Multi-Area Distribution System State Estimation Using Decentralized Physics-Aware Neural Networks
Abstract
The development of active distribution grids requires more accurate and lower computational cost state estimation. In this paper, the authors investigate a decentralized learning-based distribution system state estimation (DSSE) approach for large distribution grids. The proposed approach decomposes the feeder-level DSSE into subarea-level estimation problems that can be solved independently. The proposed method is decentralized pruned physics-aware neural network (D-P2N2). The physical grid topology is used to parsimoniously design the connections between different hidden layers of the D-P2N2. Monte Carlo simulations based on one-year of load consumption data collected from smart meters for a three-phase distribution system power flow are developed to generate the measurement and voltage state data. The IEEE 123-node system is selected as the test network to benchmark the proposed algorithm against the classic weighted least squares and state-of-the-art learning-based DSSE approaches. Numerical results show that the D-P2N2 outperforms the state-of-the-art methods in terms of estimation accuracy and computational efficiency.
- Authors:
-
[1];
[2];
[1];
- Eindhoven Univ. of Technology (Netherlands)
- National Renewable Energy Lab. (NREL), Golden, CO (United States)
- Publication Date:
- Research Org.:
- National Renewable Energy Lab. (NREL), Golden, CO (United States)
- Sponsoring Org.:
- USDOE Laboratory Directed Research and Development (LDRD) Program
- OSTI Identifier:
- 1788430
- Report Number(s):
- NREL/JA-5D00-80067
Journal ID: ISSN 1996-1073; MainId:42270;UUID:1c59d26d-7c07-4b3e-bbe6-1a0ceef92135;MainAdminID:24591
- Grant/Contract Number:
- AC36-08GO28308
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Energies (Basel)
- Additional Journal Information:
- Journal Name: Energies (Basel); Journal Volume: 14; Journal Issue: 11; Journal ID: ISSN 1996-1073
- Publisher:
- MDPI AG
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; 24 POWER TRANSMISSION AND DISTRIBUTION; neural networks; distribution system monitoring; state estimation; physics informed machine learning
Citation Formats
Tran, Minh-Quan, Zamzam, Ahmed S., Nguyen, Phuong H., and Pemen, Guus. Multi-Area Distribution System State Estimation Using Decentralized Physics-Aware Neural Networks. United States: N. p., 2021.
Web. doi:10.3390/en14113025.
Tran, Minh-Quan, Zamzam, Ahmed S., Nguyen, Phuong H., & Pemen, Guus. Multi-Area Distribution System State Estimation Using Decentralized Physics-Aware Neural Networks. United States. https://doi.org/10.3390/en14113025
Tran, Minh-Quan, Zamzam, Ahmed S., Nguyen, Phuong H., and Pemen, Guus. Mon .
"Multi-Area Distribution System State Estimation Using Decentralized Physics-Aware Neural Networks". United States. https://doi.org/10.3390/en14113025. https://www.osti.gov/servlets/purl/1788430.
@article{osti_1788430,
title = {Multi-Area Distribution System State Estimation Using Decentralized Physics-Aware Neural Networks},
author = {Tran, Minh-Quan and Zamzam, Ahmed S. and Nguyen, Phuong H. and Pemen, Guus},
abstractNote = {The development of active distribution grids requires more accurate and lower computational cost state estimation. In this paper, the authors investigate a decentralized learning-based distribution system state estimation (DSSE) approach for large distribution grids. The proposed approach decomposes the feeder-level DSSE into subarea-level estimation problems that can be solved independently. The proposed method is decentralized pruned physics-aware neural network (D-P2N2). The physical grid topology is used to parsimoniously design the connections between different hidden layers of the D-P2N2. Monte Carlo simulations based on one-year of load consumption data collected from smart meters for a three-phase distribution system power flow are developed to generate the measurement and voltage state data. The IEEE 123-node system is selected as the test network to benchmark the proposed algorithm against the classic weighted least squares and state-of-the-art learning-based DSSE approaches. Numerical results show that the D-P2N2 outperforms the state-of-the-art methods in terms of estimation accuracy and computational efficiency.},
doi = {10.3390/en14113025},
journal = {Energies (Basel)},
number = 11,
volume = 14,
place = {United States},
year = {Mon May 24 00:00:00 EDT 2021},
month = {Mon May 24 00:00:00 EDT 2021}
}
Free Publicly Available Full Text
Publisher's Version of Record
Other availability
Search WorldCat to find libraries that may hold this journal
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
A Game-Theoretic Data-Driven Approach for Pseudo-Measurement Generation in Distribution System State Estimation
journal, November 2019
- Dehghanpour, Kaveh; Yuan, Yuxuan; Wang, Zhaoyu
- IEEE Transactions on Smart Grid, Vol. 10, Issue 6
A Real-Time EV Charging Scheduling for Parking Lots With PV System and Energy Store System
journal, January 2019
- Jiang, Wei; Zhen, Yongqi
- IEEE Access, Vol. 7
Real-Time Power System State Estimation and Forecasting via Deep Unrolled Neural Networks
journal, August 2019
- Zhang, Liang; Wang, Gang; Giannakis, Georgios B.
