Related Experiment Video
Updated: Aug 2, 2026
04:35
Development of an Individual-Tree Basal Area Increment Model using a Linear Mixed-Effects Approach
Published on: July 3, 2020
Nonparametric Tree-Based Predictive Modeling of Storm Outages on an Electric Distribution Network
Jichao He1, David W Wanik2, Brian M Hartman3
1Department of Mathematics, University of Connecticut, Storrs, CT, USA.
Summary
Bayesian additive regression trees (BART) and quantile regression forests (QRF) predict storm outages, with BART offering more accurate point estimates and QRF better prediction intervals at finer resolutions. Combining both models provides a comprehensive impact assessment for utilities.
Area of Science:
- Environmental science
- Computer science
- Electrical engineering
Background:
- Accurate prediction of storm-induced power outages is crucial for electric utility resource management.
- Nonparametric tree-based models offer advanced analytical capabilities for complex environmental and infrastructure data.
Purpose of the Study:
- To compare the performance of Quantile Regression Forests (QRF) and Bayesian Additive Regression Trees (BART) for predicting storm outages on electric distribution networks.
- To evaluate the accuracy of point estimates and prediction intervals generated by QRF and BART across different spatial resolutions and storm types.
Main Methods:
- Utilized high-resolution weather, infrastructure, and land use data for 89 storm events.
- Applied and compared two nonparametric tree-based models: Quantile Regression Forests (QRF) and Bayesian Additive Regression Trees (BART).
- Assessed model performance based on point estimate accuracy and prediction interval quality at various spatial scales (2-km grid cells, towns, divisions, service territory).
Main Results:
- Bayesian Additive Regression Trees (BART) provided more accurate point estimates spatially compared to Quantile Regression Forests (QRF).
- Quantile Regression Forests (QRF) generated superior prediction intervals at higher spatial resolutions (2-km grid cells, towns).
- BART predictions were more effective when aggregated to coarser resolutions (divisions, service territory), and predictive accuracy varied by season, being highest for winter storms.
Conclusions:
- Both BART and QRF have distinct strengths in predicting storm outages, with BART excelling in point estimates and QRF in prediction intervals at fine resolutions.
- The optimal model choice depends on the desired spatial resolution and whether point estimates or prediction intervals are prioritized.
- Integrating both BART and QRF models is recommended to provide a comprehensive understanding of storm impacts, enabling better utility decision-making for resource allocation.
Related Concept Videos
01:25Distribution Reliability and Automation
Distribution reliability in electrical power systems is critical for ensuring an uninterrupted power supply to consumers at minimal cost. According to IEEE Standard Terms, reliability is the probability that a device will function without failure over a specified time period or amount of usage. For electric power distribution, this translates to maintaining continuous power supply and addressing customer concerns over power outages. Several indices, as defined by IEEE Standard 1366-2012, are...
01:23Maximum Power Flow and Line Loadability
The maximum power flow for lossy transmission lines is derived using ABCD parameters in phasor form. These parameters create a matrix relationship between the sending-end and receiving-end voltages and currents, allowing the determination of the receiving-end current. This relationship facilitates calculating the complex power delivered to the receiving end, from which real and reactive power components are derived.
01:24Fast Decoupled and DC Powerflow
The fast decoupled power flow method addresses contingencies in power system operations, such as generator outages or transmission line failures. This method provides quick power flow solutions, essential for real-time system adjustments. Fast decoupled power flow algorithms simplify the Jacobian matrix by neglecting certain elements, leading to two sets of decoupled equations:
01:18Steps in Outbreak Investigation
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
01:19Survival Tree
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a survival tree begins...
Building a Survival Tree
Constructing a survival tree begins...
01:14Parametric Survival Analysis: Weibull and Exponential Methods
Parametric survival analysis models survival data by assuming a specific probability distribution for the time until an event occurs. The Weibull and exponential distributions are two of the most commonly used methods in this context, due to their versatility and relatively straightforward application.
Weibull Distribution
The Weibull distribution is a flexible model used in parametric survival analysis. It can handle both increasing and decreasing hazard rates, depending on its shape parameter...
Weibull Distribution
The Weibull distribution is a flexible model used in parametric survival analysis. It can handle both increasing and decreasing hazard rates, depending on its shape parameter...