Search

Strong thunderstorms have substantial impacts on power systems, posing risks and inconveniences due to power outages. Developing models predicting the outages before a storm is a high priority to support restoration planning. However, most power outage data are zero-inflated, which results in some challenges in predictive modeling such as bias and inaccuracy. Power outages are also stochastic and there always exists irreducible variability in outage predictions. The goal is to develop models to overcome the challenges caused by zero-inflation and to accurately estimate power outages in terms of probability distributions to better address inherent stochasticity and uncertainty in predictions. This paper proposes a novel approach integrating mixture models with resampling and cost-sensitive learning for predicting the probability distribution for the number of outages. Validating the models using power outage data, we demonstrate that our approach offers more accurate point and probabilistic predictions compared to traditional approaches, better supporting utility restoration planning. [ABSTRACT FROM AUTHOR]

Tropical cyclones can significantly damage the electrical power system, so an accurate spatiotemporal forecast of outages prior to landfall can help utilities to optimize the power restoration process. The purpose of this article is to enhance the predictive accuracy of the Spatially Generalized Hurricane Outage Prediction Model (SGHOPM) developed by Guikema et al. (2014). In this version of the SGHOPM, we introduce a new two‐step prediction procedure and increase the number of predictor variables. The first model step predicts whether or not outages will occur in each location and the second step predicts the number of outages. The SGHOPM environmental variables of Guikema et al. (2014) were limited to the wind characteristics (speed and duration of strong winds) of the tropical cyclones. This version of the model adds elevation, land cover, soil, precipitation, and vegetation characteristics in each location. Our results demonstrate that the use of a new two‐step outage prediction model and the inclusion of these additional environmental variables increase the overall accuracy of the SGHOPM by approximately 17%. [ABSTRACT FROM AUTHOR]

Hurricanes produce significant, widespread, and often prolonged electrical-power outages. For example, Hurricane Irene caused more than 500 000 Long Island Power Authority customers to lose power and it took eight days to achieve 99% customer restoration. Individuals and businesses are heavily dependent on a continuous supply of electricity. Given this strong dependence on reliable electricity, individuals and private industries are increasingly putting collective pressure on regulators to require system hardening by utilities. In some cases, this has led to utility action. Conversely, many customers install a backup generator to guarantee electricity supply during disruptive events. These actions taken by individual customers affect their experiences in future storms, and are generally influenced by individuals’ strength of preference for reliable power, their beliefs about the likelihood of losing power in the future, and the outcomes of their most recent experiences. However, individual action may come at the expense of collective action, whereby those who buy generators, often those with more resources available to purchase the generator, do not participate in the collective grievance, reducing the demand for overall system hardening. By using a validated power-outage forecasting model in conjunction with an agent-based model, we characterize how a community’s likelihood of losing power in repeated hurricanes is affected by the complex interactions among individuals’ behavioral responses in whether to engage in personal or collective action. [ABSTRACT FROM AUTHOR]

In August 2012, Hurricane Isaac, a Category 1 hurricane at landfall, caused extensive power outages in Louisiana. The storm brought high winds, storm surge, and flooding to Louisiana, and power outages were widespread and prolonged. Hourly power outage data for the state of Louisiana were collected during the storm and analyzed. This analysis included correlation of hourly power outage figures by zip code with storm conditions including wind, rainfall, and storm surge using a nonparametric ensemble data mining approach. Results were analyzed to understand how correlation of power outages with storm conditions differed geographically within the state. This analysis provided insight on how rainfall and storm surge, along with wind, contribute to power outages in hurricanes. By conducting a longitudinal study of outages at the zip code level, we were able to gain insight into the causal drivers of power outages during hurricanes. Our analysis showed that the statistical importance of storm characteristic covariates to power outages varies geographically. For Hurricane Isaac, wind speed, precipitation, and previous outages generally had high importance, whereas storm surge had lower importance, even in zip codes that experienced significant surge. The results of this analysis can inform the development of power outage forecasting models, which often focus strictly on wind-related covariates. Our study of Hurricane Isaac indicates that inclusion of other covariates, particularly precipitation, may improve model accuracy and robustness across a range of storm conditions and geography. [ABSTRACT FROM AUTHOR]

A variety of decision-support systems, such as those employed by energy and utility companies, use the National Hurricane Center (NHC) forecasts of track and intensity to inform operational decision making as a hurricane approaches. Track and intensity forecast errors, especially just prior to landfall, can substantially impact the accuracy of these decision-support systems. This study quantifies how forecast errors can influence the results of a power outage model, highlighting the importance of considering uncertainty when using hurricane forecasts in decision-support applications. An ensemble of 1,000 forecast realizations is generated using the Monte Carlo wind speed probability model for Hurricanes Dennis, Ivan, and Katrina. The power outage model was run for each forecast realization to predict the spatial distribution of power outages. Based on observed power outage data from a Gulf Coast utility company, the authors found that in all three cases the ensemble average was a better predictor of power outages than predictions made using the official NHC forecast. The primary advantage of using an ensemble approach is that it provides a means to communicate uncertainty to decision makers. For example, the probability of a given number of outages and the potential range of power outages can be determined. Quantifying the uncertainty associated with the NHC official track and intensity forecasts can improve the real-time decisions made by governmental, public, and private stakeholders. [ABSTRACT FROM AUTHOR]

