Article

Campus Energy Use Prediction Using Artificial Intelligence to Study Climate Change Impacts

Authors:
  • University of Florida - Urban Building Energy Sensing, Controls, Big Data Analysis, and Visualization (UrbSys) Lab
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

When managing the energy performance of a portfolio of buildings over time, climate change can be a threat as it can cause significant changes in energy use patterns. This paper uses artificial intelligence techniques to develop an AI-based forecasting tool, Campus Energy Use Prediction (CEUP) that can help managers to forecast campus future monthly energy use under various climate scenarios. We have leveraged historical energy use data of buildings in the University of Florida, Gainesville, FL to develop CEUP. CEUP was then used to forecast the impact of climate change with the average outdoor temperature of the median, hottest, and coldest years of future climate scenarios of Gainesville, FL as input.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Such data can be used for efficient decision making at various levels. There is a constant need for enhancing infrastructure performance through leveraging the digital footprint and using data-driven decision tools [1][2][3][4][5]. The idea of smart cities addresses how the advancement and unavoidable use of Information and Communication Technology (ICT) can impact urban development in regards to environmental, financial, and personal satisfaction aspects [6]. ...
... The temporary IAM tokens expire in 15 days. 5. HTTP requests (e.g., GET/items and POST/survey) can be performed to fetch or store data such as logged route information as well as survey data that the user has input. ...
Article
Full-text available
The decisions managing all modes of transportation are currently based on the traffic rate and travel time. However, other factors such as Green House Gas (GHG) emissions, the sustainability index, fuel consumption, and travel costs are not considered. Therefore, more comprehensive methods need to be implemented to improve transportation systems and support users’ decision making in their daily commute. This paper addresses current challenges by utilizing data analytics derived from our proposed mobile application. The proposed application quantifies various factors of each transportation mode including but not limited to the cost, trip duration, fuel consumption, and Carbon Dioxide (CO2) emissions. All calculated travel costs are based on the real-time gas prices and toll fees. The users are also able to navigate to their destination and update the total travel costs in real-time. The emissions data per trip basis are aggregated to provide analytics of emissions usage. The traffic data is collected for the Southern California region and the effectiveness of the application is evaluated by twenty participants from California State University, Long Beach. The results demonstrate the application’s impacts on users’ decision-making and the propriety of the factors used in route selection. The proposed application can foster urban planning and operations vis-à-vis daily commutes, and as a result improve the citizens’ quality of life in various aspects.
... Accompanied by the continuous advancement of the global digital wave and the diversified development needs of higher education, the university governance team needs to further change its development concept. Taking the development of digital education as an entry point, they should shift from epitaxial development to connotative enhancement and support the construction of Chinese-style modernization with highquality higher education [10][11]. ...
Article
Full-text available
At this stage, the information literacy of teachers and students is constantly improving, and the “digital campus” represented by artificial intelligence is landing in various regions and schools. This paper accurately constructs a college management and education innovation system based on artificial intelligence technology, including institutional mechanisms, a one-stop service platform, and an early warning mechanism. The early warning mechanism has an early warning model constructed. The construction of an academic early warning model for students is based on multivariate linear regression. A model for early warning of student activity safety was constructed using multiclassification logistic regression. The impact of fusing the two models was evaluated, as well as the impact of practical application. The ROC value of the first-level warning is 0.9533, and the ROC value of the second-level warning is 0.9428, and both values are close to 1, which verifies that the model can be practically applied. By analyzing the F1-score value through practical application, the average value of the F1-score throughout the semester was as high as 84.68%, and the number of warnings of the early warning model was higher than the number of feedback from teachers. It has been verified that the early warning model in this study can effectively and efficiently manage student activities and academic anomalies in colleges and universities.
... By integrating advanced machine learning techniques, AI can propose fresh insights in complex climate simulations in the field of climate modelling [57]. Energy consumption patterns might undergo considerable changes due to climatic change, which means AI forecasts can aid in estimating future energy use for various climate scenarios [58]. ...
Conference Paper
Full-text available
In the face of an impending global energy crisis and the imperative to combat climate change, the integration of artificial intelligence (AI) into the energy sector stands as a seismic shift in the way we approach energy sustainability. This study embarks on a comprehensive journey into the profound and multifaceted role of AI in catalyzing the smart energy transition. Cases studied include; Sustainable buildings and energy consumption, AI-based DSSs for sustainable urban water management, climate artificial intelligence (climate informatics), agriculture 4.0 and sustainable sources of energy, convergence of IoT & AI for sustainable smart cities, AI-based evaluation of renewable energy technologies, and AI for energy optimization. It further delves deep into how AI is revolutionizing renewable energy generation, grid optimization, demand-side management, and carbon emissions reduction, and even envision the path forward, including the ethical and regulatory frameworks that will shape this transformative journey in Nigeria and its environs.
