Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques

By C. Fan, F. Xiao, Shengwei Wang. 2014

530 citations recorded by the source corpus.

Subfields: Building and Construction, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/4be7cedbfe7b81fd4724b407b4381db0dc6bfece

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Building and Construction

In Electrical and Electronic Engineering

Citations in the corpus

Modeling and forecasting building energy consumption: A review of data-driven techniques (2019, background): “Dew point temperature (DPT) Regression: (Fan et al., 2014)”
Identifying key variables and interactions in statistical models of building energy consumption using regularization (2015, methodology): “Other methods have been used to select or filter variables in particular situations, including principal components analysis of energy use [39], and neural networks and data mining methods to detect outliers [40] and faults [41].”
Temporal Convolutional Networks Applied to Energy-Related Time Series Forecasting (2020, background): “3 2 [1, 3, 6, 12, 24, 48] 3 [1, 2, 4, 8, 16, 32] 4 [1, 3, 6, 12, 24]”
Machine learning approaches for estimating commercial building energy consumption (2017, background): “Similarly, Fan, Xiao, and Wang use an ensemble of machine learning models to predict the next-day building energy consumption of the “International Commerce Center” in Hong Kong with good results [26].”
Day-ahead building-level load forecasts using deep learning vs. traditional time-series techniques (2019, methodology): “Most existing load forecasting models use non-DL techniques, ranging from the simplest multiple linear regression (MLR) [17,18], autoregressive integrated moving average (ARIMA) [19,20], support vector regression (SVR) [21,22] to the most sophisticated arti ﬁ cial neural network (ANN) [23,24].”
A review of the-state-of-the-art in data-driven approaches for building energy prediction (2020, methodology): “The main advantage of RT is easy to understand and interpret due to the fact that it could be displayed graphically [40], [72].”