Forecast Building Energy Research Articles

Adaptive Ensemble Learning for Enhancing Building Energy Consumption Prediction: Insights from COVID-19 Pandemic Energy Consumption Dynamics

Buildings account for approximately 40% of the total global energy consumption. Therefore, accurate prediction of building energy consumption is necessary to optimize resource allocation and promote sustainable energy usage. A key challenge in developing building energy consumption models is their adaptability to abrupt changes in consumption patterns owing to extraordinary events, such as the COVID-19 pandemic. Therefore, a two-layer ensemble-learning (EL) model incorporating sliding windows as input features is proposed. The model is a two-layer stacking EL consisting of two base learning methods: (1) support vector regression (SVR), and (2) random forest (RF). Temperature and humidity are included to account for the influence of weather conditions on energy consumption. The proposed model is deployed to forecast building energy consumption both before (November 2019) and during (May – October 2020) the COVID-19 pandemic and is compared with a single machine learning model. The results demonstrate that the EL model outperforms the SVR and RF methods, providing excellent prediction accuracy even during the pandemic when significant changes in energy consumption patterns occurred. The findings also highlight the effectiveness of sliding windows as input features for improving model adaptability. Additionally, the analysis reveals that temperature is more prominent than humidity for improving prediction accuracy.

GWO-ANFIS-RD3PG: A reinforcement learning approach with dynamic adjustment and dual replay mechanism for building energy forecasting

Reliable prediction of building energy consumption is essential for effective and sustainable energy management. Traditional forecasting methods, however, face challenges when dealing with sudden changes in energy consumption. To address the above-mentioned issue, we introduce the GWO-ANFIS-RD3PG prediction model in this paper. This model aims to ensure global forecasting accuracy while minimizing prediction errors at sudden change points. A Grey Wolf Optimization (GWO) algorithm with the Adaptive Neuro-Fuzzy Inference System (ANFIS) is proposed to predict the energy consumption type and its fluctuation magnitude for the next time step. Within the Recurrent Dual Experience Replay Buffer DDPG (RD3PG) prediction module, we employ Long Short-Term Memory (LSTM), as the actor network in the Deep Deterministic Policy Gradient (DDPG), to account for long-term dependencies in time series data. Notably, we introduce an adaptive action modification mechanism that allows the agent to optimize actions based on the output of the aforementioned ANFIS, enabling real-time adjustments during sudden change. To further enhance the model’s performance, we adopt a dual experience replay mechanism to store data samples from sudden change points, capturing insight information during these anomalies. Experimental results on two real-world datasets demonstrate that this method reduces MAE by 5.81% and 13.47%, and RMSE by 5.69% and 15.21% compared to the state-of-art models, showing the significance of the proposed method for energy efficiency improvement in real-world building operations.

A nonparametric least squares regression method for forecasting building energy performance

The Convex Nonparametric Least Squares (CNLS) method assumes that the regression function is either concave or convex to forecast building energy performance. However, there may be instances where the regression function exhibits both concave and convex patterns, rendering this assumption invalid. This paper aims to address this drawback and to derive a new method called Monotone Nonparametric Least Squares (MNLS), which incorporates both concavity and convexity constraints in CNLS. It is proved that MNLS has a better goodness-of-fit performance compared to CNLS. Since MNLS contains both concave and convex portions, it is not sufficient to rely solely on the concavity assumption (or convexity assumption) during the forecasting process of building energy performance. To tackle this issue, using both concave and convex portions separately and then combining the resulting forecasts is suggested. An illustrative example is provided, and the energy performance of Hong Kong secondary schools is used as an application to demonstrate the goodness-of-fit of MNLS.

