# Machine Learning Guided Optimal Transmission Switching to Mitigate Wildfire Ignition Risk

arXiv: https://arxiv.org/abs/2510.25147 · HTML: https://mlsanity.com/paper/2510.25147/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 41 references that are in the map.
- First posted on arXiv 29 Oct 2025.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Exact Combinatorial Optimization with Graph Convolutional Neural Networks](https://mlsanity.com/paper/1906.01629/) (2019)
- [A GNN-Guided Predict-and-Search Framework for Mixed-Integer Linear Programming](https://mlsanity.com/paper/2302.05636/) (2023)
- [Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learning](https://mlsanity.com/paper/2302.01578/) (2023)
- [Machine Learning Augmented Branch and Bound for Mixed Integer Linear Programming](https://mlsanity.com/paper/2402.05501/) (2024)
- [Distributional MIPLIB: a Multi-Domain Library for Advancing ML-Guided MILP Methods](https://mlsanity.com/paper/2406.06954/) (2024)
- [Balancing Wildfire Risk and Power Outages through Optimized Power Shut-Offs](https://mlsanity.com/paper/2004.07156/) (2020)
- [Spatio-Temporal Wildfire Prediction using Multi-Modal Data](https://mlsanity.com/paper/2207.13250/) (2022)
- [Optimizing Transmission Infrastructure Investments to Support Line De-energization for Mitigating Wildfire Ignition Risk](https://mlsanity.com/paper/2203.10176/) (2022)
- [A Framework for Risk Assessment and Optimal Line Upgrade Selection to Mitigate Wildfire Risk](https://mlsanity.com/paper/2110.07348/) (2021)
- [Predicting Electricity Infrastructure Induced Wildfire Risk in California](https://mlsanity.com/paper/2206.02930/) (2022)
- [Multi-period Power System Risk Minimization under Wildfire Disruptions](https://mlsanity.com/paper/2305.02933/) (2023)
- [Managing Wildfire Risk and Promoting Equity through Optimal Configuration of Networked Microgrids](https://mlsanity.com/paper/2306.03325/) (2023)
- [Long Solution Times or Low Solution Quality: On Trade-Offs in Choosing a Power Flow Formulation for the Optimal Power Shutoff Problem](https://mlsanity.com/paper/2310.13843/) (2023)
- [Equitably allocating wildfire resilience investments for power grids: The curse of aggregation and vulnerability indices](https://mlsanity.com/paper/2404.11520/) (2024)
- [Co-optimization of power line shutoff and restoration under high wildfire ignition risk](https://mlsanity.com/paper/2204.02507/) (2022)
- [California Test System (CATS): A Geographically Accurate Test System based on the California Grid](https://mlsanity.com/paper/2210.04351/) (2022)
- [Long Duration Battery Sizing, Siting, and Operation Under Wildfire Risk Using Progressive Hedging](https://mlsanity.com/paper/2404.12296/) (2024)
- [Quantifying Metrics for Wildfire Ignition Risk from Geographic Data in Power Shutoff Decision-Making](https://mlsanity.com/paper/2409.20511/) (2024)
- [Evaluating Undergrounding Decisions for Wildfire Ignition Risk Mitigation across Multiple Hazards](https://mlsanity.com/paper/2506.06575/) (2025)
- [Optimizing Battery and Line Undergrounding Investments for Transmission Systems under Wildfire Risk Scenarios: A Benders Decomposition Approach](https://mlsanity.com/paper/2506.06687/) (2025)

## Abstract (arXiv)

To mitigate acute wildfire ignition risks, utilities de-energize power lines in high-risk areas. The Optimal Power Shutoff (OPS) problem optimizes line energization statuses to manage wildfire ignition risks through de-energizations while reducing load shedding. OPS problems are computationally challenging Mixed-Integer Linear Programs (MILPs) that must be solved rapidly and frequently in operational settings. For a particular power system, OPS instances share a common structure with varying parameters related to wildfire risks, loads, and renewable generation. This motivates the use of Machine Learning (ML) for solving OPS problems by exploiting shared patterns across instances. In this paper, we develop an ML-guided framework that quickly produces high-quality de-energization decisions by extending existing ML-guided MILP solution methods while integrating domain knowledge on the number of energized and de-energized lines. Results on a large-scale realistic California-based synthetic test system show that the proposed ML-guided method produces high-quality solutions faster than traditional optimization methods.