Abstract:An accurate short-term load forecasting system allows an optimum daily operation of the power system and a suitable process of decision-making, such as with regard to control measures, resource planning or initial investment, to be achieved. In a previous work, the authors demonstrated that an SVR model to forecast the electric load in a non-residential building using only the temperature and occupancy of the building as attributes is the one that gives the best balance of accuracy and computational cost for t… Show more
“…A majority of the literature focuses on a single building or a small set of buildings case studies. Other ML reviews in the building industry show similar libraries of work [11,12].…”
Section: Contemporary Building Energy Predictionmentioning
Prediction is a common machine learning (ML) technique used on building energy consumption data. This process is valuable for anomaly detection, load profile-based building control and measurement and verification procedures. Hundreds of building energy prediction techniques have been developed over the last three decades, yet there is still no consensus on which techniques are the most effective for various building types. In addition, many of the techniques developed are not publicly available to the general research community. This paper outlines a library of open-source regression techniques from the Scikit-Learn Python library and describes the process of applying them to open hourly electrical meter data from 482 non-residential buildings from the Building Data Genome Project. The results illustrate that there are several techniques, notably decision tree-based models, that perform well on two-thirds of the total cohort of buildings. However, over one-third of the buildings, specifically primary schools, performed poorly. This example implementation shows that there is no one size-fits-all modeling solution and that various types of temporal behavior are difficult to capture using machine learning. An analysis of the generalizability of the models tested motivates the need for the application of future techniques to a board range of building types and behaviors. The importance of this type of scalability analysis is discussed in the context of the growth of energy meter and other Internet-of-Things (IoT) data streams in the built environment. This framework is designed to be an example baseline implementation for other building energy data prediction methods as applied to a larger population of buildings. For reproducibility, the entire code base and data sets are found on Github.
“…A majority of the literature focuses on a single building or a small set of buildings case studies. Other ML reviews in the building industry show similar libraries of work [11,12].…”
Section: Contemporary Building Energy Predictionmentioning
Prediction is a common machine learning (ML) technique used on building energy consumption data. This process is valuable for anomaly detection, load profile-based building control and measurement and verification procedures. Hundreds of building energy prediction techniques have been developed over the last three decades, yet there is still no consensus on which techniques are the most effective for various building types. In addition, many of the techniques developed are not publicly available to the general research community. This paper outlines a library of open-source regression techniques from the Scikit-Learn Python library and describes the process of applying them to open hourly electrical meter data from 482 non-residential buildings from the Building Data Genome Project. The results illustrate that there are several techniques, notably decision tree-based models, that perform well on two-thirds of the total cohort of buildings. However, over one-third of the buildings, specifically primary schools, performed poorly. This example implementation shows that there is no one size-fits-all modeling solution and that various types of temporal behavior are difficult to capture using machine learning. An analysis of the generalizability of the models tested motivates the need for the application of future techniques to a board range of building types and behaviors. The importance of this type of scalability analysis is discussed in the context of the growth of energy meter and other Internet-of-Things (IoT) data streams in the built environment. This framework is designed to be an example baseline implementation for other building energy data prediction methods as applied to a larger population of buildings. For reproducibility, the entire code base and data sets are found on Github.
“…Wang and Srinivasan came to a similar conclusion in their review since they found that ensemble models have better prediction accuracy than single models (multiple linear regression [MLR], ANN, and SVR). Massana et al found similar results comparing ANN and linear regression for electric load forecasting of a nonresidential building, but in their application, SVR was slightly better than ANN. Zhao et al focused on the energy consumption prediction of office buildings using variable refrigerant volume (VRV) cooling systems.…”
Section: Neural Network Applications Over a Building's Lifementioning
Summary
The incessant growing of the world's energy consumption and associated greenhouse gases emissions have created tremendous problems to be solved by today's and future generations. As the building sector is one of the biggest energy consumers, reducing its energy consumption is now mandatory. Being able to conceive and built efficient buildings, to effectively manage and operate them, and to rapidly renovate the existing building stock is a challenging task. Neural networks models open new possibilities to address this problem. This paper offers a comprehensive review of the studies that use neural networks for energy‐related applications in the building sector focusing on their application and on the technical characteristics of the network (ie, learning algorithm, number of layers, number of neurons, inputs and output variables, and performance criteria). On the basis of this review, limitations concerning the use of neural networks in the building sector along with existing research gaps and future research directions are identified.
“…As an integral part of the daily operational management of power utility, accuracy prediction of the short-term electric load in residential quarters is of great significance to urban power network planning and the electric power market operating. The overestimation will raise the operating cost while underestimation will lead to electricity shortage [3]. Because of the limited capacities on the user side, the load characteristics have less smoothing effect.…”
Short-term load forecasting plays a vital role in the daily operational management of power utility. To improve the forecasting accuracy, this paper proposes a hybrid EMD-PSO-SVR forecasting model for short-term load forecasting based on empirical mode decomposition (EMD), support vector regression (SVR), and particle swarm optimization (PSO), also considering the effects of temperature, weekends, and holidays. EMD is used to decompose the residential electric load data into a number of intrinsic mode function (IMF) components and one residue; then SVR is constructed to forecast these IMFs and residual value individually. In order to gain optimization parameters of SVR, PSO is implemented to automatically perform the parameter selection in SVR modeling. Then all of these forecasting values are reconstructed to produce the final forecasting result for residential electric load data. Compared with the results from the EMD-SVR model, traditional SVR model, and PSO-SVR model, the result indicates that the proposed EMD-PSO-SVR model performs more effectively and more stably in forecasting the residential short-term load.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.