Custom Outlier Detection for Electrical Energy Consumption Data Applied in Case of Demand Response in Block of Buildings
The aim of this paper is to provide an extended analysis of the outlier detection, using probabilistic and AI techniques, applied in a demo pilot demand response in blocks of buildings project, based on real experiments and energy data collection with detected anomalies. A numerical algorithm was cr...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/9/2946 |
| _version_ | 1797536643566010368 |
|---|---|
| author | Dacian I. Jurj Levente Czumbil Bogdan Bârgăuan Andrei Ceclan Alexis Polycarpou Dan D. Micu |
| author_facet | Dacian I. Jurj Levente Czumbil Bogdan Bârgăuan Andrei Ceclan Alexis Polycarpou Dan D. Micu |
| author_sort | Dacian I. Jurj |
| collection | DOAJ |
| description | The aim of this paper is to provide an extended analysis of the outlier detection, using probabilistic and AI techniques, applied in a demo pilot demand response in blocks of buildings project, based on real experiments and energy data collection with detected anomalies. A numerical algorithm was created to differentiate between natural energy peaks and outliers, so as to first apply a data cleaning. Then, a calculation of the impact in the energy baseline for the demand response computation was implemented, with improved precision, as related to other referenced methods and to the original data processing. For the demo pilot project implemented in the Technical University of Cluj-Napoca block of buildings, without the energy baseline data cleaning, in some cases it was impossible to compute the established key performance indicators (peak power reduction, energy savings, cost savings, CO<sub>2</sub> emissions reduction) or the resulted values were far much higher (>50%) and not realistic. Therefore, in real case business models, it is crucial to use outlier’s removal. In the past years, both companies and academic communities pulled their efforts in generating input that consist in new abstractions, interfaces, approaches for scalability, and crowdsourcing techniques. Quantitative and qualitative methods were created with the scope of error reduction and were covered in multiple surveys and overviews to cope with outlier detection. |
| first_indexed | 2024-03-10T12:03:41Z |
| format | Article |
| id | doaj.art-4e5026248c604c22a5d03ed763d50548 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T12:03:41Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4e5026248c604c22a5d03ed763d505482023-11-21T16:43:46ZengMDPI AGSensors1424-82202021-04-01219294610.3390/s21092946Custom Outlier Detection for Electrical Energy Consumption Data Applied in Case of Demand Response in Block of BuildingsDacian I. Jurj0Levente Czumbil1Bogdan Bârgăuan2Andrei Ceclan3Alexis Polycarpou4Dan D. Micu5Electrical Engineering Department, Technical University of Cluj-Napoca, 400027 Cluj-Napoca, RomaniaElectrical Engineering Department, Technical University of Cluj-Napoca, 400027 Cluj-Napoca, RomaniaElectrical Engineering Department, Technical University of Cluj-Napoca, 400027 Cluj-Napoca, RomaniaElectrical Engineering Department, Technical University of Cluj-Napoca, 400027 Cluj-Napoca, RomaniaDepartment of Electrical and Computer Engineering and Informatics, Frederick University, 1036 Nicosia, CyprusElectrical Engineering Department, Technical University of Cluj-Napoca, 400027 Cluj-Napoca, RomaniaThe aim of this paper is to provide an extended analysis of the outlier detection, using probabilistic and AI techniques, applied in a demo pilot demand response in blocks of buildings project, based on real experiments and energy data collection with detected anomalies. A numerical algorithm was created to differentiate between natural energy peaks and outliers, so as to first apply a data cleaning. Then, a calculation of the impact in the energy baseline for the demand response computation was implemented, with improved precision, as related to other referenced methods and to the original data processing. For the demo pilot project implemented in the Technical University of Cluj-Napoca block of buildings, without the energy baseline data cleaning, in some cases it was impossible to compute the established key performance indicators (peak power reduction, energy savings, cost savings, CO<sub>2</sub> emissions reduction) or the resulted values were far much higher (>50%) and not realistic. Therefore, in real case business models, it is crucial to use outlier’s removal. In the past years, both companies and academic communities pulled their efforts in generating input that consist in new abstractions, interfaces, approaches for scalability, and crowdsourcing techniques. Quantitative and qualitative methods were created with the scope of error reduction and were covered in multiple surveys and overviews to cope with outlier detection.https://www.mdpi.com/1424-8220/21/9/2946data cleaningdemand responsebaseline electricity consumptionoutlierslocal outlier factor (LOF)interquartile range (IQR) |
| spellingShingle | Dacian I. Jurj Levente Czumbil Bogdan Bârgăuan Andrei Ceclan Alexis Polycarpou Dan D. Micu Custom Outlier Detection for Electrical Energy Consumption Data Applied in Case of Demand Response in Block of Buildings Sensors data cleaning demand response baseline electricity consumption outliers local outlier factor (LOF) interquartile range (IQR) |
| title | Custom Outlier Detection for Electrical Energy Consumption Data Applied in Case of Demand Response in Block of Buildings |
| title_full | Custom Outlier Detection for Electrical Energy Consumption Data Applied in Case of Demand Response in Block of Buildings |
| title_fullStr | Custom Outlier Detection for Electrical Energy Consumption Data Applied in Case of Demand Response in Block of Buildings |
| title_full_unstemmed | Custom Outlier Detection for Electrical Energy Consumption Data Applied in Case of Demand Response in Block of Buildings |
| title_short | Custom Outlier Detection for Electrical Energy Consumption Data Applied in Case of Demand Response in Block of Buildings |
| title_sort | custom outlier detection for electrical energy consumption data applied in case of demand response in block of buildings |
| topic | data cleaning demand response baseline electricity consumption outliers local outlier factor (LOF) interquartile range (IQR) |
| url | https://www.mdpi.com/1424-8220/21/9/2946 |
| work_keys_str_mv | AT dacianijurj customoutlierdetectionforelectricalenergyconsumptiondataappliedincaseofdemandresponseinblockofbuildings AT leventeczumbil customoutlierdetectionforelectricalenergyconsumptiondataappliedincaseofdemandresponseinblockofbuildings AT bogdanbargauan customoutlierdetectionforelectricalenergyconsumptiondataappliedincaseofdemandresponseinblockofbuildings AT andreiceclan customoutlierdetectionforelectricalenergyconsumptiondataappliedincaseofdemandresponseinblockofbuildings AT alexispolycarpou customoutlierdetectionforelectricalenergyconsumptiondataappliedincaseofdemandresponseinblockofbuildings AT dandmicu customoutlierdetectionforelectricalenergyconsumptiondataappliedincaseofdemandresponseinblockofbuildings |