BEForeGAN: An image-based deep generative approach for day-ahead forecasting of building HVAC energy consumption

This study presents a pioneering approach in building energy forecasting by introducing a novel reformulation framework that transforms the forecasting task into an image inpainting problem. Based upon the fundamental notion that “forecasting is about generating data of the future”, we propose BEForeGAN, an innovative deep generative approach for day-ahead Building HVAC Energy consumption Forecasting based on multi-channel conditional Generative Adversarial Networks (GANs) with U-Net generators. Our method is evaluated using 96,360 hourly HVAC energy consumption records from 11 buildings, demonstrating significant accuracy improvements of 17%∼76% and a substantial variability reduction of 3%∼96% compared to a suite of conventional and deep learning benchmark models across individual-building and zero-shot cross-building forecasting tasks. Notably, BEForeGAN exhibits robustness to noisy inputs, with an increase below 3% in Coefficient of Variation of Root Mean Square Error (CV-RMSE) for each 10% noise increment. This study addresses critical gaps in existing literature by showcasing the untapped potential of GANs as standalone forecasters, advocating for further exploration of two-dimensional (2D) GAN-based methods in building energy forecasting, and emphasising the need for more studies focusing on cross-building forecasting tasks. In conclusion, our findings underscore the transformative impact of GANs in revolutionising building energy forecasting practices, paving the way for enhanced energy-efficient building management and beyond.

Intrinsically interpretable machine learning-based building energy load prediction method with high accuracy and strong interpretability

Black-box models have demonstrated remarkable accuracy in forecasting building energy loads. However, they usually lack interpretability and do not incorporate domain knowledge, making it difficult for users to trust their predictions in practical applications. One important and interesting question remains unanswered: is it possible to use intrinsically interpretable models to achieve accuracy comparable to that of black-box models? With an aim of answering this question, this study proposes an intrinsically interpretable machine learning-based method to forecast building energy loads. It creatively combines two intrinsically interpretable machine learning algorithms: clustering decision trees and adaptive multiple linear regression. Clustering decision trees aim to automatically identify various building operation conditions, allowing for the training of multiple models tailored to each condition. It can reduce the complexity of model training data, leading to higher accuracy. Adaptive multiple linear regression is an improved regression algorithm tailored to building energy load prediction. It can adaptively modify regression coefficients according to building operations, enhancing the non-linear fitting capability of multiple linear regression. The proposed method is evaluated utilizing the operational data from an office building. The results indicate that the proposed method exhibits comparable accuracy to both random forests and extreme gradient boosting. Furthermore, it shows significantly superior accuracy, with an average improvement of 10.2 %, compared with some popular black-box algorithms such as artificial neural networks, support vector regression, and classification and regression trees. As for model interpretability, the proposed method reveals that historical cooling loads are the most crucial for predicting building cooling loads under most conditions. Additionally, outdoor air temperature has a significant contribution to building cooling load prediction during the daytime on weekdays in summer and transition seasons. In the future, it will be valuable to explore integrating the laws of physics into the proposed method to further enhance its interpretability.

Transfer learning integrating similarity analysis for short-term and long-term building energy consumption prediction

Currently, building energy consumption prediction models are usually based on a large amount of historical operational data in high demands of building operating hours and monitoring systems. However, many buildings may lack operational data due to relatively limited monitoring systems, causing the failure to use data-driven methods to characterize the energy profile. In this context, transfer learning is a promising method to establish the knowledge transfer between many high-quality building operation datasets and a small amount of target building data, and to help predict energy consumption in the target building. This paper studies the possibility of employing transfer learning to achieve both short and long-term building energy consumption prediction. Firstly, a similarity analysis method, based on variable modal decomposition and dynamic time warping, is proposed for identifying the source buildings with the most similar energy features to the target building. Then, transfer learning for long-term prediction air-conditioning energy consumption is developed with weather parameters generated by the Morphing method as inputs. For the short-term single-step prediction, the proposed model CV-RMSE improves 81.3% (AEC) and 77.4% (EEC), respectively, compared to the prediction model that does not implement the transfer learning strategy and directly uses the target BEC data. As for the short-term multi-step prediction, the proposed model CV-RMSE improves 62.0% (AEC) and 65.5% (EEC), respectively. For the long-term prediction, the average CV-RMSE for the whole year is 6.62% and 11.15% for the proposed and directly target domain-based model, respectively. The proposed method explores the practicality of transfer learning in building energy forecasting, contributing to the use of existing building operation data for energy management at different timespan.