... By integrating advanced machine learing techniques, AI can propose fresh insights in complex climate simulations in the field of climate modeling (Yuval and O'Gorman, 2020). Energy consumption patterns might undergo considerable changes due to climatic change, which means AI forecasts can aid in estimating future energy use for various climate scenarios (Fathi et al., 2019). It's not only businesses and other organizations that are using AI algorithms these days-AI algorithms are also being utilized to foster sustainable urban growth and mitigate climate change by examining how future urban expansion will affect material and energy flows (Blecic et al., 2011). ...
Article
Full-text available
Parallel to the rising debates over sustainable energy and artificial intelligence solutions, the world is currently discussing the ethics of artificial intelligence and its possible negative effects on society and the environment. In these arguments, sustainable AI is proposed, which aims at advancing the pathway toward sustainability, such as sustainable energy. In this paper, we offered a novel contextual topic modeling combining LDA, BERT and Clustering. We then combined these computational analyses with content analysis of related scientific publications to identify the main scholarly topics, sub-themes and cross-topic themes within scientific research on sustainable AI in energy. Our research identified eight dominant topics including sustainable buildings, AI-based DSSs for urban water management, climate artificial intelligence, Agriculture 4, convergence of AI with IoT, AI-based evaluation of renewable technologies, smart campus and engineering education and AI-based optimization. We then recommended 14 potential future research strands based on the observed theoretical gaps. In addition to its theoretical contribution to scientific research on sustainable artificial intelligence in energy management, the research utilizes a novel topic modeling method in exploring scientific texts and identifying challenges and possible solutions. A variety of solutions was incorporated, including huggingface tool or elbow method, to address these challenges.
... in life cycle assessment applications with nine typical Florida residential houses [18]. Additionally, Fathi et al. and Fathi and Srinivasan expanded the sample size and targeted a university campus instead of residential buildings, wherein Principal Component Analysis (PCA) and Autoregressive Integrated Moving Average (ARIMA) techniques were selected for energy prediction with climate change [19,20]. Another example is that Godoy-Shimizu et al. estimated urban-scale energy consumption using physics-based models for future weather [21]. ...
Article
Full-text available
Global warming is expected to increase 1.5 °C between 2030 and 2052. This may lead to an increase in building energy consumption. With the changing climate, university campuses need to prepare to mitigate risks with building energy forecasting models. Although many scholars have developed buildings energy models (BEMs), only a few have focused on the interpretation of the meaning of BEM, including climate change and its impacts. Additionally, despite several review papers on BEMs, there is no comprehensive guideline indicating which variables are appropriate to use to explain building energy consumption. This study developed building energy prediction models by using statistical analysis: multivariate regression models, multiple linear regression (MLR) models, and relative importance analysis. The outputs are electricity (ELC) and steam (STM) consumption. The independent variables used as inputs are building characteristics, temporal variables, and meteorological variables. Results showed that categorizing the campus buildings by building type is critical, and the equipment power density is the most important factor for ELC consumption, while the heating degree is the most critical factor for STM consumption. The laboratory building type is the most STM-consumed building type, so it needs to be monitored closely. The prediction models give an insight into which building factors remain essential and applicable to campus building policy and campus action plans. Increasing STM is to raise awareness of the severity of climate change through future weather scenarios.
... Energy consumption patterns might undergo considerable changes due to climatic change, which means AI forecasts can aid in estimating future energy use for various climate scenarios [63]. It's not only businesses and other organizations that are using AI algorithms these days-AI algorithms are also being utilized to foster sustainable urban growth and mitigate climate change by examining how future urban expansion will affect material and energy flows [64]. ...
Preprint
Full-text available
Parallel to the rising debates over sustainable energy and artificial intelligence solutions, the world is currently discussing the ethics of artificial intelligence and its possible negative effects on society and the environment. In these arguments, sustainable AI is proposed, which aims at advancing the pathway toward sustainability, such as sustainable energy. In this paper, we offered a novel contextual topic modeling combining LDA, BERT, and Clustering. We then combined these computational analyses with content analysis of related scientific publications to identify the main scholarly topics, sub-themes, and cross-topic themes within scientific research on sustainable AI in energy. Our research identified eight dominant topics including sustainable buildings, AI-based DSSs for urban water management, climate artificial intelligence, Agriculture 4, the convergence of AI with IoT, AI-based evaluation of renewable technologies, smart campus and engineering education, and AI-based optimization. We then recommended 14 potential future research strands based on the observed theoretical gaps. Theoretically, this analysis contributes to the existing literature on sustainable AI and sustainable energy, and practically, it intends to act as a general guide for energy engineers and scientists, AI scientists, and social scientists to widen their knowledge of sustainability in AI and energy convergence research.
