Voltage sag estimation in sparsely monitored power systems based on deep learning and system area mapping
- Submitting institution
-
Sheffield Hallam University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1663
- Type
- D - Journal article
- DOI
-
10.1109/TPWRD.2018.2865906
- Title of journal
- IEEE Transactions on Power Delivery
- Article number
- 6
- First page
- 3162
- Volume
- 33
- Issue
- 6
- ISSN
- 0885-8977
- Open access status
- Compliant
- Month of publication
- August
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 17
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Originality: To our knowledge this is the first paper to apply Convolutional Neural Networks at a system-level to power system analysis using just measured data (without requiring information on current operating conditions).
Significance: Voltage sags cause significant disruption to industrial processes and using AI to predict their occurrence allows for contingency planning and mitigation. A result of collaboration with the University of Manchester, this work allows accurate voltage sag prediction under uncertain conditions.
Rigour: Analysis is presented for multiple power system fault conditions using simulation of a standard network.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -