Integrated Risk-informed Decision Framework to Minimize Wildfire-induced Power Outage Risks: A County-level Spatiotemporal Analysis

Masoudvaziri, Nima; Ganguly, Prasangsha; Mukherjee, Sayanti; Sun, Kang

doi:10.3850/978-981-14-8593-0_4243-cd

Cited by 7 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…described such a sensitivity analysis framework in detail for sensitivity analysis of model parameters applied to crime analysis (Ganguly & Mukherjee, 2021) and mental health prediction (Mukherjee et al., 2021). Such a framework has also been used in the scientific domain of infrastructure risk assessment using data‐driven techniques (Masoudvaziri et al., 2020; Mukherjee & Nateghi, 2019). However, in this paper, the failure rate λ is considered to follow a normal distribution with mean

\lambda _{base}

and standard deviation

\sigma _{base}

identified using the chi‐square goodness‐of‐fit test.…”

Section: Resultsmentioning

confidence: 99%

A simulation‐based generalized framework to model vulnerability of interdependent critical infrastructure systems under incomplete information

Ganguly

Mukherjee

2023

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

This paper proposes a novel simulation‐based hybrid approach coupled with time‐dependent Bayesian network analysis to model multi‐infrastructure vulnerability over time under physical, spatial, and informational uncertainties while considering cascading failures within and across infrastructure networks. Unlike existing studies that unrealistically assume that infrastructure managers have full knowledge of all the infrastructure systems, the proposed approach considers a realistic scenario where complete information about the infrastructure network topology or the supply–demand flow characteristics is not available while estimating multi‐infrastructure vulnerability. A novel heuristic algorithm is proposed to construct a dynamic fault tree to abstract the network topology of any infrastructure. In addition, to account for the unavailability of exact supply–demand flow characteristics, the proposed approach constructs the interdependence links across infrastructure network systems using different simulated parameters considering the physical, logical, and geographical dependencies. Finally, using parameters for geographical proximity, infrastructure managers' risk perception, and the relative importance of one infrastructure on another, the multi‐infrastructure vulnerability over time is estimated. Results from the numerical experiment show that for an opportunistic risk perception, the interdependencies attribute to redundancies, and with an increase in redundancy, the vulnerability decreases. On the other hand, from a conservative risk perspective, the interdependencies attribute to deficiencies/liabilities, and the vulnerability increases with an increase in the number of such interdependencies.

show abstract

\lambda _{base}

and standard deviation

\sigma _{base}

identified using the chi‐square goodness‐of‐fit test.…”

Section: Resultsmentioning

confidence: 99%

A simulation‐based generalized framework to model vulnerability of interdependent critical infrastructure systems under incomplete information

Ganguly

Mukherjee

2023

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

show abstract

“…Random Forest (RF ) (Breiman, 2001), Gradient Boosting Method (GBM ) (Friedman, 2001), Extreme Gradient Boosting (XGBoost), and Bayesian Additive Regression Trees (BART ) (Chipman et al, 2010;Kapelner and Bleich, 2016), are investigated. In our preliminary work (Masoudvaziri et al, 2020), it is demonstrated that for such a problem, tree-based algorithms outperform linear models.…”

Section: Overview Of Statistical Supervised Learningmentioning

confidence: 98%

“…This process was conducted to capture the effect of seasonality and preconditioning (Urbieta et al, 2015;Trigo et al, 2016;Littell et al, 2009;Gedalof et al, 2005;Crimmins and Comrie, 2005). Moreover, (Masoudvaziri et al, 2020) also provides evidence that aggregating this data to a finer temporal resolution (e.g., monthly) does not provide any significant advantage. Details of these calculations are presented in Figure 3.…”

Section: Pre-processing Of Collected Datamentioning

confidence: 99%

Impact of Geophysical and Anthropogenic Factors on Wildfire Size: A Spatiotemporal Data-Driven Risk Assessment Approach Using Statistical Learning

Masoudvaziri

Ganguly

Mukherjee

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Wildfire spread is a stochastic phenomenon driven by a multitude of geophysical and anthropogenic factors. In this study, we propose a spatiotemporal data-driven risk assessment framework to understand the effect of various geophysical/anthropogenic factors on wildfire size, leveraging a systematic machine learning approach. We apply this framework in the state of California—the most vulnerable US state to wildfires. Using county-level annual wildfire data from 2001-2015, and various geophysical (e.g., landcover, wind, surface temperature) and anthropogenic features (e.g., population density, housing type), we trained, tested, and validated a suite of ensemble tree-based learning algorithms to identify and evaluate the key factors associated with wildfire size. The extreme gradient boosting (XGBoost) algorithm outperformed all the other models in terms of generalization performance, categorization of important features, and risk performance. We found that standard deviations of meteorological variables with long-tailed distributions play a key role in predicting wildfire size. Specifically, the top ten factors associated with high risk of larger wildfires include larger standard deviations of surface temperature and vapor pressure deficit, higher wind gust, more grassy and barren land covers, lower night-time boundary layer height and higher population density. Our proposed risk assessment framework will help federal/state decision-makers to adequately plan for wildfire risk mitigation and resource allocation strategies.

show abstract

“…The degree of loss can differ based on the duration and frequency of the interruptions, as well as the particular sectors and geographical areas impacted. According to some estimates, power outages can result in annual losses of billions of dollars [5]. This is caused by a variety of factors, such as decreased productivity, infrastructure and equipment damage, and higher energy costs.…”

Section: Introductionmentioning

confidence: 99%

Classification of Electrical Fault Severity in a Modern Power System Operating Environment

Ismaeel Khalel

2023

Jurnal Teknologi

View full text Add to dashboard Cite

Electrical power systems frequently experience different kinds of faults while they are used on a daily basis. Therefore, it is crucial to classify faults according to their severity in order to keep the system operating reliably. In this study, a novel method for categorising the severity of faults in the stability of the power system into three cases namely Minor, Moderate, and Major Fault was presented. This method is based on cutting-edge artificial intelligence algorithms. Under different types of faults, the suggested methodology was used in IEEE 9-bus. The study's findings give network operators important information that they can use to spot electrical system weaknesses during serious faults and maintain the power system's dependability and continuity of energy flow.

show abstract

Integrated Risk-informed Decision Framework to Minimize Wildfire-induced Power Outage Risks: A County-level Spatiotemporal Analysis

Cited by 7 publications

References 0 publications

A simulation‐based generalized framework to model vulnerability of interdependent critical infrastructure systems under incomplete information

A simulation‐based generalized framework to model vulnerability of interdependent critical infrastructure systems under incomplete information

Impact of Geophysical and Anthropogenic Factors on Wildfire Size: A Spatiotemporal Data-Driven Risk Assessment Approach Using Statistical Learning

Classification of Electrical Fault Severity in a Modern Power System Operating Environment

Contact Info

Product

Resources

About