... • There is no study which assesses the effects of climate change on buildings energy performance using future weather scenarios, as well as addressing adaptation strategies or design resiliency. In order to fill this research gap, and as a further study, AI-based prediction tools have been used to study future climate change impacts on campus buildings energy use [100][101][102]104]. ...
Article
In developed countries, buildings are involved in almost 50% of total energy use and 30% of global green-house gas emissions. Buildings’ operational energy is highly dependent on various building physical, operational, and functional characteristics, as well as meteorological and temporal properties. Besides physics-based building energy modeling, machine learning techniques can provide faster and higher accuracy estimates, given buildings’ historic energy consumption data. Looking beyond individual building levels, forecasting buildings’ energy performance helps city and community managers have a better understanding of their future energy needs, and plan for satisfying them more efficiently. Focusing on an urban-scale, this study systematically reviews 70 journal articles, published in the field of building energy performance forecasting between 2015 and 2018. The recent literature have been categorized according to five criteria: 1. Learning Method, 2. Building Type, 3. Energy Type, 4. Input Data, and 5. Time-scale. The scarcity of building energy performance forecasting studies in urban-scale versus individual level is considerable. There is no study incorporating building functionality in terms of space functionality share percentages, nor assessing the effects of climate change on urban buildings energy performance using machine learning approaches and future weather scenarios. There is no optimal criteria combination for achieving the most accurate machine learning-based forecast, as there is no universal measure able to provide such global comparison. Accuracy levels are highly correlated with the characteristics of forecasting problems. The goal is to provide a comprehensive status of machine learning applications in urban building energy performance forecasting, during 2015–2018.
... Due to such interactions, accurate simulation of buildings using energy simulation software is extremely difficult [17]. Therefore, the use of data-driven techniques can fundamentally help in assessing the energy performance of existing buildings [20][21][22][23][24]. These techniques rely on a building's historic data in order to model its future energy use patterns. ...
Article
Full-text available
In developed countries, buildings are involved in almost 50% of total energy use and 30% of global annual greenhouse gas emissions. The operational energy needs of buildings are highly dependent on various building physical, operational, and functional characteristics, as well as meteorological and temporal properties. Besides physics-based energy modeling of buildings, Artificial Intelligence (AI) has the capability to provide faster and higher accuracy estimates, given buildings' historic energy consumption data. Looking beyond individual building levels, forecasting building energy performance can help city and community managers have a better understanding of their future energy needs, and to plan for satisfying them more efficiently. Focusing at an urban scale, this research develops a campus energy use prediction tool for predicting the effects of long-term climate change on the energy performance of buildings using AI techniques. The tool comprises four steps: Data Collection, AI Development, Model Validation, and Model Implementation, and can predict the energy use of campus buildings with 90% accuracy. We have relied on energy use data of buildings situated in the University of Florida, Gainesville, Florida (FL). To study the impact of climate change, we have used climate properties of three future weather files of Gainesville, FL, developed by the North American Regional Climate Change Assessment Program (NARCCAP), represented based on their impact: median (year 2063), hottest (2057), and coldest (2041).
... In the reviewed literature, there is no study which assesses the effects of climate change on community buildings energy performance using future weather scenarios, as well as addressing adaptation strategies or design resiliency. In order to fill this research gap, and as a further study, we have used an AI-based prediction tool to study future climate change impacts on campus buildings energy use [13]. ...
Conference Paper
Almost 50% of global energy consumption is associated with buildings, among which buildings operational energy account for a major share. Buildings operational energy needs are highly dependent on the envelope and space functionality characteristics, as well as climate properties, which is expected to change over time. While managing buildings energy performance, climate change can be a threat as it can cause significant changes in energy use patterns. This paper discusses the use of artificial intelligence techniques to assess the impact of climate change on campus buildings energy use under various future envelope and climate scenarios. We have relied on hourly energy use data of buildings situated in the University of Florida, Gainesville, FL, as well as their thermo-physical and space functionality properties. To study the impact of climate change, we have used climate properties of three future climate scenarios developed by North American Regional Climate Change Assessment Program (NARCCAP) for Gainesville, FL, represented based on their impact within a 40-year prospect: median (year 2063), hottest (2057), and coldest (2041). In order to conduct the scenario analysis, we refer to the Technology Roadmap, Energy Efficient Building Envelopes, that is used to assess and present the development of technology products in building sector. According to the roadmap, we have assessed campus energy use for five envelope scenarios for each of the future climate scenarios.