DECODE: Data-driven energy consumption prediction leveraging historical data and environmental factors in buildings

Energy prediction in buildings plays a crucial role in effective energy management. Precise predictions are essential for achieving optimal energy consumption and distribution within the grid. This paper introduces a Long Short-Term Memory (LSTM) model designed to forecast building energy consumption using historical energy data, occupancy patterns, and weather conditions. The LSTM model provides accurate short, medium, and long-term energy predictions for residential and commercial buildings compared to existing prediction models. We compare our LSTM model with established prediction methods, including linear regression, decision trees, and random forest. Encouragingly, the proposed LSTM model emerges as the superior performer across all metrics. It demonstrates exceptional prediction accuracy, boasting the highest R2 score of 0.97 and the most favorable mean absolute error (MAE) of 0.007. An additional advantage of our developed model is its capacity to achieve efficient energy consumption forecasts even when trained on a limited dataset. We address concerns about overfitting (variance) and underfitting (bias) through rigorous training and evaluation on real-world data. In summary, our research contributes to energy prediction by offering a robust LSTM model that outperforms alternative methods and operates with remarkable efficiency, generalizability, and reliability.

A comprehensive framework based on Bayesian optimization and skip connections artificial neural networks to predict buildings energy performance

Artificial Neural Networks (ANNs) are a powerful modeling and prediction tool. However, in the energy and buildings fields, certain articles have been highlighted for reducing ANNs' ability to aid in building energy prediction. This result stems from the author's limited ability to regulate a large number of hyper-parameters. As a result, this paper provides a comprehensive study of ANN challenges and solutions in a single framework. The study's research aims may be stated as defining the necessary data preparation stages; selecting the appropriate ANN design for each study scenario with its hyper-parameters; and presenting the approach for training and evaluating ANNs to obtain the best performance. All of these concerns are presented in this study, compiled into a comprehensive framework, and implemented on two different types of real-life data: 1) CBECS data for US commercial buildings, and 2) ASHRAE data for different buildings around the world. The framework optimization loop mainly relies on the Bayesian optimization technique, which employs Gaussian Processes (GP) as a surrogate function; a combination of two concepts (i.e., Expected Improvement (EI) and Probability Improvement (PI)) as an acquisition function; hyper-parameters as a dimension space optimization; and adjusted R2 value as a target optimization score to be improved. Various skip connection ANN architectures are applied to demonstrate the ability to modify ANNs' limitations in the energy and building fields, assuring excellent accuracy and reliability in forecasting building energy performance, with adjusted R2 of more than 0.93 for both data sets.

Predicting and forecasting building energy performance using RSM and ANN

Predicting and forecasting building energy performance using RSM and ANN

Transformers for Energy Forecast.

Forecasting energy consumption models allow for improvements in building performance and reduce energy consumption. Energy efficiency has become a pressing concern in recent years due to the increasing energy demand and concerns over climate change. This paper addresses the energy consumption forecast as a crucial ingredient in the technology to optimize building system operations and identifies energy efficiency upgrades. The work proposes a modified multi-head transformer model focused on multi-variable time series through a learnable weighting feature attention matrix to combine all input variables and forecast building energy consumption properly. The proposed multivariate transformer-based model is compared with two other recurrent neural network models, showing a robust performance while exhibiting a lower mean absolute percentage error. Overall, this paper highlights the superior performance of the modified transformer-based model for the energy consumption forecast in a multivariate step, allowing it to be incorporated in future forecasting tasks, allowing for the tracing of future energy consumption scenarios according to the current building usage, playing a significant role in creating a more sustainable and energy-efficient building usage.

Forecasting energy demand of PCM integrated residential buildings: A machine learning approach

Forecasting energy demand has become an essential element for energy stakeholders in planning and reducing the energy consumption of buildings. Machine learning techniques have become popular for forecasting building energy demand owing to their reliability and cost efficiency. This research aims to propose a model for predicting the energy consumption of PCM-integrated residential buildings in the Mediterranean climate region. For the model development, Multiple Regression (MR), Support Vector Machines (SVM), and Artificial Neural Networks (ANN) were used. For the first time, the PCM melting point, building, and environment parameters were considered simultaneously as input parameters to predict the energy consumption of PCM-integrated buildings. The energy simulation of nine different building types located in seven different cities of the Mediterranean climate region were performed to generate the database. After the model development, the most influential design parameters were established by performing sensitivity and parametric analysis. The results showed that the optimum PCM for annual energy savings varied from PCM-25 to PCM-27. The shape factor significantly influenced the specific heating and cooling demand of buildings. Moreover, the statistically evaluated prediction models showed that SVM and ANN methods are more reliable, with R2 value of over 0.99. The externally validated prediction models demonstrated that the ANN model can estimate the energy consumption of PCM-integrated buildings with more accuracy. From sensitivity analysis, it was found that cooling degree days, heating degree days, volume, shape factor, and PCM melting point are the key influencing parameters affecting the energy demand of buildings.

Using Real Building Energy Use Data to Explain the Energy Performance Gap of Energy-Efficient Residential Buildings: A Case Study from the Hot Summer and Cold Winter Zone in China

The International Energy Agency (IEA) emphasizes that using real building energy use data (RBEUD) to reflect the actual condition of buildings and inform policy-making is the most effective way to reduce buildings’ carbon emissions. However, based on IEA’s evaluation, regional and national building stock data are limited and lacking. Especially for China, the lack of RBEUD in buildings has limited our ability to address the energy performance gap (EPG). In this research, EPG refers to the difference between regulated energy consumption by design standards and actual energy usage. EPG makes it difficult to develop buildings that are energy-efficient. Therefore, this study aims to gather and analyze RBEUD in order to understand the role of occupants’ behavior in explaining the EPG of energy-efficient residential buildings in China. The results suggest that the actual consumption of residential buildings is less than 1/5–1/3 of the theoretical limits. The heat pump and air conditioner’s actual schedules and setpoint settings are the significant drivers that explain the EPG. In addition, the presentation of a database of 1128 households provides actual usage behavior parameters for policy-makers to improve the accuracy of building energy forecasting models.

Analysis of Challenges and Solutions of IoT in Smart Grids Using AI and Machine Learning Techniques: A Review

With the assistance of machine learning, difficult tasks can be completed entirely on their own. In a smart grid (SG), computers and mobile devices may make it easier to control the interior temperature, monitor security, and perform routine maintenance. The Internet of Things (IoT) is used to connect the various components of smart buildings. As the IoT concept spreads, SGs are being integrated into larger networks. The IoT is an important part of SGs because it provides services that improve everyone’s lives. It has been established that the current life support systems are safe and effective at sustaining life. The primary goal of this research is to determine the motivation for IoT device installation in smart buildings and the grid. From this vantage point, the infrastructure that supports IoT devices and the components that comprise them is critical. The remote configuration of smart grid monitoring systems can improve the security and comfort of building occupants. Sensors are required to operate and monitor everything from consumer electronics to SGs. Network-connected devices should consume less energy and be remotely monitorable. The authors’ goal is to aid in the development of solutions based on AI, IoT, and SGs. Furthermore, the authors investigate networking, machine intelligence, and SG. Finally, we examine research on SG and IoT. Several IoT platform components are subject to debate. The first section of this paper discusses the most common machine learning methods for forecasting building energy demand. The authors then discuss IoT and how it works, in addition to the SG and smart meters, which are required for receiving real-time energy data. Then, we investigate how the various SG, IoT, and ML components integrate and operate using a simple architecture with layers organized into entities that communicate with one another via connections.

