Short-Term Prediction of Electricity Outages Caused by Convective Storms

Research output: Contribution to journalArticleScientificpeer-review

Standard

Short-Term Prediction of Electricity Outages Caused by Convective Storms. / Tervo, Roope; Karjalainen, Joonas; Jung, Alexander.

In: IEEE Transactions on Geoscience and Remote Sensing, Vol. 57, No. 11, 8751131, 01.11.2019, p. 8618-8626.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

APA

Vancouver

Author

Bibtex - Download

@article{32dda85dbd67476198cdf0d94292cfa7,
title = "Short-Term Prediction of Electricity Outages Caused by Convective Storms",
abstract = "Prediction of power outages caused by convective storms, which are highly localized in space and time, is of crucial importance to power grid operators. We propose a new machine learning approach to predict the damage caused by storms. This approach hinges identifying and tracking of storm cells using weather radar images on the application of machine learning techniques. Overall prediction process consists of identifying storm cells from CAPPI weather radar images by contouring them with a solid 35-dBZ threshold, predicting a track of storm cells, and classifying them based on their damage potential to power grid operators. Tracked storm cells are then classified by combining data obtained from weather radar, ground weather observations, and lightning detectors. We compare random forest classifiers and deep neural networks as alternative methods to classify storm cells. The main challenge is that the training data are heavily imbalanced, as extreme weather events are rare.",
keywords = "Machine learning, multilayer perceptrons (MLPs), power distribution faults, radar tracking",
author = "Roope Tervo and Joonas Karjalainen and Alexander Jung",
year = "2019",
month = "11",
day = "1",
doi = "10.1109/TGRS.2019.2921809",
language = "English",
volume = "57",
pages = "8618--8626",
journal = "IEEE Transactions on Geoscience and Remote Sensing",
issn = "0196-2892",
number = "11",

}

RIS - Download

TY - JOUR

T1 - Short-Term Prediction of Electricity Outages Caused by Convective Storms

AU - Tervo, Roope

AU - Karjalainen, Joonas

AU - Jung, Alexander

PY - 2019/11/1

Y1 - 2019/11/1

N2 - Prediction of power outages caused by convective storms, which are highly localized in space and time, is of crucial importance to power grid operators. We propose a new machine learning approach to predict the damage caused by storms. This approach hinges identifying and tracking of storm cells using weather radar images on the application of machine learning techniques. Overall prediction process consists of identifying storm cells from CAPPI weather radar images by contouring them with a solid 35-dBZ threshold, predicting a track of storm cells, and classifying them based on their damage potential to power grid operators. Tracked storm cells are then classified by combining data obtained from weather radar, ground weather observations, and lightning detectors. We compare random forest classifiers and deep neural networks as alternative methods to classify storm cells. The main challenge is that the training data are heavily imbalanced, as extreme weather events are rare.

AB - Prediction of power outages caused by convective storms, which are highly localized in space and time, is of crucial importance to power grid operators. We propose a new machine learning approach to predict the damage caused by storms. This approach hinges identifying and tracking of storm cells using weather radar images on the application of machine learning techniques. Overall prediction process consists of identifying storm cells from CAPPI weather radar images by contouring them with a solid 35-dBZ threshold, predicting a track of storm cells, and classifying them based on their damage potential to power grid operators. Tracked storm cells are then classified by combining data obtained from weather radar, ground weather observations, and lightning detectors. We compare random forest classifiers and deep neural networks as alternative methods to classify storm cells. The main challenge is that the training data are heavily imbalanced, as extreme weather events are rare.

KW - Machine learning

KW - multilayer perceptrons (MLPs)

KW - power distribution faults

KW - radar tracking

UR - http://www.scopus.com/inward/record.url?scp=85074498250&partnerID=8YFLogxK

U2 - 10.1109/TGRS.2019.2921809

DO - 10.1109/TGRS.2019.2921809

M3 - Article

AN - SCOPUS:85074498250

VL - 57

SP - 8618

EP - 8626

JO - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

SN - 0196-2892

IS - 11

M1 - 8751131

ER -

ID: 38650319