Generation of synthetic multi‐resolution time series load data
Abstract The availability of large datasets is crucial for the development of new power system applications and tools; unfortunately, very few are publicly and freely available. The authors designed an end‐to‐end generative framework for the creation of synthetic bus‐level time‐series load data for...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-10-01
|
| Series: | IET Smart Grid |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/stg2.12116 |
| _version_ | 1797660088981258240 |
|---|---|
| author | Andrea Pinceti Lalitha Sankar Oliver Kosut |
| author_facet | Andrea Pinceti Lalitha Sankar Oliver Kosut |
| author_sort | Andrea Pinceti |
| collection | DOAJ |
| description | Abstract The availability of large datasets is crucial for the development of new power system applications and tools; unfortunately, very few are publicly and freely available. The authors designed an end‐to‐end generative framework for the creation of synthetic bus‐level time‐series load data for transmission networks. The model is trained on a real dataset of over 70 Terabytes of synchrophasor measurements spanning multiple years. Leveraging a combination of principal component analysis and conditional generative adversarial network models, the developed scheme allows for the generation of data at varying sampling rates (up to a maximum of 30 samples per second) and ranging in length from seconds to years. The generative models are tested extensively to verify that they correctly capture the diverse characteristics of real loads. Finally, an opensource tool called LoadGAN is developed which gives researchers access to the fully trained generative models via a graphical interface. |
| first_indexed | 2024-03-11T18:25:39Z |
| format | Article |
| id | doaj.art-1557d5a1829c42009b52b5a9d3d7d432 |
| institution | Directory Open Access Journal |
| issn | 2515-2947 |
| language | English |
| last_indexed | 2024-03-11T18:25:39Z |
| publishDate | 2023-10-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Smart Grid |
| spelling | doaj.art-1557d5a1829c42009b52b5a9d3d7d4322023-10-14T03:51:30ZengWileyIET Smart Grid2515-29472023-10-016549250210.1049/stg2.12116Generation of synthetic multi‐resolution time series load dataAndrea Pinceti0Lalitha Sankar1Oliver Kosut2School of Electrical, Computer and Energy Engineering Arizona State University Tempe Arizona USASchool of Electrical, Computer and Energy Engineering Arizona State University Tempe Arizona USASchool of Electrical, Computer and Energy Engineering Arizona State University Tempe Arizona USAAbstract The availability of large datasets is crucial for the development of new power system applications and tools; unfortunately, very few are publicly and freely available. The authors designed an end‐to‐end generative framework for the creation of synthetic bus‐level time‐series load data for transmission networks. The model is trained on a real dataset of over 70 Terabytes of synchrophasor measurements spanning multiple years. Leveraging a combination of principal component analysis and conditional generative adversarial network models, the developed scheme allows for the generation of data at varying sampling rates (up to a maximum of 30 samples per second) and ranging in length from seconds to years. The generative models are tested extensively to verify that they correctly capture the diverse characteristics of real loads. Finally, an opensource tool called LoadGAN is developed which gives researchers access to the fully trained generative models via a graphical interface.https://doi.org/10.1049/stg2.12116artificial intelligence and data analyticsbig datadata analysislearning (artificial intelligence)load flowmultilayer perceptrons |
| spellingShingle | Andrea Pinceti Lalitha Sankar Oliver Kosut Generation of synthetic multi‐resolution time series load data IET Smart Grid artificial intelligence and data analytics big data data analysis learning (artificial intelligence) load flow multilayer perceptrons |
| title | Generation of synthetic multi‐resolution time series load data |
| title_full | Generation of synthetic multi‐resolution time series load data |
| title_fullStr | Generation of synthetic multi‐resolution time series load data |
| title_full_unstemmed | Generation of synthetic multi‐resolution time series load data |
| title_short | Generation of synthetic multi‐resolution time series load data |
| title_sort | generation of synthetic multi resolution time series load data |
| topic | artificial intelligence and data analytics big data data analysis learning (artificial intelligence) load flow multilayer perceptrons |
| url | https://doi.org/10.1049/stg2.12116 |
| work_keys_str_mv | AT andreapinceti generationofsyntheticmultiresolutiontimeseriesloaddata AT lalithasankar generationofsyntheticmultiresolutiontimeseriesloaddata AT oliverkosut generationofsyntheticmultiresolutiontimeseriesloaddata |