A physics-based domain adaptation framework for modeling and forecasting building energy systems

Abstract State-of-the-art machine-learning-based models are a popular choice for modeling and forecasting energy behavior in buildings because given enough data, they are good at finding spatiotemporal patterns and structures even in scenarios where the complexity prohibits analytical descriptions. However, their architecture typically does not hold physical correspondence to mechanistic structures linked with governing physical phenomena. As a result, their ability to successfully generalize for unobserved timesteps depends on the representativeness of the dynamics underlying the observed system in the data, which is difficult to guarantee in real-world engineering problems such as control and energy management in digital twins. In response, we present a framework that combines lumped-parameter models in the form of linear time-invariant (LTI) state-space models (SSMs) with unsupervised reduced-order modeling in a subspace-based domain adaptation (SDA) approach, which is a type of transfer-learning (TL) technique. Traditionally, SDA is adopted for exploiting labeled data from one domain to predict in a different but related target domain for which labeled data is limited. We introduced a novel SDA approach where instead of labeled data, we leverage the geometric structure of the LTI SSM governed by well-known heat transfer ordinary differential equations to forecast for unobserved timesteps beyond available measurement data by geometrically aligning the physics-derived and data-derived embedded subspaces closer together. In this initial exploration, we evaluate the physics-based SDA framework on a demonstrative heat conduction scenario by varying the thermophysical properties of the source and target systems to demonstrate the transferability of mechanistic models from physics to observed measurement data.

An intelligent big data analytics method for two-dimensional non-residential building energy forecasting

The wide use of sensor and information technologies in buildings resulted in the massive generation of data related to its operation. Thus, there is a need for identifying patterns in data that they may use for the optimal operation of the buildings. The case of non-residential building characteristically provides a big volume of data whose analysis requires computational efficient methods. In this paper, we introduce a new big data analytic method that is applicable to forecasting energy demand in non-residential buildings. The goal is to make energy forecasts in a two-dimensional (2D) space defined by i) the electricity load and ii) gas demand. The proposed method combines the matrix profile (MP) method with a Long-Short Term Memory (LSTM) neural network. The combination of the above tools provides an efficient method in 2D hour ahead forecasting with the big data environment of smart buildings. In specific, with respect to mean average percentage error (MAPE) the combined MP-LSTM method provides a concurrent forecast of electricity and gas around 3% and 4%, respectively.

Multiobjective optimization of building energy consumption and thermal comfort based on integrated BIM framework with machine learning-NSGA II

Detailed parametric analysis and measurements are required to reduce building energy usage while maintaining acceptable thermal conditions. This research suggested a system that combines Building Information Modeling (BIM), machine learning, and the non-dominated sorting genetic algorithm-II (NSGA II) to investigate the impact of building factors on energy usage and find the optimal design. A plugin is developed to receive sensor data and export all necessary information from BIM to MSSQL and Excel. The BIM model was imported to IDA Indoor Climate and Energy (IDA ICE) to execute an energy consumption simulation and then a pairwise test to produce the sample data set. To study the data set and develop a prediction model between building factors and energy usage, 11 machine learning algorithms are used. The best algorithm was Group Least Square Support Vector Machine (GLSSVM), later employed in NSGA II as the building energy consumption fitness function using Dynamo software. An NSGA II multi-objective optimization model is designed to reduce building energy consumption and optimize interior thermal comfort (measured by the predicted percentage of dissatisfied (PPD)). The Pareto front is calculated, and the optimum point approach is used to find the best combination of building envelope characteristics, HVAC setpoints, shading parameters, lighting, and air infiltration. The feasibility and effectiveness of the developed framework are demonstrated using a case study of an upper secondary school building in Norway; the results show that: (1) The GLSSVM has a unique capacity to forecast building energy use with high accuracy: R2 of 0.99, an RMSE of 1.2, MSE of 1.44, and MAE of 0.89; (2) Building energy consumption and thermal comfort may be successfully improved by the GLSSVM-NSGA II hybrid technique, which reduces energy consumption by 37.5% and increases thermal comfort by 33.5%, respectively.

