A review on time series forecasting techniques for building energy consumption

By C. Deb, Fan Zhang, Junjing Yang, S. Lee, K. W. Shah. 2017

976 citations recorded by the source corpus.

Subfields: Building and Construction, Electrical and Electronic Engineering, Renewable Energy, Sustainability and the Environment

View Paper: https://www.semanticscholar.org/paper/f2c4d54df0d1d6a13c6043a6e416b69d7f0e3eb9

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

1. Jin Wen
2. Joakim Widén
3. Pierre Pinson

In Electrical and Electronic Engineering

1. Pierre Pinson
2. Thordis Linda Thorarinsdottir
3. Fotios Petropoulos
4. Christoph Bergmeir
5. Ricardo J. Bessa
6. Florian Ziel
7. Joakim Munkhammar
8. Paul Goodwin

In Renewable Energy, Sustainability and the Environment

1. Nikolaos Kourentzes
2. Fotios Petropoulos
3. M. Babai
4. Stephan Kolassa
5. Konstantinos Nikolopoulos
6. A. Syntetos
7. Spyros Makridakis
8. Vassilios Assimakopoulos

Citations in the corpus

• Forecasting: theory and practice (2020, methodology): “ion, ARIMA, ARIMAX, and exponential smoothing) are fast to compute, require less information as input, can easily adapt to pattern changes, and be effectively adjusted for different types of buildings (Deb et al., 2017). Yet, statistical methods prescribe the behaviour of the systems, while also ignor”
• An Experimental Review on Deep Learning Architectures for Time Series Forecasting (2020, background): “500 ··· · · · · · · 30 4 64 [1, 2, 4, 8] 3 False 21.”
• Modeling and forecasting building energy consumption: A review of data-driven techniques (2019, methodology): “Ensemble models have gained in interest for BECMF in the past few years.”
• A review of the-state-of-the-art in data-driven approaches for building energy prediction (2020, neutral): “[10] 2017 √ × √ √ × √ √ × × × × √ √ × [11] 2017 √ √ √ √ √ √ √ × × Commercial √ × × × [12] 2017 × × √ √ × √ √ Hybrid × × × × × × [13] 2017 √ × √ × × √ √ √ × √ √ × √ × [14] 2017 × × × √ × √ √ Hybrid Fuzzy time series; moving average and exponential smoothing, kNearest Neighbor (kNN) × × × × ×”
• Residential probabilistic load forecasting: A method using Gaussian process designed for electric load data (2018, background): “In the recent years, hybrid models which combine two forecasting methods have been gaining popularity [7].”
• A review of machine learning in building load prediction (2021, positive): “…of machine learning applications: Li and Wen [2] mentioned that the key obstacle of machine learning application lies on the data side; the papers [20, 25] reviewed the data side of machine learning application, arguing that a reliable testing platform and high-quality, representative, and…”