Session: 01-01 A Just Transition to a Sustainable Future

Paper Number: 107380

107380 - Evaluation of Transmission Line Hardening Scenarios Using a Machine Learning Approach 

The power transmission infrastructure is vulnerable to extreme weather events, particularly hurricanes and tropical storms. A recent example is the damage caused by Hurricane Maria (H-Maria) in the archipelago of Puerto Rico in September 2017, where major failures in the transmission infrastructure led to a total blackout. Numerous studies have been conducted to examine strategies to strengthen the transmission system, including burying the power lines underground or increasing the frequency of tree trimming. However, few studies focus on the direct hardening of the transmission towers to accomplish an increase in resiliency. This machine learning-based study fills this need by analyzing three direct hardening scenarios and determining the effectiveness of these changes in the context of H-Maria. A methodology for estimating transmission tower damage is presented here as well as an analysis of the impact of replacing structures with a high failure rate with more resilient ones.

To determine which transmission line towers are the weakest, utility information on the material, type, location, and damage of power towers was used. The utility data analysis revealed that, as anticipated, wooden constructions were found to be more prone to fail. As a result, three hardened infrastructure scenarios were tested. The first one consists of replacing the wood two poles with a stronger structure. In the second one, the wood two-poles and three-poles were replaced, and in the third one, the wood two-pole, three-pole, and single poles were all replaced.

We utilized a Random Forest Classifier to create the damage prediction model for power towers, where, H-Maria simulated weather data from the Weather and Research Forecast Model (WRF), elevation, and land cover are combined with the features of the power towers to train the model. The damage in the towers (i.e. response variable), is processed as a binary variable, it indicates if the tower failed or not. The dataset was divided into 20% for testing and 80% for training the model. Additionally, we under and over-sampled the training dataset in order to reduce the zero inflation in the dataset. A 5-fold cross-validation was used to tune the hyperparameters of the model and compare the sampling techniques. The over-sampled dataset was found to perform better.

We experimented to determine which construction would be the best replacement for the previously discovered weak ones using the predicting model in a segment of the 115kV transmission line. We found the steel self-support pole to be the best replacement option for the towers with a high failure rate. Subsequently, the hardening analysis was scaled to all the lines on the Island. Based on the findings, we conclude that all three hardening scenarios are viable options to increase the resiliency of the lines. However, the third hardening scenario decreased the mean damaged structures per line by 10% and had a maximum decrease in damaged structures in a single line of 66%.

Presenting Author: Jorge Gonzalez City College of New York

Presenting Author Biography: n/a