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

Assessing Fire Risk in Wildland–Urban Interface Regions Using a Machine Learning Method and GIS data: The Example of Istanbul’s European Side

“…In this way, when a fire starts, it can spread rapidly due to the effect of dry air and wind. For this reason, this tends to create a larger burnt area than fires started by other sources [59]. Power transmission lines play an important role in forest and WUI fires as a human-made factor because faults in the lines can, at the same time, also cause fires, including in cities, regardless of meteorological conditions [60,61].…”

Recursive restoration refinement: A fast heuristic for near-optimal restoration prioritization in power systems

“…Previous work has investigated approaches to optimize a deenergization plan that minimizes wildfire ignition risk while maximizing the load demand that can be met [27], [28]. Data driven and machine learning methods attempt to accelerate the solution time of these optimization problems, which can be very difficult to solve to optimality [29]- [31]. Other research uses the Optimal Power Shutoff problem as a basis to plan infrastructure upgrades that minimize the impact of PSPS or reduce the need for PSPS in the future.…”

“…Resilience through battery installations or under-grounding of lines is studied in [32]- [35], resilience through microgrid operations in [36], [37], and load shifting through energy storage to reduce power outages in [38]. Other OPS research considers extensions necessary for distribution grids [39], concurrent planning of PSPS and grid restoration [40], considerations of fairness for load outages [41], improved forecasting of wildfire ignition risk [31], [42], and dynamic line rating to reduce current rather than fully de-energize lines [43].…”