Design of a Meaningful Framework for Time Series Forecasting in Smart Buildings
This paper aims to provide discernment toward establishing a general framework, dedicated to data analysis and forecasting in smart buildings. It constitutes an industrial return of experience from an industrialist specializing in IoT supported by the academic world. With the necessary improvement o...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/15/2/94 |
| _version_ | 1797297943679598592 |
|---|---|
| author | Louis Closson Christophe Cérin Didier Donsez Jean-Luc Baudouin |
| author_facet | Louis Closson Christophe Cérin Didier Donsez Jean-Luc Baudouin |
| author_sort | Louis Closson |
| collection | DOAJ |
| description | This paper aims to provide discernment toward establishing a general framework, dedicated to data analysis and forecasting in smart buildings. It constitutes an industrial return of experience from an industrialist specializing in IoT supported by the academic world. With the necessary improvement of energy efficiency, discernment is paramount for facility managers to optimize daily operations and prioritize renovation work in the building sector. With the scale of buildings and the complexity of Heating, Ventilation, and Air Conditioning (HVAC) systems, the use of artificial intelligence is deemed the cheapest tool, holding the highest potential, even if it requires IoT sensors and a deluge of data to establish genuine models. However, the wide variety of buildings, users, and data hinders the development of industrial solutions, as specific studies often lack relevance to analyze other buildings, possibly with different types of data monitored. The relevance of the modeling can also disappear over time, as buildings are dynamic systems evolving with their use. In this paper, we propose to study the forecasting ability of the widely used Long Short-Term Memory (LSTM) network algorithm, which is well-designed for time series modeling, across an instrumented building. In this way, we considered the consistency of the performances for several issues as we compared to the cases with no prediction, which is lacking in the literature. The insight provided let us examine the quality of AI models and the quality of data needed in forecasting tasks. Finally, we deduced that efficient models and smart choices about data allow meaningful insight into developing time series modeling frameworks for smart buildings. For reproducibility concerns, we also provide our raw data, which came from one “real” smart building, as well as significant information regarding this building. In summary, our research aims to develop a methodology for exploring, analyzing, and modeling data from the smart buildings sector. Based on our experiment on forecasting temperature sensor measurements, we found that a bigger AI model (1) does not always imply a longer time in training and (2) can have little impact on accuracy and (3) using more features is tied to data processing order. We also observed that providing more data is irrelevant without a deep understanding of the problem physics. |
| first_indexed | 2024-03-07T22:27:38Z |
| format | Article |
| id | doaj.art-6930b7f852ae4be19e9ce4f6348d4307 |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-07T22:27:38Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-6930b7f852ae4be19e9ce4f6348d43072024-02-23T15:21:06ZengMDPI AGInformation2078-24892024-02-011529410.3390/info15020094Design of a Meaningful Framework for Time Series Forecasting in Smart BuildingsLouis Closson0Christophe Cérin1Didier Donsez2Jean-Luc Baudouin3Adeunis, Grenoble Computer Science Laboratory, Université Grenoble Alpes, 621 avenue Centrale, 38400 Saint-Martin-d’Hères, FranceLIPN/CNRS UMR 7030, University Sorbonne Paris Nord (Paris 13), 99 avenue Jean-Baptiste Clément, F-93430 Villetaneuse, FranceLIG ERODS Team, Grenoble University, 38041 Grenoble, FranceAdeunis, Grenoble Computer Science Laboratory, Université Grenoble Alpes, 621 avenue Centrale, 38400 Saint-Martin-d’Hères, FranceThis paper aims to provide discernment toward establishing a general framework, dedicated to data analysis and forecasting in smart buildings. It constitutes an industrial return of experience from an industrialist specializing in IoT supported by the academic world. With the necessary improvement of energy efficiency, discernment is paramount for facility managers to optimize daily operations and prioritize renovation work in the building sector. With the scale of buildings and the complexity of Heating, Ventilation, and Air Conditioning (HVAC) systems, the use of artificial intelligence is deemed the cheapest tool, holding the highest potential, even if it requires IoT sensors and a deluge of data to establish genuine models. However, the wide variety of buildings, users, and data hinders the development of industrial solutions, as specific studies often lack relevance to analyze other buildings, possibly with different types of data monitored. The relevance of the modeling can also disappear over time, as buildings are dynamic systems evolving with their use. In this paper, we propose to study the forecasting ability of the widely used Long Short-Term Memory (LSTM) network algorithm, which is well-designed for time series modeling, across an instrumented building. In this way, we considered the consistency of the performances for several issues as we compared to the cases with no prediction, which is lacking in the literature. The insight provided let us examine the quality of AI models and the quality of data needed in forecasting tasks. Finally, we deduced that efficient models and smart choices about data allow meaningful insight into developing time series modeling frameworks for smart buildings. For reproducibility concerns, we also provide our raw data, which came from one “real” smart building, as well as significant information regarding this building. In summary, our research aims to develop a methodology for exploring, analyzing, and modeling data from the smart buildings sector. Based on our experiment on forecasting temperature sensor measurements, we found that a bigger AI model (1) does not always imply a longer time in training and (2) can have little impact on accuracy and (3) using more features is tied to data processing order. We also observed that providing more data is irrelevant without a deep understanding of the problem physics.https://www.mdpi.com/2078-2489/15/2/94smart building datasets analysesenabling technologies for the IoTBuilding Information Modeling (BIM)knowledge generalizationdata evaluation |
| spellingShingle | Louis Closson Christophe Cérin Didier Donsez Jean-Luc Baudouin Design of a Meaningful Framework for Time Series Forecasting in Smart Buildings Information smart building datasets analyses enabling technologies for the IoT Building Information Modeling (BIM) knowledge generalization data evaluation |
| title | Design of a Meaningful Framework for Time Series Forecasting in Smart Buildings |
| title_full | Design of a Meaningful Framework for Time Series Forecasting in Smart Buildings |
| title_fullStr | Design of a Meaningful Framework for Time Series Forecasting in Smart Buildings |
| title_full_unstemmed | Design of a Meaningful Framework for Time Series Forecasting in Smart Buildings |
| title_short | Design of a Meaningful Framework for Time Series Forecasting in Smart Buildings |
| title_sort | design of a meaningful framework for time series forecasting in smart buildings |
| topic | smart building datasets analyses enabling technologies for the IoT Building Information Modeling (BIM) knowledge generalization data evaluation |
| url | https://www.mdpi.com/2078-2489/15/2/94 |
| work_keys_str_mv | AT louisclosson designofameaningfulframeworkfortimeseriesforecastinginsmartbuildings AT christophecerin designofameaningfulframeworkfortimeseriesforecastinginsmartbuildings AT didierdonsez designofameaningfulframeworkfortimeseriesforecastinginsmartbuildings AT jeanlucbaudouin designofameaningfulframeworkfortimeseriesforecastinginsmartbuildings |