Spatial-Temporal Deep Learning for Hosting Capacity Analysis in Distribution Grids
Abstract
The widespread use of distributed energy sources (DERs) raises significant challenges for power system design, planning, and operation, leading to wide adaptation of tools on hosting capacity analysis (HCA). Traditional HCA methods conduct extensive power flow analysis. Due to the computation burden, these time-consuming methods fail to provide online hosting capacity (HC) in large distribution systems. To solve the problem, we first propose a deep learning-based problem formulation for HCA, which conducts offline training and determines HC in real time. The used learning model, long short-term memory (LSTM), implements historical time-series data to capture periodical patterns in distribution systems. However, directly applying LSTMs suffers from low accuracy due to the lack of consideration on spatial information, where location information like feeder topology is critical in nodal HCA. Therefore, we modify the forget gate function to dual forget gates, to capture the spatial correlation within the grid. Such a design turns the LSTM into the Spatial-Temporal LSTM (ST-LSTM). Moreover, as voltage violations are the most vital constraints in HCA, we design a voltage sensitivity gate to increase accuracy further. The results of LSTMs and ST-LSTMs on feeders, such as IEEE 34-, 123-bus feeders, and utility feeders, validate our designs.
- Authors:
-
[1];
[1];
[1];
[1]
- School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA
- Publication Date:
- Research Org.:
- Arizona State Univ., Tempe, AZ (United States)
- Sponsoring Org.:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Solar Energy Technologies Office
- OSTI Identifier:
- 1906412
- Alternate Identifier(s):
- OSTI ID: 1906414; OSTI ID: 1963767
- Grant/Contract Number:
- EE0008773
- Resource Type:
- Published Article
- Journal Name:
- IEEE Transactions on Smart Grid
- Additional Journal Information:
- Journal Name: IEEE Transactions on Smart Grid Journal Volume: 14 Journal Issue: 1; Journal ID: ISSN 1949-3053
- Publisher:
- Institute of Electrical and Electronics Engineers
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 14 SOLAR ENERGY; 24 POWER TRANSMISSION AND DISTRIBUTION; Hosting capacity; deep learning; data-driven method; long short-term memory (LSTM); spatial-temporal correlation; distributed energy resource
Citation Formats
Wu, Jiaqi, Yuan, Jingyi, Weng, Yang, and Ayyanar, Raja. Spatial-Temporal Deep Learning for Hosting Capacity Analysis in Distribution Grids. United States: N. p., 2023.
Web. doi:10.1109/TSG.2022.3196943.
Wu, Jiaqi, Yuan, Jingyi, Weng, Yang, & Ayyanar, Raja. Spatial-Temporal Deep Learning for Hosting Capacity Analysis in Distribution Grids. United States. https://doi.org/10.1109/TSG.2022.3196943
Wu, Jiaqi, Yuan, Jingyi, Weng, Yang, and Ayyanar, Raja. Sun .
"Spatial-Temporal Deep Learning for Hosting Capacity Analysis in Distribution Grids". United States. https://doi.org/10.1109/TSG.2022.3196943.
@article{osti_1906412,
title = {Spatial-Temporal Deep Learning for Hosting Capacity Analysis in Distribution Grids},
author = {Wu, Jiaqi and Yuan, Jingyi and Weng, Yang and Ayyanar, Raja},
abstractNote = {The widespread use of distributed energy sources (DERs) raises significant challenges for power system design, planning, and operation, leading to wide adaptation of tools on hosting capacity analysis (HCA). Traditional HCA methods conduct extensive power flow analysis. Due to the computation burden, these time-consuming methods fail to provide online hosting capacity (HC) in large distribution systems. To solve the problem, we first propose a deep learning-based problem formulation for HCA, which conducts offline training and determines HC in real time. The used learning model, long short-term memory (LSTM), implements historical time-series data to capture periodical patterns in distribution systems. However, directly applying LSTMs suffers from low accuracy due to the lack of consideration on spatial information, where location information like feeder topology is critical in nodal HCA. Therefore, we modify the forget gate function to dual forget gates, to capture the spatial correlation within the grid. Such a design turns the LSTM into the Spatial-Temporal LSTM (ST-LSTM). Moreover, as voltage violations are the most vital constraints in HCA, we design a voltage sensitivity gate to increase accuracy further. The results of LSTMs and ST-LSTMs on feeders, such as IEEE 34-, 123-bus feeders, and utility feeders, validate our designs.},
doi = {10.1109/TSG.2022.3196943},
journal = {IEEE Transactions on Smart Grid},
number = 1,
volume = 14,
place = {United States},
year = {Sun Jan 01 00:00:00 EST 2023},
month = {Sun Jan 01 00:00:00 EST 2023}
}
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.1109/TSG.2022.3196943
https://doi.org/10.1109/TSG.2022.3196943
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:
An Attention-Based Spatiotemporal LSTM Network for Next POI Recommendation
journal, November 2021
- Huang, Liwei; Ma, Yutao; Wang, Shibo
- IEEE Transactions on Services Computing, Vol. 14, Issue 6
Streamlined Method for Determining Distribution System Hosting Capacity
conference, April 2015
- Rylander, Matthew; Smith, Jeff; Sunderman, Wes
- 2015 IEEE Rural Electric Power Conference (REPC)
State-of-the-art of hosting capacity in modern power systems with distributed generation
journal, January 2019
- Ismael, Sherif M.; Abdel Aleem, Shady H. E.; Abdelaziz, Almoataz Y.
