skip to main content


This content will become publicly available on October 15, 2024

Title: Transmission Line Outage Detection with Limited Information Using Machine Learning
Transmission line outage detection plays an important role in maintaining the reliability of electric power systems. Most existing methods rely on optimization models to estimate the outage of transmission lines, and the process is computationally burdensome. In this study, we propose a transmission line outage detection method using machine learning. Using this method, we could monitor the power flow of one line and estimate whether another line is in service or not, despite the load fluctuations in the system. The study also investigates the principles for observation point selection and the effectiveness of this method in detecting the outage of transmission lines with different levels of power flows. The method was implemented on an IEEE 118-bus system, and results show that the method is effective for transmission lines with all levels of power flows, and line outage distribution factors (LODF) are good indicators in observation point selection.  more » « less
Award ID(s):
2131201
NSF-PAR ID:
10483094
Author(s) / Creator(s):
; ;
Publisher / Repository:
IEEE
Date Published:
Journal Name:
2023 North American Power Symposium (NAPS)
ISBN:
979-8-3503-1509-7
Page Range / eLocation ID:
1 to 5
Format(s):
Medium: X
Location:
Asheville, NC, USA
Sponsoring Org:
National Science Foundation
More Like this
  1. The growing integration of distributed energy resources (DERs) in distribution grids raises various reliability issues due to DER's uncertain and complex behaviors. With large-scale DER penetration in distribution grids, traditional outage detection methods, which rely on customers report and smart meters' “last gasp” signals, will have poor performance, because renewable generators and storage and the mesh structure in urban distribution grids can continue supplying power after line outages. To address these challenges, we propose a data-driven outage monitoring approach based on the stochastic time series analysis with a theoretical guarantee. Specifically, we prove via power flow analysis that dependency of time-series voltage measurements exhibits significant statistical changes after line outages. This makes the theory on optimal change-point detection suitable to identify line outages. However, existing change point detection methods require post-outage voltage distribution, which are unknown in distribution systems. Therefore, we design a maximum likelihood estimator to directly learn distribution pa-rameters from voltage data. We prove the estimated parameters-based detection also achieves optimal performance, making it extremely useful for fast distribution grid outage identifications. Furthermore, since smart meters have been widely installed in distribution grids and advanced infrastructure (e.g., PMU) has not widely been available, our approach only requires voltage magnitude for quick outage identification. Simulation results show highly accurate outage identification in eight distribution grids with 17 configurations with and without DERs using smart meter data. 
    more » « less
  2. Multiple line outages that occur together show a variety of spatial patterns in the power transmission network. Some of these spatial patterns form network contingency motifs, which we define as the patterns of multiple outages that occur much more frequently than multiple outages chosen randomly from the network. We show that choosing N-k contingencies from these commonly occurring contingency motifs accounts for most of the probability of multiple initiating line outages. This result is demonstrated using historical outage data for two transmission systems. It enables N-k contingency lists that are much more efficient in accounting for the likely multiple initiating outages than exhaustive listing or random selection. The N-k contingency lists constructed from motifs can improve risk estimation in cascading outage simulations and help to confirm utility contingency selection. 
    more » « less
  3. Transmission expansion planning (TEP) plays a vital role in ensuring the reliable and efficient operation of power systems, especially with the growing demand for electricity and the integration of renewable energy sources. This paper focuses on applying unconventional high surge impedance loading (HSIL) lines in transmission expansion planning and compares their outcomes with conventional line-based transmission expansion planning. Starting with a 17 bus- 500 kV power system connected by a conventional transmission line, the objective is to connect a new load located in a new bus, bus #18, to the existing 17-bus power system via two approaches: using conventional lines and incorporating unconventional HSIL lines. By comparing the number of lines required for the conventional and unconventional approaches, maintaining almost identical conductor volume per circuit, the effectiveness of unconventional HSIL lines in TEP is evaluated where using only two unconventional HSIL lines is sufficient to connect 1000 MW load demand at bus 18 while three lines are required when using the conventional design. 
    more » « less
  4. Risk assessment of power transmission systems against strong winds requires models that can accurately represent the realistic performance of the physical infrastructure. Capturing material nonlinearity, p-delta effects in towers, buckling of lattice elements, joint slippage, and joint failure requires nonlinear models. For this purpose, this study investigates the reliability of transmission line systems by utilizing a nonlinear model of steel lattice towers, generated in OpenSEES platform. This model is capable of considering various geometric and material nonlinearities mentioned earlier. In order to efficiently estimate the probability of failure of transmission lines, the current study adopts an advanced reliability method through Error rate-based Adaptive Kriging (REAK) proposed by the authors. This method is capable of significantly reducing the number of simulations compared to conventional Monte Carlo methods such that reliability analysis can be done within a reasonable time. Results indicate that REAK efficiently estimates the reliability of transmission lines with a maximum of 150 Finite Element simulations for various wind intensities. 
    more » « less
  5. Earthquakes cause outages of power transmission system components due to direct physical damage and also through the initiation of cascading processes. This article explores what are the optimal capacity investments to increase the resilience of electric power transmission systems to earthquakes and how those investments change with respect to two issues: (1) the impact of including cascades in the investment optimization model and (2) the impact of focusing more heavily on the early stages of the outages after the earthquake in contrast to more evenly focusing on outages across the entire restoration process. A cascading outage model driven by the statistics of sample utility data is developed and used to locate the cascading lines. We compare the investment plans with and without the modeling of the cascades and with different levels of importance attached to outages that occur during different periods of the restoration process. Using a case study of the Eastern Interconnect transmission grid, where the seismic hazard stems mostly from the New Madrid Seismic Zone, we find that the cascades have little effect on the optimal set of capacity enhancement investments. However, the cascades do have a significant impact on the early stages of the restoration process. Also, the cascading lines can be far away from the initial physically damaged lines. More broadly, the early stages of the earthquake restoration process is affected by the extent of the cascading outages and is critical for search and rescue as well as restoring vital services. Also, we show that an investment plan focusing more heavily on outages in the first 3 days after the earthquake yields fewer outages in the first month, but more outages later in comparison with an investment plan focusing uniformly on outages over an entire 6-month restoration process.

     
    more » « less