This article compares statistical methods for modeling power outage durations during hurricanes and examines the predictive accuracy of these methods. Being able to make accurate predictions of power outage durations is valuable because the information can be used by utility companies to plan their restoration efforts more efficiently. This information can also help inform customers and public agencies of the expected outage times, enabling better collective response planning, and coordination of restoration efforts for other critical infrastructures that depend on electricity. In the long run, outage duration estimates for future storm scenarios may help utilities and public agencies better allocate risk management resources to balance the disruption from hurricanes with the cost of hardening power systems. We compare the out-of-sample predictive accuracy of five distinct statistical models for estimating power outage duration times caused by Hurricane Ivan in 2004. The methods compared include both regression models (accelerated failure time (AFT) and Cox proportional hazard models (Cox PH)) and data mining techniques (regression trees, Bayesian additive regression trees (BART), and multivariate additive regression splines). We then validate our models against two other hurricanes. Our results indicate that BART yields the best prediction accuracy and that it is possible to predict outage durations with reasonable accuracy. [ABSTRACT FROM AUTHOR]

Hurricanes can severely damage the electric power system, and therefore, predicting the potential impact of an approaching hurricane is of importance for facilitating planning and storm-response activities. A data mining approach, classification and regression trees (CART), was employed to evaluate whether the inclusion of soil and topographic variables improved the predictive accuracy of the power outage models. A total of 37 soil variables and 20 topographic variables were evaluated in addition to hurricane, power system, and environmental variables. Hurricane variables, specifically the maximum wind gust and duration of strong winds, were the most important variables for predicting power outages in all models. Although the inclusion of soil and topographic variables did not significantly improve the overall accuracy of outage predictions, soil type and soil texture are useful predictors of hurricane-related power outages. Both of these variables provide information about the soil stability which, in turn, influences the likelihood of poles remaining upright and trees being uprooted. CART was also used to evaluate whether environmental variables can be used instead of power system variables. Our results demonstrated that certain land cover variables (e.g., LC21, LC22, and LC23) are reasonable proxies for the power system and can be used in a CART model, with only a minor decrease in predictive accuracy, when detailed information about the power system is not available. Therefore, CART-based power outage models can be developed in regions where detailed information on the power system is not available. [ABSTRACT FROM AUTHOR]

Electric power is a critical infrastructure service after hurricanes, and rapid restoration of electric power is important in order to minimize losses in the impacted areas. However, rapid restoration of electric power after a hurricane depends on obtaining the necessary resources, primarily repair crews and materials, before the hurricane makes landfall and then appropriately deploying these resources as soon as possible after the hurricane. This, in turn, depends on having sound estimates of both the overall severity of the storm and the relative risk of power outages in different areas. Past studies have developed statistical, regression-based approaches for estimating the number of power outages in advance of an approaching hurricane. However, these approaches have either not been applicable for future events or have had lower predictive accuracy than desired. This article shows that a different type of regression model, a generalized additive model (GAM), can outperform the types of models used previously. This is done by developing and validating a GAM based on power outage data during past hurricanes in the Gulf Coast region and comparing the results from this model to the previously used generalized linear models. [ABSTRACT FROM AUTHOR]

Abstract: Hurricanes have caused severe damage to the electric power system throughout the Gulf coast region of the US, and electric power is critical to post-hurricane disaster response as well as to long-term recovery for impacted areas. Managing power outage risk and preparing for post-storm recovery efforts requires accurate methods for estimating the number and location of power outages. This paper builds on past work on statistical power outage estimation models to develop, test, and demonstrate a statistical power outage risk estimation model for the Gulf Coast region of the US. Previous work used binary hurricane-indicator variables representing particular hurricanes in order to achieve a good fit to the past data. To use these models for predicting power outages during future hurricanes, one must implicitly assume that an approaching hurricane is similar to the average of the past hurricanes. The model developed in this paper replaces these indicator variables with physically measurable variables, enabling future predictions to be based on only well-understood characteristics of hurricanes. The models were developed using data about power outages during nine hurricanes in three states served by a large, investor-owned utility company in the Gulf Coast region. [Copyright &y& Elsevier]

This paper describes the application of a new discrete-event-simulation model of the post-earthquake electric power restoration process in Los Angeles. The findings are that (1) Los Angeles residents may experience power outages lasting up to 10 days; (2) what we call the power rapidity risk (the joint probability distribution of restoration of a specified number of customers in a specified amount of time) varies throughout the area; (3) there is a relatively high likelihood that more repair materials than are currently available will be required if a large earthquake occurs; and (4) there are ways to reduce the expected duration of earthquake-initiated power outages and they should be subjected to cost-benefit analysis. These results should be useful to utilities and emergency planners in Los Angeles. The new simulation modeling approach could be used in other seismically active cities to gain insights into the restoration process that other modeling approaches cannot provide. [ABSTRACT FROM AUTHOR]