Predicting Power Outages from Ice Storms Using Machine Learning Models with SHAP Interpretability DOI
Farishta Rahman, T. Hassan, Prakash Ranganathan

et al.

Published: Oct. 13, 2024

Language: Английский

Assessing grid hardening strategies to improve power system performance during storms using a hybrid mechanistic-machine learning outage prediction model DOI
William Hughes, Peter L. Watson, Diego Cerrai

et al.

Reliability Engineering & System Safety, Journal Year: 2024, Volume and Issue: 248, P. 110169 - 110169

Published: May 5, 2024

Language: Английский

Citations

8
Most influential feature form for supervised learning in voltage sag source localization DOI Creative Commons
Younes Mohammadi, Boštjan Polajžer, Roberto Chouhy Leborgne

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 133, P. 108331 - 108331

Published: April 2, 2024

The paper investigates the application of machine learning (ML) for voltage sag source localization (VSSL) in electrical power systems. To overcome feature-selection challenges traditional ML methods and provide more meaningful sequential features deep methods, proposes three time-sample-based feature forms, evaluates an existing form. effectiveness these forms is assessed using k-means clustering with k = 2 referred to as downstream upstream classes, according direction origins. Through extensive simulations, including noises a regional network, identifies sequence involving multiplication positive-sequence current magnitude sine its angle most prominent study develops further such decision trees (DT), support vector (SVM), random forest (RF), k-nearest neighbor (KNN), ensemble (EL), designed one-dimensional convolutional neural network (1D-CNN). results found that combination 1D-CNN or SVM achieved highest accuracies 99.37% 99.13%, respectively, acceptable/fast prediction times, enhancing VSSL. exceptional performance CNN was also approved by field measurements real network. However, selecting best deployment requires trade-off between accuracy real-time implementation requirements. research findings benefit operators, large factory owners, renewable energy park producers. They enable preventive maintenance, reduce equipment downtime/damage industry systems, mitigate financial losses, facilitate assignment power-quality penalties responsible parties.

Language: Английский

Citations

7
Extreme outage prediction in power systems using a new deep generative Informer model DOI
Razieh Rastgoo, Nima Amjady, Syed Islam

et al.

International Journal of Electrical Power & Energy Systems, Journal Year: 2025, Volume and Issue: 167, P. 110627 - 110627

Published: March 23, 2025

Language: Английский

Citations

1
Quantifying household vulnerability to power outages: Assessing risks of rapid electrification in smart cities DOI Creative Commons

Andrew Majowicz,

Chetan Popli,

Philip Odonkor

et al.

Journal of Smart Cities and Society, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 15, 2025

As cities accelerate decarbonization through building electrification, the growing dependence on electrical systems introduces new vulnerabilities during power disruptions. While grid-level resilience has been widely studied, household-scale impacts of electrification remain poorly understood. In this study, we develop a vulnerability assessment framework that combines machine learning classification with high-resolution synthetic energy data from 129,000 U.S. single-family homes. Our two-stage approach first identifies household levels over 80% accuracy and then quantifies outage using composite risk index incorporates profiles, backup capabilities, climate exposure. A simulated case study reveals fully electrified households face significantly higher risks winter storms, 60% greater compared to mixed-energy contrast, solar-equipped exhibit enhanced heat waves, leveraging renewable resources mitigate risks. By highlighting critical dependencies adaptive capacities, our emphasizes importance diversity distributed in reducing vulnerabilities. This scalable, non-intrusive methodology provides actionable insights for policymakers urban planners design climate-resilient systems.

Language: Английский

Citations

0
Dynamic Bayesian Network Model for Overhead Power Lines Affected by Hurricanes DOI Creative Commons
Kehkashan Fatima, Hussain Shareef

Forecasting, Journal Year: 2025, Volume and Issue: 7(1), P. 11 - 11

Published: March 5, 2025

This paper investigates the dynamics of Hurricane-Induced Failure (HIF) by developing a probabilistic framework using Dynamic Bayesian Network (DBN) model. The model captures complex interplay factors influencing Hurricane Wind Speed Intensity (HWSI) and its impact on asset failures. In proposed DBN model, pole failure mechanism is represented principles, encompassing bending elasticity endurance foundational strength system poles. To characterize stochastic properties HIF, Monte Carlo simulation (MCS) employed in conjunction with fragility curves (FC) scenario reduction (SCENRED) algorithm. evaluates probability compares results based curve algorithm (FC-MCS-SCENRED) are validated standard IEEE 15 bus 33 radial distribution as case study. show that they consistent data obtained FC-MCS-SCENRED also reveal HWSI plays critical role determining HIF rates likelihood These findings hold significant implications for inspection maintenance scheduling overhead power lines susceptible to hurricane-induced impacts.

Language: Английский

Citations

0
AI-Enabled Predictive Analytics in Smart Grids: The Case of Sweden DOI Creative Commons
Theodore Kindong, Björn Johansson, Victoria Paulsson

et al.

Complex Systems Informatics and Modeling Quarterly, Journal Year: 2025, Volume and Issue: 42, P. 43 - 62

Published: April 30, 2025

Smart grids (SGs) revolutionize existing power by using a wide range of developing disruptive technologies to generate clean, efficient, and predictable energy. Our study uses an action research method focuses solely on the first two stages process, diagnosis planning, evaluate ways adopt artificial intelligence (AI) applications in SGs for predictive analytics practice. The stage entails conducting systematic literature review AI SGs, highlighting four areas potential analytics: outage prediction, demand response, control coordination, AI-enabled security optimize decision-making, diagnose faults, improve grid stability security. planning step included document analysis devise methods enable practical implementation smart analytics. Finally, we address implementing transparent analytics, followed conclusion future direction. study’s key is that more needed complete taking (implementing solution), evaluation (assessing results), learning (reflecting lessons learned) phases cycle.

Language: Английский

Citations

0
A multivariate prediction framework for flood-induced substation damage based on Generative Adversarial Network and MPformer-based two-stage model DOI
Yu Shi, Ying Shi, Degui Yao

et al.

Sustainable Energy Grids and Networks, Journal Year: 2025, Volume and Issue: unknown, P. 101740 - 101740

Published: May 1, 2025

Language: Английский

Citations

0
Resilient dynamic microgrid formation by deep reinforcement learning integrating physics-informed neural networks DOI
Mingze Xu, Shunbo Lei, Chong Wang

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 138, P. 109470 - 109470

Published: Oct. 22, 2024

Language: Английский

Citations

3
Predicting Power Outages from Ice Storms Using Machine Learning Models with SHAP Interpretability DOI
Farishta Rahman, T. Hassan, Prakash Ranganathan

et al.

Published: Oct. 13, 2024

Language: Английский

Citations

0