TY - JOUR
T1 - Spatial-Temporal Deep Learning for Hosting Capacity Analysis in Distribution Grids
AU - Wu, Jiaqi
AU - Yuan, Jingyi
AU - Weng, Yang
AU - Ayyanar, Raja
N1 - Publisher Copyright:
© 2010-2012 IEEE.
PY - 2023/1/1
Y1 - 2023/1/1
N2 - 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.
AB - 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.
KW - Hosting capacity
KW - data-driven method
KW - deep learning
KW - distributed energy resource
KW - long short-term memory (LSTM)
KW - spatial-temporal correlation
UR - http://www.scopus.com/inward/record.url?scp=85136132429&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85136132429&partnerID=8YFLogxK
U2 - 10.1109/TSG.2022.3196943
DO - 10.1109/TSG.2022.3196943
M3 - Article
AN - SCOPUS:85136132429
SN - 1949-3053
VL - 14
SP - 354
EP - 364
JO - IEEE Transactions on Smart Grid
JF - IEEE Transactions on Smart Grid
IS - 1
ER -