... This study developed scenarios from individual buildings and the sample size was too small to generalize. Fathi and Srinivasan (2019) expanded the sample size and targeted university campus instead of residential buildings [6,7]. Principal Component Analysis (PCA) and Autoregressive Integrated Moving Average (ARIMA) techniques were selected for energy prediction with climate change. ...
Conference Paper
Full-text available
Global warming is expected to increase of 1.5°C between 2030 and 2052. This may lead to an increase in building energy consumption. With the changing climate, cities, communities, and university campuses need a more dynamic forecasting model to predict their future energy demands to mitigate risks. Although many building energy prediction models have been developed, only a few have focused on climate change and its impacts. This paper discusses the development of a regression-based forecasting model for a university campus energy use under changing climate. The forecasting model development follows a four-step process: (1) data frame setting, (2) descriptive statistics, (3) statistical regression modeling, and (4) validation and prediction. The independent numeric variables used as inputs are building characteristics (gross square feet, lighting power density, equipment power density; U factor of roof, wall, and windows; building age; years after building renovation; and window-to-wall ratio) and weather data (temperature and humidity). The outputs are electricity and chilled water for 2054. Prior to modeling, matrix plots and histograms are used to identify correlations between variables. This step is followed by normalization of independent variables to check their impact. Finally, multiple linear regression model for electricity and Lasso regression models for chilled water estimations are developed. For the purpose of predicting energy consumption owing to climate change, we used weather data that represents 2054. The equipment power density was the most important factor for electricity consumption and temperature was the most important one for chilled water consumption. The prediction models give an insight of which factors remain essential and applicable to campus building policy to prevent wasting energy in buildings, as a result of climate change.
Chapter
Climate change has become the most important issue that face the humanity and hazed the life on the earth. Therefore, the researches have been conducted in continuous mode to reduce the native impacts of climate change and to control its sources. The environmental damage due to the climate change may include, pollution transfer through food chain which affect the food sustainability. In addition, the climate change leads to loss or migration of some species of living organisms including plants, animals, and human resulting in biodiversity change and/or security disturbance. The application of artificial intelligence (AI) enhances the human ability to control climate change for achieving sustainability during usage of environmental resources. This chapter concludes the benefit of AI for addressing environmental problems and preserving the eco-system for sustainable urban development.
Chapter
Cities are facing unprecedented growth with an increase in population and urbanization. The United Nations estimates that the global population will increase to 9.3 billion by 2050, which is an increase of 30% compared to the population in 2011 (UN, 2015). As development in dense urban areas continues, the scientific community must continue to observe, analyze, and interpret the effects of dense urbanization, including climate change impacts on urban sustainability, particularly buildings. The city governments are gradually modifying their policies, decisions, and strategies towards green and energy efficient approaches. Particularly, decisions related to expanding energy generation facilities are critical. Additionally, cities need to manage their energy consumption, now and in future, as they move toward a time variable sources of renewable energy such as solar and wind. In this chapter, we discuss the development of a novel Urban Building Energy CPS (UBE-CPS) framework that bridges the physical and the digital world through seamless data transfer for real-time demand response. While the data from physical world relates to sensor data obtained from buildings, the digital world is the Digital Twin, an advanced machine-learning model that is coupled with urban-scale EnergyPlus™ models that represent individual buildings. Through a feedback loop to the City Utility Manager / Administrator, UBE-CPS will become an integral part of the city energy management to automate and, potentially, control building-level demand curve to satisfy grid-level demand response.
Article
Full-text available
This essay comments and expands upon an emerging area of research, energy communication, that shares with environmental communication the fraught commitment to simultaneously study communication as an ordinary yet potentially transformative practice, and a strategic endeavour to catalyse change. We begin by defining and situating energy communication within ongoing work on the discursive dimensions of energy extraction, production, distribution, and consumption. We then offer three generative directions for future research related to energy transitions as communicative processes: analysing campaigns’ strategic efforts, critically theorizing energy’s transnational power dynamics, and theorizing the energy democracy movement.
Article
Full-text available
Over the past decades, detailed individual building energy models (BEM) on the one side and regional and country-level building stock models on the other side have become established modes of analysis for building designers and energy policy makers, respectively. More recently, these two toolsets have begun to merge into hybrid methods that are meant to analyze the energy performance of neighborhoods, i.e. several dozens to thousands of buildings. This paper reviews emerging simulation methods and implementation workflows for such bottom-up urban building energy models (UBEM). Simulation input organization, thermal model generation and execution, as well as result validation, are discussed successively and an outlook for future developments is presented.