Machine Learning, Deep Learning and Statistical Analysis for forecasting building energy consumption — A systematic review

The building sector accounts for 36 % of the total global energy usage and 40% of associated Carbon Dioxide emissions. Therefore, the forecasting of building energy consumption plays a key role for different building energy management applications (e.g., demand-side management and promoting energy efficiency measures), and implementing intelligent control strategies. Thanks to the advancement of Internet of Things in the last few years, this has led to an increase in the amount of buildings energy related-data. The accessibility of this data has inspired the interest of researchers to utilize different data-driven approaches to forecast building energy consumption. In this study, we first present state of-the-art Machine Learning, Deep Learning and Statistical Analysis models that have been used in the area of forecasting building energy consumption. In addition, we also introduce a comprehensive review of the existing research publications that have been published since 2015. The reviewed literature has been categorized according to the following scopes: (I) building type and location; (II) data components; (III) temporal granularity; (IV) data pre-processing methods; (V) features selection and extraction techniques; (VI) type of approaches; (VII) models used; and (VIII) key performance indicators. Finally, gaps and current challenges with respect to data-driven building energy consumption forecasting have been highlighted, and promising future research directions are also recommended.

Short-term building electrical load forecasting using adaptive neuro-fuzzy inference system (ANFIS)

The aim of this study is to develop very short-term and accurate energy consumption forecasts for educational building. The purpose is to develop a predictive model for building energy planning to balance the supply from renewable power systems and the building electrical load demand). For the methodology, an adaptive neuro-fuzzy inference system (ANFIS) was used as a machine learning approach for building energy forecasting. The data for training (80%), testing (10%), and validation (10%) was used from smart energy meters installed in the building and weather data. A total of 20520 dataset instances was used for developing the forecasting model. The originality of this study is the ANFIS model was validated for the training, testing, and validation data, and the accuracy and reliability of the forecasting model was assessed over various very short time horizon of past data (0.5–4 h ahead). The main results reveal that the predictive model is extremely accurate in predicting the energy consumption of a building. The values of coefficient of correlation R for training, testing, and validation are 0.98017, 0.9778, and 0.97593, respectively, for the 30 min ahead energy forecasting. The R values for all the data are respectively 0.97951, 09854, and 0,96778 for the 0.5, 1, 4 h ahead energy forecasting. The low nMSE and nMAE errors for the ANFIS model demonstrate how well the model replicates the reported results from smart energy meters. The research findings are very important for the energy planning of microgrid power systems (energy purchase, building operations and maintenance, and demand side management).

Forecasting Building Energy Consumption Using Ensemble Empirical Mode Decomposition, Wavelet Transformation, and Long Short-Term Memory Algorithms

A building, a central location of human activities, is equipped with many devices that consume a lot of electricity. Therefore, predicting the energy consumption of a building is essential because it helps the building management to make better energy management policies. Thus, predicting energy consumption of a building is very important, and this study proposes a forecasting framework for energy consumption of a building. The proposed framework combines a decomposition method with a forecasting algorithm. This study applies two decomposition algorithms, namely the empirical mode decomposition and wavelet transformation. Furthermore, it applies the long short term memory algorithm to predict energy consumption. This study applies the proposed framework to predict the energy consumption of 20 buildings. The buildings are located in different time zones and have different functionalities. The experiment results reveal that the best forecasting algorithm applies the long short term memory algorithm with the empirical mode decomposition. In addition to the proposed framework, this research also provides the recommendation of the forecasting model for each building. The result of this study could enrich the study about the building energy forecasting approach. The proposed framework also can be applied to the real case of electricity consumption.

The Impact of Climate Change on a University Campus’ Energy Use: Use of Machine Learning and Building Characteristics

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.