Journal ArticleDOI
A review on time series forecasting techniques for building energy consumption
TLDR
The various combinations of the hybrid model are found to be the most effective in time series energy forecasting for building and the nine most popular forecasting techniques based on the machine learning platform are analyzed.Abstract:
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.read more
Citations
More filters
Journal ArticleDOI
Predicting residential energy consumption using CNN-LSTM neural networks
Tae Young Kim,Sung-Bae Cho +1 more
TL;DR: This paper proposes a CNN-LSTM neural network that can extract spatial and temporal features to effectively predict the housing energy consumption and achieves almost perfect prediction performance for electric energy consumption that was previously difficult to predict.
Journal ArticleDOI
Review of Smart Meter Data Analytics: Applications, Methodologies, and Challenges
TL;DR: An application-oriented review of smart meter data analytics identifies the key application areas as load analysis, load forecasting, and load management and reviews the techniques and methodologies adopted or developed to address each application.
Journal ArticleDOI
Review of Smart Meter Data Analytics: Applications, Methodologies, and Challenges
TL;DR: In this paper, the authors conduct an application-oriented review of smart meter data analytics following the three stages of analytics, namely, descriptive, predictive and prescriptive analytics, identifying the key application areas as load analysis, load forecasting, and load management.
Journal ArticleDOI
Modeling and forecasting building energy consumption: A review of data-driven techniques
TL;DR: A review of studies developing data-driven models for building scale applications with a focus on the input data characteristics and data pre-processing methods, the building typologies considered, the targeted energy end-uses and forecasting horizons, and accuracy assessment.
Journal ArticleDOI
Urban heat island impacts on building energy consumption: A review of approaches and findings
TL;DR: In this paper, the authors reviewed existing literature for improving the understanding of UHI impacts on building energy consumption and found that UHI could result in a median increase of 19.0% in cooling energy consumption, and a median decrease of 18.7% in heating energy consumption.
References
More filters
Journal ArticleDOI
Demand For Electricity In Lebanon
TL;DR: In this article, the demand for electricity in Lebanon was estimated by employing three modeling techniques namely OLS, ARIMA and exponential smoothing for the time span January 1995 to December 2005.
Evaluation of a case-based Reasoning Energy Prediction Tool for Commercial Buildings
TL;DR: In this paper, a case-based reasoning (CBR) approach was used to predict the energy consumption of commercial buildings in Varennes, Québec, and the results showed that during occupancy, 7:00 to 17:00, the coefficient of variance of the root-mean-square-error (CVRMSE) is below 12.3%, the normalized mean bias error (NMBE) was below 1.7%, and the RMSE is 17.6 kW.
Short-term load forecasting by artificial neural ne tworks specified by genetic algorithms - a simulation stud y over a Brazilian dataset.
TL;DR: This paper studies the application of genetic algorithms in helping to select the proper architecture and training paramet ers, by means of evolutionary simulations done on a series of real load data, for a neural network to be used in electric load forecasting.
Proceedings ArticleDOI
Maximum Length Weighted Nearest Neighbor approach for electricity load forecasting
TL;DR: A new approach for time series forecasting, called Maximum Length Weighted Nearest Neighbor (MLWNN), which combines prediction based on sequence similarity with optimization techniques, which shows that MLWNN is a promising approach for one day ahead electricity load forecasting.
Journal ArticleDOI
Improved Electric Power Demand Forecasting by adapting the Weighted Average to the MISMO Strategy
TL;DR: The objective here is to obtain a forecast which is as precise as possible, while conserving the stochastic nature between the historical and the forecasted data.
Related Papers (5)
A review of data-driven building energy consumption prediction studies
Kadir Amasyali,Nora El-Gohary +1 more