Article
Full-text available
Clustering methods are often used to model energy consumption for two reasons. First, clustering is often used to process data and to improve the predictive accuracy of subsequent energy models. Second, stable clusters that are reproducible with respect to non-essential changes can be used to group, target, and interpret observed subjects. However, it is well known that clustering methods are highly sensitive to the choice of algorithms and variables. This can lead to misleading assessments of predictive accuracy and mis-interpretation of clusters in policymaking. This paper therefore introduces two methods to the modeling of energy consumption in buildings: clusterwise regression, also known as latent class regression, which integrates clustering and regression simultaneously; and cluster validation methods to measure stability. Using a large dataset of multifamily buildings in New York City, clusterwise regression is compared to common two-stage algorithms that use K-means and model-based clustering with linear regression. Predictive accuracy is evaluated using 20-fold cross validation, and the stability of the perturbed clusters is measured using the Jaccard coefficient. These results show that there seems to be an inherent tradeoff between prediction accuracy and cluster stability. This paper concludes by discussing which clustering methods may be appropriate for different analytical purposes.
Article
Full-text available
For prediction of heating energy consumption of a university campus, various artificial neural networks are used: feed forward backpropagation neural network (FFNN), radial basis function network (RBFN) and adaptive neuro-fuzzy interference system (ANFIS). Actual measured data are used for training and testing the models. For each neural networks type, three models (using different number of input parameters) are analyzed. In order to improve prediction accuracy, ensemble of neural networks is examined. Three different combinations of output are analyzed. It is shown that all proposed neural networks can predict heating consumption with great accuracy, and that using ensemble achieves even better results.
Article
Full-text available
Climatic measurements from almost 30 urban and suburban stations as well as specific measurements performed in 10 urban canyons in Athens, Greece, have been used to assess the impact of the urban climate on the energy consumption of buildings. It is found that for the city of Athens, where the mean heat island intensity exceeds 10°C, the cooling load of urban buildings may be doubled, the peak electricity load for cooling purposes may be tripled especially for higher set point temperatures, while the minimum COP value of air conditioners may be decreased up to 25% because of the higher ambient temperatures. During the winter period, the heating load of centrally located urban buildings is found to be reduced up to 30%. Regarding the potential of natural ventilation techniques when applied to buildings located in urban canyons, it is found that, mainly during the day, this is seriously reduced because of the important decrease of the wind speed inside the canyon. Air flow reduction may be up to 10 times the flow that corresponds to undisturbed ambient wind conditions.
Conference Paper
Almost 50% of global energy consumption is associated with buildings, among which buildings operational energy account for a major share. Buildings operational energy needs are highly dependent on the envelope and space functionality characteristics, as well as climate properties, which is expected to change over time. While managing buildings energy performance, climate change can be a threat as it can cause significant changes in energy use patterns. This paper discusses the use of artificial intelligence techniques to assess the impact of climate change on campus buildings energy use under various future envelope and climate scenarios. We have relied on hourly energy use data of buildings situated in the University of Florida, Gainesville, FL, as well as their thermo-physical and space functionality properties. To study the impact of climate change, we have used climate properties of three future climate scenarios developed by North American Regional Climate Change Assessment Program (NARCCAP) for Gainesville, FL, represented based on their impact within a 40-year prospect: median (year 2063), hottest (2057), and coldest (2041). In order to conduct the scenario analysis, we refer to the Technology Roadmap, Energy Efficient Building Envelopes, that is used to assess and present the development of technology products in building sector. According to the roadmap, we have assessed campus energy use for five envelope scenarios for each of the future climate scenarios.
Article
Energy conservation in residential buildings has gained increased attention due to its large portion of global energy use and potential of energy savings. Occupant behavior has been recognized as a key factor influencing the energy use and load diversity in buildings, therefore more realistic and accurate air-conditioning (AC) operating schedules are imperative for load estimation in equipment design and operation optimization. With the development of sensor technology, it became easier to access an increasing amount of heating/cooling data from thermal energy metering systems in residential buildings, which provides another possible way to understand building energy usage and occupant behaviors. However, except for cooling energy consumption benchmarking, there currently lacks effective and easy approaches to analyze AC usage and provide actionable insights for occupants. To fill this gap, this study proposes clustering analysis to identify AC use patterns of residential buildings, and develops new key performance indicators (KPIs) and data analytics to explore the AC operation characteristics using the long-term metered cooling energy use data, which is of great importance for inhabitants to understand their thermal energy use and save energy cost through adjustment of their AC use behavior. We demonstrate the proposed approaches in a residential district comprising 300 apartments, located in Zhengzhou, China. Main outcomes include: Representative AC use patterns are developed for three room types of residential buildings in the cold climate zone of China, which can be used as more realistic AC schedules to improve accuracy of energy simulation; Distributions of KPIs on household cooling energy usage are established, which can be used for household AC use intensity benchmarking and performance diagnoses.
