can utilize the same Brick model. The paper also explores the challenges and lessons learned we encountered while creating these data models, such as: 1) difficulties in finding metadata descriptions and relationships for existing buildings; 2) handling missing concepts in the schema needed to model a building; 3) lack of guidance on how to structure the data model or how much detail to include; 4) unfamiliarity with technologies, which makes the learning curve steep for applications developers. Finally, we also describe future directions for semantic metadata research and development to make such transformative technologies more accessible to practitioners.

Roa, Carlos Duarte↗

Commercial Building Tenant Energy Usage Aggregation and Privacy

A growing number of building owners are benchmarking their building energy use. This requires the building owner to acquire monthly whole-building energy usage information, which can be challenging for buildings in which individual tenants have their own utility meters and accounts with the utility. Some utilities and utility regulators have turned to aggregation of customer energy use data (CEUD) as a way to give building owners whole-building energy usage data while protecting customer privacy. Meter profile aggregation adds a layer of protection that decreases the risk of revealing CEUD as the number of meters aggregated increases. The report statistically characterizes the similarity between individual energy usage patterns and whole-building totals at various levels of meter aggregation.

Data aggregation,. Aggregation threhold selection↗

Developing evidence-based prescriptive ventilation rate standards for commercial buildings in California: a proposed framework

Background - The goal of this project, with a focus on commercial buildings in California, was to develop a new framework for evidence-based minimum ventilation rate (MVR) standards that protect occupants in buildings while also considering energy use and cost. This was motivated by research findings suggesting that current prescriptive MVRs in commercial buildings do not provide occupants with fully safe and satisfactory indoor environments. Methods - The project began with a broad review in several areas ? the diverse strategies now used for standards or guidelines for MVRs or for environmental contaminant exposures, current knowledge about adverse human effects associated with VRs, and current knowledge about contaminants in commercial buildings, including their their presence, their adverse human effects, and their relationships with VRs. Based on a synthesis of the reviewed information, new principles and approaches are proposed for setting evidence-based VRs standards for commercial buildings, considering a range of human effects including health, performance, and acceptability of air. Results ? A review and evaluation is first presented of current approaches to setting prescriptive building ventilation standards and setting acceptable limits for human contaminant exposures in outdoor air and occupational settings. Recent research on approaches to setting acceptable levels of environmental exposures in evidence-based MVR standards is also described. From a synthesis and critique of these materials, a set of principles for setting MVRs is presented, along with an example approach based on these principles. The approach combines two sequential strategies. In a first step, an acceptable threshold is set for each adverse outcome that has a demonstrated relationship to VRs, as an increase from a (low) outcome level at a high reference ventilation rate (RVR, the VR needed to attain the best achievable levels of the adverse outcome); MVRs required to meet each specific outcome threshold are estimated; and the highest of these MVRs, which would then meet all outcome thresholds, is selected as the target MVR. In a second step, implemented only if the target MVR from step 1 is judged impractically high, costs and benefits are estimated and this information is used in a risk management process. Four human outcomes with substantial quantitative evidence of relationships to VRs are identified for initial consideration in setting MVR standards. These are: building-related symptoms (sometimes called sick building syndrome symptoms), poor perceived indoor air quality, and diminished work performance, all with data relating them directly to VRs; and cancer and non-cancer chronic outcomes, related indirectly to VRs through specific VR-influenced indoor contaminants. In an application of step 1 for offices using a set of example outcome thresholds, a target MVR of 9 L/s (19 cfm) per person was needed. Because this target MVR was close to MVRs in current standards, use of a cost/benefit process seemed unnecessary. Selection of more stringent thresholds for one or more human outcomes, however, could raise the target MVR to 14 L/s (30 cfm) per person or higher, triggering the step 2 risk management process. Consideration of outdoor air pollutant effects would add further complexity to the framework. For balancing the objective and subjective factors involved in setting MVRs in a cost-benefit process, it is suggested that a diverse group of stakeholders make the determination after assembling as much quantitative data as possible.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Training in Building Audit Technologies

In 2011, the Tribe proposed and was awarded the Training in Building Audit Technologies grant from the DOE in the amount of $55,748 to contract for training programs for infrared cameras, blower door technology applications and building systems. The coursework consisted of; Infrared Camera Training: Level I - Thermal Imaging for Energy Audits; Blower Door Analysis and Building-As-A-System Training, Building Performance Institute (BPI) Building Analyst; Building Envelope Training, Building Performance Institute (BPI) Envelope Professional; and Audit/JobFLEX Tablet Software. Competitive procurement of the training contractor resulted in lower costs, allowing the Tribe to request and receive DOE approval to additionally purchase energy audit equipment and contract for residential energy audits of 25 low-income Tribal Housing units. Sault Tribe personnel received field training to supplement the classroom instruction on proper use of the energy audit equipment. Field experience was provided through the second DOE energy audits grant, allowing Sault Tribe personnel to join the contractor, Building Science Academy, in conducting 25 residential energy audits of low-income Tribal Housing units.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Buildings Interoperability Landscape – DRAFT

Buildings are an integral part of our nation’s energy economy. The advancement in information and communications technology (ICT) has revolutionized energy management in industrial facilities and large commercial buildings. As ICT costs decrease and capabilities increase, buildings automation and energy management features are transforming the small-medium commercial and residential buildings sectors. A vision of a connected world in which equipment and systems within buildings coordinate with each other to efficiently meet their owners’ and occupants’ needs, and where buildings regularly transact business with other buildings and service providers (such as gas and electric service providers) is emerging. However, while the technology to support this collaboration has been demonstrated at various degrees of maturity, the integration frameworks and ecosystems of products that support the ability to easily install, maintain, and evolve building systems and their equipment components are struggling to nurture the fledging business propositions of their proponents.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Energy Efficiency Building Systems Regional Innovation Cluster Initiative