- Renewable Energy, Vol. 130
Advanced distribution planning tools for high penetration PV deployment
conference, July 2012
- Smith, J. W.; Dugan, R.; Rylander, M.
- 2012 IEEE Power & Energy Society General Meeting. New Energy Horizons - Opportunities and Challenges, 2012 IEEE Power and Energy Society General Meeting
An Integrated Transmission-Distribution Co-Simulation for a Distribution System with High Renewable Penetration
conference, June 2021
- Thakar, Sushrut; Vittal, Vijay; Ayyanar, Raja
- 2021 IEEE 48th Photovoltaic Specialists Conference (PVSC)
Technologies to increase PV hosting capacity in distribution feeders
conference, July 2016
- Ding, Fei; Mather, Barry; Gotseff, Peter
- 2016 IEEE Power and Energy Society General Meeting (PESGM)
Probabilistic baseline estimation based on load patterns for better residential customer rewards
journal, September 2018
- Weng, Yang; Yu, Jiafan; Rajagopal, Ram
- International Journal of Electrical Power & Energy Systems, Vol. 100
Optimization-based distribution grid hosting capacity calculations
journal, June 2018
- Alturki, Mansoor; Khodaei, Amin; Paaso, Aleksi
- Applied Energy, Vol. 219
Hosting Capacity of the Power Grid for Renewable Electricity Production and New Large Consumption Equipment
journal, September 2017
- Bollen, Math; Rönnberg, Sarah
- Energies, Vol. 10, Issue 9
On Distributed PV Hosting Capacity Estimation, Sensitivity Study, and Improvement
journal, July 2017
- Ding, Fei; Mather, Barry
- IEEE Transactions on Sustainable Energy, Vol. 8, Issue 3
A Review of the Tools and Methods for Distribution Networks’ Hosting Capacity Calculation
journal, June 2020
- Zain ul Abideen, Mohammad; Ellabban, Omar; Al-Fagih, Luluwah
- Energies, Vol. 13, Issue 11
LSTM: A Search Space Odyssey
journal, October 2017
- Greff, Klaus; Srivastava, Rupesh K.; Koutnik, Jan
- IEEE Transactions on Neural Networks and Learning Systems, Vol. 28, Issue 10
Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network
journal, March 2020
- Sherstinsky, Alex
- Physica D: Nonlinear Phenomena, Vol. 404
Distributed Energy Resources Topology Identification via Graphical Modeling
journal, July 2017
- Weng, Yang; Liao, Yizheng; Rajagopal, Ram
- IEEE Transactions on Power Systems, Vol. 32, Issue 4
HST-LSTM: A Hierarchical Spatial-Temporal Long-Short Term Memory Network for Location Prediction
conference, July 2018
- Kong, Dejiang; Wu, Fei
- Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Potential Harmonic Resonance Impacts of PV Inverter Filters on Distribution Systems
journal, January 2015
- Hu, Haitao; Shi, Qingxin; He, Zhengyou
- IEEE Transactions on Sustainable Energy, Vol. 6, Issue 1
Learning EV Placement Factors with Social Welfare and Economic Variation Modeling
conference, October 2019
- Yuan, Jingyi; Cui, Qiushi; Ma, Zhihao
- 2019 North American Power Symposium (NAPS)
Learning to Forget: Continual Prediction with LSTM
journal, October 2000
- Gers, Felix A.; Schmidhuber, Jürgen; Cummins, Fred
- Neural Computation, Vol. 12, Issue 10
Assessment of the hosting capacity in distribution networks with different DG location
conference, June 2017
- Quintero-Molina, V.; Romero-L, Miguel; Pavas, Andres
- 2017 IEEE Manchester PowerTech
Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates
journal, December 2018
- Liu, Jun; Shahroudy, Amir; Xu, Dong
- IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 40, Issue 12
Quasi-Static Time-Series PV Hosting Capacity Methodology and Metrics
conference, February 2019
- Jain, Akshay Kumar; Horowitz, Kelsey; Ding, Fei
- 2019 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT)
Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks
conference, January 2015
- Tai, Kai Sheng; Socher, Richard; Manning, Christopher D.
- Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Distributed algorithms for convexified bad data and topology error detection and identification problems
journal, December 2016
- Weng, Yang; Ilić, Marija D.; Li, Qiao
- International Journal of Electrical Power & Energy Systems, Vol. 83
A High Performance Communication Architecture for a Smart Micro-Grid Testbed Using Customized Edge Intelligent Devices (EIDs) With SPI and Modbus TCP/IP Communication Protocols
journal, January 2021
- Si, Yunpeng; Korada, Nikhil; Ayyanar, Raja
- IEEE Open Journal of Power Electronics, Vol. 2
An Iterative Approach to Improve PV Hosting Capacity for a Remote Community
conference, August 2018
- Joshi, Kalpesh; Gokaraju, Ramakrishna Rama
- 2018 IEEE Power & Energy Society General Meeting (PESGM)
Motivation and requirements for quasi-static time series (QSTS) for distribution system analysis
conference, July 2017
- Reno, Matthew J.; Deboever, Jeremiah; Mather, Barry
- 2017 IEEE Power & Energy Society General Meeting (PESGM)
Long Short-Term Memory
journal, November 1997
- Hochreiter, Sepp; Schmidhuber, Jürgen
- Neural Computation, Vol. 9, Issue 8
A review of hosting capacity quantification methods for photovoltaics in low-voltage distribution grids
journal, February 2020
- Mulenga, Enock; Bollen, Math H. J.; Etherden, Nicholas
- International Journal of Electrical Power & Energy Systems, Vol. 115
Analytic time series load flow
journal, February 2018
- Samet, Haidar; Khorshidsavar, Morteza
- Renewable and Sustainable Energy Reviews, Vol. 82
Electric Vehicle Charging Station Placement Method for Urban Areas
journal, November 2019
- Cui, Qiushi; Weng, Yang; Tan, Chin-Woo
- IEEE Transactions on Smart Grid, Vol. 10, Issue 6
Probabilistic load flow computation using first-order second-moment method
conference, July 2012
- Can Wan,
- 2012 IEEE Power and Energy Society General Meeting
Photovoltaic Generation Penetration Limits in Radial Distribution Systems
journal, August 2011
- Shayani, Rafael Amaral; de Oliveira, Marco Aurélio Gonçalves
- IEEE Transactions on Power Systems, Vol. 26, Issue 3
Analytical approach for placement and sizing of distributed generation on distribution systems
journal, June 2014
- Elsaiah, Salem; Benidris, Mohammed; Mitra, Joydeep
- IET Generation, Transmission & Distribution, Vol. 8, Issue 6
Time series simulation of voltage regulation device control modes
conference, June 2013
- Quiroz, Jimmy E.; Reno, Matthew J.; Broderick, Robert J.
- 2013 IEEE 39th Photovoltaic Specialists Conference (PVSC)
A Hybrid Machine Learning Framework for Enhancing PMU-based Event Identification with Limited Labels
conference, May 2019
- Li, Haoran; Weng, Yang; Farantatos, Evangelos
- 2019 International Conference on Smart Grid Synchronized Measurements and Analytics (SGSMA)
Evaluation of statistical and machine learning models for time series prediction: Identifying the state-of-the-art and the best conditions for the use of each model
journal, May 2019
- Parmezan, Antonio Rafael Sabino; Souza, Vinicius M. A.; Batista, Gustavo E. A. P. A.
- Information Sciences, Vol. 484
Determining maximum hosting capacity for PV systems in distribution grids
journal, February 2022
- Yuan, Jingyi; Weng, Yang; Tan, Chin-Woo
- International Journal of Electrical Power & Energy Systems, Vol. 135
Graph convolutional networks: a comprehensive review
journal, November 2019
- Zhang, Si; Tong, Hanghang; Xu, Jiejun
- Computational Social Networks, Vol. 6, Issue 1