Article
The formulation of energy policies for urban building stock frequently requires the evaluation of the energy use of large numbers of buildings. When urban energy modelling is utilised as part of this process, the identification of building groups and associated representative buildings can play a critical role. This paper outlines a novel methodology for identifying building groups and associated representative buildings in urban datasets. The methodology utilizes a combination of building classification, building clustering and predictive modelling. First, multiple urban-scale datasets are collected, and then, classification techniques and clustering algorithms are applied to identify building clusters. Next, representative buildings (medoids) in each cluster are identified. Predictive modelling is used to expand cluster membership in the case where some buildings were excluded from the previous analysis. A number of different clustering algorithms are assessed, including K-means and hierarchical (agglomerative and divisive) and partitioning around medoids. The methodology is applied to a large dataset of mixed-use buildings in the city of Geneva, Switzerland. The results, assessed by nine validation indices, indicate the capacity of the decision support framework to identify clusters and associated representative buildings. Furthermore, post-application of predictive modelling, using a random forest approach, facilitates the incorporation of a larger portion of the building stock within the established clusters with an overall average classification accuracy of 89%. A total of 67 representative buildings were identified in the urban dataset, which consisted of 13614 mixed-use buildings in the city of Geneva.
Article
Energy is the lifeblood of modern societies. In the past decades, the world's energy consumption and associated CO2 emissions increased rapidly due to the increases in population and comfort demands of people. Building energy consumption prediction is essential for energy planning, management, and conservation. Data-driven models provide a practical approach to energy consumption prediction. This paper offers a review of the studies that developed data-driven building energy consumption prediction models, with a particular focus on reviewing the scopes of prediction, the data properties and the data preprocessing methods used, the machine learning algorithms utilized for prediction, and the performance measures used for evaluation. Based on this review, existing research gaps are identified and future research directions in the area of data-driven building energy consumption prediction are highlighted.
Article
Building energy consumption makes up 40% of the total energy consumption in the United States. Given that energy consumption in buildings is influenced by aspects of urban form such as density and floor-area-ratios (FAR), understanding the distribution of energy intensities is critical for city planners. This paper presents a novel technique for estimating commercial building energy consumption from a small number of building features by training machine learning models on national data from the Commercial Buildings Energy Consumption Survey (CBECS). Our results show that gradient boosting regression models perform the best at predicting commercial building energy consumption, and can make predictions that are on average within a factor of 2 from the true energy consumption values (with an r2 score of 0.82). We validate our models using the New York City Local Law 84 energy consumption dataset, then apply them to the city of Atlanta to create aggregate energy consumption estimates. In general, the models developed only depend on five commonly accessible building and climate features, and can therefore be applied to diverse metropolitan areas in the United States and to other countries through replication of our methodology.
Article
The public buildings sector represents one of the most intensive items of EU energy consumption; the application of retrofit solutions in existing buildings is a crucial way to reduce its impact. To facilitate the knowledge of the energy performance of existing non-residential buildings and the choice of the more adequate actions, Public Administrations (PA) should have the availability of proper tools. Within the Italian project “POI 2007-13”, a database and a decision support tool, for easy use, even to a non-technical user, have been developed. A large set of data, obtained from the energy audits of 151 existing public buildings located in four regions of South Italy have been analysed, elaborated, and organised in a database. This was used to identify the best architectures of two ANNs and to train them. The first ANN provides the actual energy performance of any building; the second ANN assesses key economic indicators. A decision support tool, based on the use of these ANNs is conceived for a fast prediction of the energy performance of buildings and for a first selection of energy retrofit actions that can be applied.