The Consortium for Building Energy Innovation (CBEI) was established through a Funding Opportunity Announcement led by the U.S. Department of Energy, under a cooperative agreement managed by the National Energy Technology Laboratory. CBEI is led by The Pennsylvania State University and is composed of partners from academia, the private sector, and economic development agencies. The Consortium has included as many as 24 different partners over the five years, but 14 have been core to the work over the five year cooperative agreement. CBEI primarily focused on developing energy efficiency solutions for the small and medium commercial building market, with a focus on buildings less than 50,000 square feet. This market has been underserved by the energy efficiency industry, which has focused on larger commercial buildings where the scale of an individual retrofit lends itself to the use of sophisticated modeling tools and more advanced solutions. Owners/operators and retrofit providers for larger buildings have a greater level of understanding of, and experience with different solutions. In contrast, smaller commercial building retrofits, like residential retrofits, often have owners with less knowledge about energy management and less time to learn about it. This market segment is also served by retrofit providers that are smaller and often focused on particular building systems, e.g. heating, ventilation and air conditioning (HVAC), lighting, roofing, or insulation. The size of a smaller commercial building retrofit does not lend itself, from a cost perspective, to the application of multiple, sophisticated design and modeling tools, which means that they are less likely to have integrated solutions.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Building Protection Against External Ionizing Fallout Radiation

A nuclear explosion has the potential to injure or kill tens to hundreds of thousands of people through exposure to fallout (external gamma) radiation. Existing buildings can protect their occupants (reducing external radiation exposures) by placing material and distance between fallout particles and indoor individuals. This protection is not well captured in current fallout risk assessment models and so the US Department of Defense is implementing the Regional Shelter Analysis methodology to improve the ability of the Hazard Prediction and Assessment Capability (HPAC) model to account for building protection. This report supports the HPAC improvement effort by identifying a set of building attributes (next page) that, when collectively specified, are sufficient to calculate reasonably accurate, i.e., within a factor of 2, fallout shelter quality estimates for many individual buildings. The set of building attributes were determined by first identifying the key physics controlling building protection from fallout radiation and then assessing which building attributes are relevant to the identified physics. This approach was evaluated by developing a screening model (PFscreen) based on the identified physics and comparing the screening model results against the set of existing independent experimental, theoretical, and modeled building protection estimates. In the interests of transparency, we have developed a benchmark dataset containing (a) most of the relevant primary experimental data published by prior generations of fallout protection scientists as well as (b) the screening model results.

42 ENGINEERING↗

Establishing a Commercial Buildings Energy Data Framework for India: A Comprehensive Look at Data Collection Approaches, Use Cases and Institutions

Enhancing energy efficiency of the commercial building stock is an important aspect of any national energy policy. Understanding how buildings use energy is critical to formulating any new policy that may impact energy use, underscoring the importance of credible data. Data enables informed decision making and good quality data is essential for policy makers to prioritize energy saving strategies and track implementation. Given the uniqueness of the buildings sector and challenges to collecting relevant energy data, this study characterizes various elements involved in pertinent data collection and management, with the specific focus on well-defined data requirements, appropriate methodologies and processes, feasible data collection mechanisms, and approaches to institutionalizing the collection process. This report starts with a comprehensive review of available examples of energy data collection frameworks for buildings across different countries. The review covers the U.S. experience in the commercial buildings sector, the European experience in the buildings sector and other data collection initiatives in Singapore and China to capture the more systematic efforts in Asia in the commercial sector. To provide context, the review includes a summary and status of disparate efforts in India to collect and use commercial building energy data. Using this review as a key input, the study developed a data collection framework for India with specific consideration to relevant use cases. Continuing with the framework for data collection, this study outlines the key performance indicators applicable to the use cases and their collection feasibility, as well as immediate priorities of the participating stakeholders. It also discusses potential considerations for data collection and the possible approaches for survey design. With the specific purpose of laying out the possible ways to structure and organize data collection institutionally, the study collates existing mechanisms to analyze building energy performance in India and opportunities for standardizing data collection. This report describes the existing capacities and resources for establishing an institutional framework for data collection, the legislation and mandates that support such activity, and identifies roles and responsibilities of the relevant ministries and organizations. Finally, the study presents conclusions and identifies two major data collection strategies within the existing legal framework.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Exploration of Domain Aware Machine Learning for Grid Analytics: Transfer-Learnt Energy Models to Assist Buildings Control with Sparse Field Data

Buildings are a primary consumer of energy in the United States and are also increasingly being perceived as providers of grid services such as load shifting, shedding and modulation. High fidelity models of building energy consumption are needed to set appropriate baselines for measurement and verification (M&V) of controllers designed for energy efficient operation of buildings and to enable buildings to provide grid services via. participation in demand response programs. State-of-the-art building energy modeling techniques either rely on Physics based models, or extensive instrumentation of the building envelope to gather “big” data to train machine learning based models such as deep neural networks. While Physics based models are often limited by their accuracy, it is not always feasible to gather a significant amount of field data required to train machine learning based models with sufficient accuracy. In this paper, we explore the use of transfer learning-based strategies to address unsatisfactory accuracy of models for estimating building energy consumption when available field data for training is sparse or of unacceptable quality. In particular, we transfer knowledge in the form of data and parameters, from Physics based simulation frameworks to the field to improve the model accuracy, thus resulting in a Physics-informed Machine Learning framework. We evaluated the efficacy of our approach on field data collected from six commercial buildings and our results indicate that the proposed transfer learning based models provide comparative (and in some cases better) accuracy than state-of-the-art machine learning and deep learning solutions, with just one month of field data.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