Evaluation of Sequence-Learning Models for Large-Commercial-Building Load Forecasting

Cristina Nichiforov, Grigore Stamatescu, Iulia Stamatescu, Ioana Fagarasan

Research output: Contribution to journalConference articleResearchpeer-review

Abstract

Buildings play a critical role in the stability and resilience of modern smart grids, leading to a refocusing of large-scale energy-management strategies from the supply side to the consumer side. When buildings integrate local renewable-energy generation in the form of renewable-energy resources, they become prosumers, and this adds more complexity to the operation of interconnected complex energy systems. A class of methods of modelling the energy-consumption patterns of the building have recently emerged as black-box input–output approaches with the ability to capture underlying consumption trends. These make use and require large quantities of quality data produced by nondeterministic processes underlying energy consumption. We present an application of a class of neural networks, namely, deep-learning techniques for time-series sequence modelling, with the goal of accurate and reliable building energy-load forecasting. Recurrent Neural Network implementation uses Long Short-Term Memory layers in increasing density of nodes to quantify prediction accuracy. The case study is illustrated on four university buildings from temperate climates over one year of operation using a reference benchmarking dataset that allows replicable results. The obtained results are discussed in terms of accuracy metrics and computational and network architecture aspects, and are considered suitable for further use in future in situ energy management at the building and neighborhood levels.
Original languageEnglish
Article number189
Number of pages14
JournalInformation
Volume10
Issue number6
DOIs
Publication statusPublished - 1 Jun 2019
EventICSTCC 2018: 22nd International Conference on System Theory, Control and Computing - Sinaia, Romania
Duration: 10 Oct 201812 Oct 2018

Fingerprint

Loads (forces)
Energy management
Energy utilization
Renewable energy resources
Recurrent neural networks
Benchmarking
Dynamic loads
Network architecture
Time series
Neural networks
Long short-term memory
Deep learning

Cite this

Evaluation of Sequence-Learning Models for Large-Commercial-Building Load Forecasting. / Nichiforov, Cristina; Stamatescu, Grigore; Stamatescu, Iulia; Fagarasan, Ioana.

In: Information, Vol. 10, No. 6, 189, 01.06.2019.

Research output: Contribution to journalConference articleResearchpeer-review

Nichiforov, Cristina ; Stamatescu, Grigore ; Stamatescu, Iulia ; Fagarasan, Ioana. / Evaluation of Sequence-Learning Models for Large-Commercial-Building Load Forecasting. In: Information. 2019 ; Vol. 10, No. 6.
@article{acc27edf2d0246f895fbcb9db92d36ed,
title = "Evaluation of Sequence-Learning Models for Large-Commercial-Building Load Forecasting",
abstract = "Buildings play a critical role in the stability and resilience of modern smart grids, leading to a refocusing of large-scale energy-management strategies from the supply side to the consumer side. When buildings integrate local renewable-energy generation in the form of renewable-energy resources, they become prosumers, and this adds more complexity to the operation of interconnected complex energy systems. A class of methods of modelling the energy-consumption patterns of the building have recently emerged as black-box input–output approaches with the ability to capture underlying consumption trends. These make use and require large quantities of quality data produced by nondeterministic processes underlying energy consumption. We present an application of a class of neural networks, namely, deep-learning techniques for time-series sequence modelling, with the goal of accurate and reliable building energy-load forecasting. Recurrent Neural Network implementation uses Long Short-Term Memory layers in increasing density of nodes to quantify prediction accuracy. The case study is illustrated on four university buildings from temperate climates over one year of operation using a reference benchmarking dataset that allows replicable results. The obtained results are discussed in terms of accuracy metrics and computational and network architecture aspects, and are considered suitable for further use in future in situ energy management at the building and neighborhood levels.",
author = "Cristina Nichiforov and Grigore Stamatescu and Iulia Stamatescu and Ioana Fagarasan",
year = "2019",
month = "6",
day = "1",
doi = "10.3390/info10060189",
language = "English",
volume = "10",
journal = "Information",
issn = "2078-2489",
publisher = "MDPI AG",
number = "6",

}

TY - JOUR

T1 - Evaluation of Sequence-Learning Models for Large-Commercial-Building Load Forecasting

AU - Nichiforov, Cristina

AU - Stamatescu, Grigore

AU - Stamatescu, Iulia

AU - Fagarasan, Ioana

PY - 2019/6/1

Y1 - 2019/6/1

N2 - Buildings play a critical role in the stability and resilience of modern smart grids, leading to a refocusing of large-scale energy-management strategies from the supply side to the consumer side. When buildings integrate local renewable-energy generation in the form of renewable-energy resources, they become prosumers, and this adds more complexity to the operation of interconnected complex energy systems. A class of methods of modelling the energy-consumption patterns of the building have recently emerged as black-box input–output approaches with the ability to capture underlying consumption trends. These make use and require large quantities of quality data produced by nondeterministic processes underlying energy consumption. We present an application of a class of neural networks, namely, deep-learning techniques for time-series sequence modelling, with the goal of accurate and reliable building energy-load forecasting. Recurrent Neural Network implementation uses Long Short-Term Memory layers in increasing density of nodes to quantify prediction accuracy. The case study is illustrated on four university buildings from temperate climates over one year of operation using a reference benchmarking dataset that allows replicable results. The obtained results are discussed in terms of accuracy metrics and computational and network architecture aspects, and are considered suitable for further use in future in situ energy management at the building and neighborhood levels.

AB - Buildings play a critical role in the stability and resilience of modern smart grids, leading to a refocusing of large-scale energy-management strategies from the supply side to the consumer side. When buildings integrate local renewable-energy generation in the form of renewable-energy resources, they become prosumers, and this adds more complexity to the operation of interconnected complex energy systems. A class of methods of modelling the energy-consumption patterns of the building have recently emerged as black-box input–output approaches with the ability to capture underlying consumption trends. These make use and require large quantities of quality data produced by nondeterministic processes underlying energy consumption. We present an application of a class of neural networks, namely, deep-learning techniques for time-series sequence modelling, with the goal of accurate and reliable building energy-load forecasting. Recurrent Neural Network implementation uses Long Short-Term Memory layers in increasing density of nodes to quantify prediction accuracy. The case study is illustrated on four university buildings from temperate climates over one year of operation using a reference benchmarking dataset that allows replicable results. The obtained results are discussed in terms of accuracy metrics and computational and network architecture aspects, and are considered suitable for further use in future in situ energy management at the building and neighborhood levels.

U2 - 10.3390/info10060189

DO - 10.3390/info10060189

M3 - Conference article

VL - 10

JO - Information

JF - Information

SN - 2078-2489

IS - 6

M1 - 189

ER -