Article
Many cities across the United States have turned to building energy disclosure (or benchmarking) laws to encourage transparency in energy efficiency markets and to support sustainability and carbon reduction plans. In addition to direct peer-to-peer comparisons, the benchmarking data published under these laws have been used as a tool by researchers and policy-makers to study the distribution and determinants of energy use in large buildings. However, these policies only cover a small subset of the building stock in a given city, and thus capture only a fraction of energy use at the urban scale. To overcome this limitation, we develop a predictive model of energy use at the building, district, and city scales using training data from energy disclosure policies and predictors from widely-available property and zoning information. We use statistical models to predict the energy use of 1.1 million buildings in New York City using the physical, spatial, and energy use attributes of a subset derived from 23,000 buildings required to report energy use data each year. Linear regression (OLS), random forest, and support vector regression (SVM) algorithms are fit to the city's energy benchmarking data and then used to predict electricity and natural gas use for every property in the city. Model accuracy is assessed and validated at the building level and zip code level using actual consumption data from calendar year 2014. We find the OLS model performs best when generalizing to the City as a whole, and SVM results in the lowest mean absolute error for predicting energy use within the LL84 sample. Our median predicted electric energy use intensity for office buildings is 71.2 kbtu/sf and for residential buildings is 31.2 kbtu/sf with mean absolute log accuracy ratio of 0.17. Building age is found to be a significant predictor of energy use, with newer buildings (particularly those built since 1991) found to have higher consumption levels than those constructed before 1930. We also find higher electric consumption in office and retail buildings, although the sign is reversed for natural gas. In general, larger buildings use less energy per square foot, while taller buildings with more stories, controlling for floor area, use more energy per square foot. Attached buildings – those with adjacent buildings and a shared party wall – are found to have lower natural gas use intensity. The results demonstrate that electricity consumption can be reliably predicted using actual data from a relatively small subset of buildings, while natural gas use presents a more complicated problem given the bimodal distribution of consumption and infrastructure availability.
Article
Energy consumption forecasting for buildings has immense value in energy efficiency and sustainability research. Accurate energy forecasting models have numerous implications in planning and energy optimization of buildings and campuses. For new buildings, where past recorded data is unavailable, computer simulation methods are used for energy analysis and forecasting future scenarios. However, for existing buildings with historically recorded time series energy data, statistical and machine learning techniques have proved to be more accurate and quick. This study presents a comprehensive review of the existing machine learning techniques for forecasting time series energy consumption. Although the emphasis is given to a single time series data analysis, the review is not just limited to it since energy data is often co-analyzed with other time series variables like outdoor weather and indoor environmental conditions. The nine most popular forecasting techniques that are based on the machine learning platform are analyzed. An in-depth review and analysis of the ‘hybrid model’, that combines two or more forecasting techniques is also presented. The various combinations of the hybrid model are found to be the most effective in time series energy forecasting for building.
Article
Building energy use prediction plays an important role in building energy management and conservation as it can help us to evaluate building energy efficiency, conduct building commissioning, and detect and diagnose building system faults. Building energy prediction can be broadly classified into engineering, Artificial Intelligence (AI) based, and hybrid approaches. While engineering and hybrid approaches use thermodynamic equations to estimate energy use, the AI-based approach uses historical data to predict future energy use under constraints. Owing to the ease of use and adaptability to seek optimal solutions in a rapid manner, the AI-based approach has gained popularity in recent years. For this reason and to discuss recent developments in the AI-based approaches for building energy use prediction, this paper conducts an in-depth review of single AI-based methods such as multiple linear regression, artificial neural networks, and support vector regression, and ensemble prediction method that, by combining multiple single AI-based prediction models improves the prediction accuracy manifold. This paper elaborates the principles, applications, advantages and limitations of these AI-based prediction methods and concludes with a discussion on the future directions of the research on AI-based methods for building energy use prediction.
Article
Urban Building Energy Modeling (UBEM) is an emerging method for exploring energy efficiency solutions at urban or district scales. More versatile than statistical models, physical bottom-up UBEMs allow planners to quantitatively assess retrofit strategies and energy supply options, leading to more effective policies and management of energy demand. The most common approach for formulating an UBEM involves segmenting a building stock into archetypes, characterizing each type, and validating the model by comparing its output to aggregated measured energy consumption. This paper presents a more detailed methodology for setting up UBEMs while faced with incomplete information about the buildings. The procedure calls for defining unknown or uncertain parameters in archetype descriptions as probability distributions and, if available, using measured energy data to update these distributions by Bayesian calibration. The methodology is validated on residential houses in Cambridge, Massachusetts. Distributions for uncertain parameters are initially generated using a training set of 399 homes with monthly electricity and gas consumption records and then applied to a larger test set of 2,263 homes. The procedure is applied both for monthly and annual metered energy usage data. Results show that both annual and monthly Bayesian calibration lead to significantly better annual energy use intensity (EUI) fits compared to traditional deterministic archetype definitions. As expected, an UBEM calibrated with monthly metered data more truthfully mimics monthly EUI distributions than one based on annual data, revealing the benefit of calibrating UBEMs using the smallest measurement time step available.
