Quantifying the Risk of Wildfire Ignition by Power Lines under Extreme Weather Conditions.

This paper presents a surrogate model to quantify the risk of wildfire ignition by individual power lines under extreme weather conditions. Wind speed and wind gust can lead to conductor clashing, which is a cause of igniting disastrous wildfires. The 3D non-linear vibration equations of power lines are employed to generate a dataset that considers physical, structural, and meteorological parameters, including the span of the power line, conductor diameter, wind speed, wind gust, phase clearance, and wind direction. A set of machine learning models is assembled based on these features to generate a score representing the risk of conductor clashing for each power line within a network, quantifying the risk of wildfire ignition. The rendered score represents the chance of the conductor clashing in place of simulating a Runge-Kutta method. A discussion on the impact of various meteorological parameters on power lines under the energization risk is presented. Besides, it is shown how the presented risk measure can be utilized to weigh in the fire safety and service continuity trade-off.