Smart Meters Time Series Clustering for Demand Response Applications in the Context of High Penetration of Renewable Energy Resources
The variability in generation introduced in the electrical system by an increasing share of renewable technologies must be addressed by balancing mechanisms, demand response being a prominent one. In parallel, the massive introduction of smart meters allows for the use of high frequency energy use t...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/14/12/3458 |
| _version_ | 1797530499857514496 |
|---|---|
| author | Santiago Bañales Raquel Dormido Natividad Duro |
| author_facet | Santiago Bañales Raquel Dormido Natividad Duro |
| author_sort | Santiago Bañales |
| collection | DOAJ |
| description | The variability in generation introduced in the electrical system by an increasing share of renewable technologies must be addressed by balancing mechanisms, demand response being a prominent one. In parallel, the massive introduction of smart meters allows for the use of high frequency energy use time series data to segment electricity customers according to their demand response potential. This paper proposes a smart meter time series clustering methodology based on a two-stage k-medoids clustering of normalized load-shape time series organized around the day divided into 48 time points. Time complexity is drastically reduced by first applying the k-medoids on each customer separately, and second on the total set of customer representatives. Further time complexity reduction is achieved using time series representation with low computational needs. Customer segmentation is undertaken with only four easy-to-interpret features: average energy use, energy–temperature correlation, entropy of the load-shape representative vector, and distance to wind generation patterns. This last feature is computed using the dynamic time warping distance between load and expected wind generation shape representative medoids. The two-stage clustering proves to be computationally effective, scalable and performant according to both internal validity metrics, based on average silhouette, and external validation, based on the ground truth embedded in customer surveys. |
| first_indexed | 2024-03-10T10:30:51Z |
| format | Article |
| id | doaj.art-fd0433feb3aa4cdca7e2de695e4979b6 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T10:30:51Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-fd0433feb3aa4cdca7e2de695e4979b62023-11-21T23:43:28ZengMDPI AGEnergies1996-10732021-06-011412345810.3390/en14123458Smart Meters Time Series Clustering for Demand Response Applications in the Context of High Penetration of Renewable Energy ResourcesSantiago Bañales0Raquel Dormido1Natividad Duro2Department of Computer Sciences and Automatic Control, Universidad Nacional de Educación a Distancia (UNED), C/Juan del Rosal, 16, 28015 Madrid, SpainDepartment of Computer Sciences and Automatic Control, Universidad Nacional de Educación a Distancia (UNED), C/Juan del Rosal, 16, 28015 Madrid, SpainDepartment of Computer Sciences and Automatic Control, Universidad Nacional de Educación a Distancia (UNED), C/Juan del Rosal, 16, 28015 Madrid, SpainThe variability in generation introduced in the electrical system by an increasing share of renewable technologies must be addressed by balancing mechanisms, demand response being a prominent one. In parallel, the massive introduction of smart meters allows for the use of high frequency energy use time series data to segment electricity customers according to their demand response potential. This paper proposes a smart meter time series clustering methodology based on a two-stage k-medoids clustering of normalized load-shape time series organized around the day divided into 48 time points. Time complexity is drastically reduced by first applying the k-medoids on each customer separately, and second on the total set of customer representatives. Further time complexity reduction is achieved using time series representation with low computational needs. Customer segmentation is undertaken with only four easy-to-interpret features: average energy use, energy–temperature correlation, entropy of the load-shape representative vector, and distance to wind generation patterns. This last feature is computed using the dynamic time warping distance between load and expected wind generation shape representative medoids. The two-stage clustering proves to be computationally effective, scalable and performant according to both internal validity metrics, based on average silhouette, and external validation, based on the ground truth embedded in customer surveys.https://www.mdpi.com/1996-1073/14/12/3458time series clusteringtime series representationelectrical smart metersdemand responserenewable energyclustering validation |
| spellingShingle | Santiago Bañales Raquel Dormido Natividad Duro Smart Meters Time Series Clustering for Demand Response Applications in the Context of High Penetration of Renewable Energy Resources Energies time series clustering time series representation electrical smart meters demand response renewable energy clustering validation |
| title | Smart Meters Time Series Clustering for Demand Response Applications in the Context of High Penetration of Renewable Energy Resources |
| title_full | Smart Meters Time Series Clustering for Demand Response Applications in the Context of High Penetration of Renewable Energy Resources |
| title_fullStr | Smart Meters Time Series Clustering for Demand Response Applications in the Context of High Penetration of Renewable Energy Resources |
| title_full_unstemmed | Smart Meters Time Series Clustering for Demand Response Applications in the Context of High Penetration of Renewable Energy Resources |
| title_short | Smart Meters Time Series Clustering for Demand Response Applications in the Context of High Penetration of Renewable Energy Resources |
| title_sort | smart meters time series clustering for demand response applications in the context of high penetration of renewable energy resources |
| topic | time series clustering time series representation electrical smart meters demand response renewable energy clustering validation |
| url | https://www.mdpi.com/1996-1073/14/12/3458 |
| work_keys_str_mv | AT santiagobanales smartmeterstimeseriesclusteringfordemandresponseapplicationsinthecontextofhighpenetrationofrenewableenergyresources AT raqueldormido smartmeterstimeseriesclusteringfordemandresponseapplicationsinthecontextofhighpenetrationofrenewableenergyresources AT natividadduro smartmeterstimeseriesclusteringfordemandresponseapplicationsinthecontextofhighpenetrationofrenewableenergyresources |