Article
Although it is often stated that the energy consumption in buildings accounts for more than 30% of total global final energy use, only a few studies analyze updated data about the current building energy consumptions or focus on comparing different countries. Similarly, models that predict future trends in building energy demand often use contrasting algorithms which result in diverse forecasts. Scope of this paper is to present and discuss data taken from several studies about the building energy consumptions in US, EU, and BRIC (Brazil, Russia, India, and China) countries and to provide an updated inventory of useful figures. Comparisons among countries are used to show historical, actual, and future energy consumption trends. Data presented by the World Bank, the United Nations Environment Program, the Intergovernmental Panel on Climate Change, and the International Energy Agency are compared with national reports as well as with research studies. The variety of the approaches used in each of the previous sources was considered fundamental to allow a complete review. The paper shows that the total building energy consumptions in BRIC countries have already overcome those in developed countries, and the continuous increase in the building stock of the BRIC countries creates an urgency for promoting building energy efficiency policies in these countries. At the same time, the policies actually adopted in developed countries are insufficient to guarantee a significant reduction in their building energy consumption in the years to come. In the current scenario, at least a doubling of the global energy demand in buildings compared to today’s levels will occur by 2050. To avoid this forecast, cost-effective best practices and technologies as well as behavioral and lifestyle changes need to be diffused and accepted globally.
Conference Paper
Buildings play a major role in total annual energy use worldwide. The purpose of this study is to evaluate the energy performance of University of Florida (UF) buildings and assess the effects of selected Energy Efficiency Measures (EEMs) on their energy performance. For this study, a set of buildings were identified based on a space functionality classification and two of them were chosen for simulation with energy modeling software. After calibrating the models to match actual energy use, we assessed their performance. The effect of EEMs on reducing the energy demands of buildings were analyzed. Analysis showed the potential energy saving for UF buildings. Modifying the EEMs, we could reduce the Energy Use Intensity values of the simulated buildings for 7-13%. Finally, using extrapolation and previous utility bills data, the campus-wide financial benefits of this saving were discussed.
Article
Energy consumption forecasting is a critical and necessary input to planning and controlling energy usage in the building sector which accounts for 40% of the world’s energy use and the world’s greatest fraction of greenhouse gas emissions. However, due to the diversity and complexity of buildings as well as the random nature of weather conditions, energy consumption and loads are stochastic and difficult to predict. This paper presents a new methodology for energy demand forecasting that addresses the heterogeneity challenges in energy modeling of buildings. The new method is based on a physical–statistical approach designed to account for building heterogeneity to improve forecast accuracy. The physical model provides a theoretical input to characterize the underlying physical mechanism of energy flows. Then stochastic parameters are introduced into the physical model and the statistical time series model is formulated to reflect model uncertainties and individual heterogeneity in buildings. A new method of model generalization based on a convex hull technique is further derived to parameterize the individual-level model parameters for consistent model coefficients while maintaining satisfactory modeling accuracy for heterogeneous buildings. The proposed method and its validation are presented in detail for four different sports buildings with field measurements. The results show that the proposed methodology and model can provide a considerable improvement in forecasting accuracy.
Article
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.
Article
In this paper a new approach for short-term load prediction in buildings is shown. The method is based on a special kind of artificial neural network (ANN), which feeds back a part of its outputs. This ANN is trained by means of a hybrid algorithm. The new system uses current and forecasted values of temperature, the current load and the hour and the day as inputs. The performance of this predictor was evaluated using real data and results from international contests. The achieved results demonstrate the high precision reached with this system.
Directive of the European parliament and of the council on the energy performance of buildings
  • Epbd Directive
EPBD Directive 2002/91/EC (2003). Directive of the European parliament and of the council on the energy performance of buildings. The European Community Official Journal 2003;L001:0065-71.
Modeling Building Energy Performance in Urban Context
  • T Hong
  • X Luo
Hong, T, and Luo, X. (2018). Modeling Building Energy Performance in Urban Context. ASHRAE BPAC Conference, Chicago, IL.
ASHRAE guideline 14, measurement of energy and demand savings
  • Ashrae Standards Committee
ASHRAE Standards Committee. (2002). ASHRAE guideline 14, measurement of energy and demand savings. Atlanta.
Greenovate Boston. 2014 climate action plan update
  • City
  • Boston
City of Boston (2014). Greenovate Boston. 2014 climate action plan update. Boston: City of Boston.
Annual Energy Outlook
U.S Energy Information Administration. (2018). Annual Energy Outlook 2018 with Projections to 2050.