- IEEE Transactions on Signal Processing, Vol. 67, Issue 15
Decentralized Robust State Estimation of Active Distribution Grids Incorporating Microgrids Based on PMU Measurements
journal, January 2020
- Lin, Chenhui; Wu, Wenchuan; Guo, Ye
- IEEE Transactions on Smart Grid, Vol. 11, Issue 1
A Review on Distribution System State Estimation
journal, September 2017
- Primadianto, Anggoro; Lu, Chan-Nan
- IEEE Transactions on Power Systems, Vol. 32, Issue 5
A direct numerical method for observability analysis
journal, May 2000
- Gou, B.; Abur, A.
- IEEE Transactions on Power Systems, Vol. 15, Issue 2
Experimental evaluation of a real time energy management system for stand-alone microgrids in day-ahead markets
journal, June 2013
- Marzband, Mousa; Sumper, Andreas; Ruiz-Álvarez, Albert
- Applied Energy, Vol. 106
A Multi-Timescale Data-Driven Approach to Enhance Distribution System Observability
journal, July 2019
- Yuan, Yuxuan; Dehghanpour, Kaveh; Bu, Fankun
- IEEE Transactions on Power Systems, Vol. 34, Issue 4
Analytic Considerations and Design Basis for the IEEE Distribution Test Feeders
journal, May 2018
- Schneider, K. P.; Mather, B. A.; Pal, B. C.
- IEEE Transactions on Power Systems, Vol. 33, Issue 3
Impact of Different Uncertainty Sources on a Three-Phase State Estimator for Distribution Networks
journal, September 2014
- Muscas, Carlo; Sulis, Sara; Angioni, Andrea
- IEEE Transactions on Instrumentation and Measurement, Vol. 63, Issue 9
An Improved Measurement Placement Algorithm for Network Observability
journal, October 2001
- Gou, B.; Abur, A.
- IEEE Power Engineering Review, Vol. 21, Issue 10
A Fuzzy Energy Management Strategy for the Coordination of Electric Vehicle Charging in Low Voltage Distribution Grids
journal, July 2020
- Boglou, Vasileios; Karavas, Christos-Spyridon; Arvanitis, Konstantinos
- Energies, Vol. 13, Issue 14
A New Pseudo Load Profile Determination Approach in Low Voltage Distribution Networks
journal, January 2018
- Gahrooei, Yaser Raeisi; Khodabakhshian, Amin; Hooshmand, Rahmat-Allah
- IEEE Transactions on Power Systems, Vol. 33, Issue 1
Physics-Aware Neural Networks for Distribution System State Estimation
journal, November 2020
- Zamzam, Ahmed Samir; Sidiropoulos, Nicholas D.
- IEEE Transactions on Power Systems, Vol. 35, Issue 6
A Survey on State Estimation Techniques and Challenges in Smart Distribution Systems
journal, March 2019
- Dehghanpour, Kaveh; Wang, Zhaoyu; Wang, Jianhui
- IEEE Transactions on Smart Grid, Vol. 10, Issue 2