More Like this

1. Spatiotemporal Multiplex Network Model for Predicting Forced Outage Severity in Distribution Grids

   Aljurbua, R; Baembitov, R; Petridis, C; Saranovic, D; Kezunovic, M; Obradovic, Z (June 2025, Springer Verlag)

   Iliadis, L; Maglogiannis, I; Kyriacou, E; Jayne, C (Ed.)

   Weather-related power disruptions present significant challenges to public infrastructure, societal well-being, and the distribution grid. Predicting outage durations in distribution grids is another challenge compared to transmission line outage durations due to distribution networks’ complexity and finer granularity. While forecasting forced power outages is crucial, accurately estimating their duration is essential for timely response and mitigation measures. This study introduces the Spatiotemporal Multiplex Network (SMN-WVF), a methodology designed to predict power outage durations across varying lead times, tackling the difficulties posed by small, high-complexity spaces within distribution grids. SMN-WVF employs multiplex networks that incorporate multi-modal data across both time and space, including layers such as power outages, weather conditions, weather forecasts, vegetation, and distances between substations. We demonstrate the importance of incorporating additional layers of data sources as they are shown to help the model’s predictions through gradual improvement in the macro F1 score performance. 

   more » « less
2. A Remedial Action Scheme Against False Data Injection Cyberattacks Targeting ULTC Transformers in Smart Distribution Systems

   https://doi.org/10.1109/ICPSAsia61913.2024.10761531  

   Naderi, Ehsan; Asrari, Arash; Fajri, Poria (July 2024, IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia))

   This paper proposes an on-line remedial action scheme (OLRAS) in order to mitigate the voltage violations caused by false data injection attacks (FDIAs) targeting under load tap changing (ULTC) transformers in smart distribution systems. The FDIA framework contains two different phases. In the attack phase, distribution system operator (DSO), being in attacker's shoe, considers cyberattack scenarios through compromising the results of volt-var optimization problem in a radial distribution grid modified with distributed energy resources (DERs) such as photovoltaic (PV) units and wind turbines (WTs). The outcome of the attack phase will be the compromised voltage profile of the distribution grid showing different rates of voltage violations. In the reaction phase, the DSO rapidly identifies a customized distribution feeder reconfiguration (CDFR) in order to update the flows of active and reactive power throughout the targeted distribution system and recover the voltage profile. The objective functions of the proposed CDFR are defined to minimize the impacts of such cyberattacks targeting ULTCs within distribution grids. This will empower DSOs to react to severe cyberattacks, bypassing the detection stage, and address the voltage violations in a timely manner. The effectiveness of the proposed OLRAS is validated on an IEEE test system. 

   more » « less
3. Real-time Assessment of Distribution Grid Security through Adaptive Smart Meter Measurements

   https://doi.org/10.1109/CDC56724.2024.10885867  

   Chen, Jiaqi; Roald, Line A (December 2024, IEEE)

   The rapid expansion of distributed energy resources is heightening uncertainty and variability in distribution system operations, potentially leading to power quality challenges such as voltage magnitude violations and excessive voltage unbalance. Ensuring the dependable and secure operation of distribution grids requires system real-time assessment. However, constraints in sensing, measurement, and communication capabilities within distribution grids result in limited awareness of the system’s state. To achieve better real-time estimates of distribution system security, we propose a real-time security assessment based on data from smart meters, which are already prevalent in most distribution grids. Assuming that it is possible to obtain a limited number of voltage magnitude measurements in real time, we design an iterative algorithm to adaptively identify a subset of smart meters whose real-time measurements allow us to certify that all voltage magnitudes remain within bounds. This algorithm iterates between (i) solving optimization problems to determine the worst possible voltage magnitudes, given a limited set of voltage magnitude measurements, and (ii) leveraging the solutions and sensitivity information from these problems to update the measurement set. Numerical tests on the IEEE 123 bus distribution feeder demonstrate that the proposed algorithm consistently identifies and tracks the nodes with the highest and lowest voltage magnitude, even as the load changes over time. 

   more » « less
4. Transmission Line Outage Detection with Limited Information Using Machine Learning

   https://doi.org/10.1109/NAPS58826.2023.10318637  

   Flores, Daniel; Sang, Yuanrui; McGarry, Michael P. (October 2023, 2023 North American Power Symposium (NAPS))

   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
5. Bayesian Optimization and Hierarchical Forecasting of Non-Weather-Related Electric Power Outages

   https://doi.org/10.3390/en15061958  

   Owolabi, Olukunle O.; Sunter, Deborah A. (March 2022, Energies)

   Power outage prediction is important for planning electric power system response, restoration, and maintenance efforts. It is important for utility managers to understand the impact of outages on the local distribution infrastructure in order to develop appropriate maintenance and resilience measures. Power outage prediction models in literature are often limited in scope, typically tailored to model extreme weather related outage events. While these models are sufficient in predicting widespread outages from adverse weather events, they may fail to capture more frequent, non-weather related outages (NWO). In this study, we explore time series models of NWO by incorporating state-of-the-art techniques that leverage the Prophet model in Bayesian optimization and hierarchical forecasting. After defining a robust metric for NWO (non-weather outage count index, NWOCI), time series forecasting models that leverage advanced preprocessing and forecasting techniques in Kats and Prophet, respectively, were built and tested using six years of daily state- and county-level outage data in Massachusetts (MA). We develop a Prophet model with Bayesian True Parzen Estimator optimization (Prophet-TPE) using state-level outage data and a hierarchical Prophet-Bottom-Up model using county-level data. We find that these forecasting models outperform other Bayesian and hierarchical model combinations of Prophet and Seasonal Autoregressive Integrated Moving Average (SARIMA) models in predicting NWOCI at both county and state levels. Our time series trend decomposition reveals a concerning trend in the growth of NWO in MA. We conclude with a discussion of these observations and possible recommendations for mitigating NWO. 

   more » « less