Enrico Marchesini @emarche.bsky.social · 01/07/2025🎯 39+ environments over 7 base grids, including: 🔹 Topology optimization actions 🔹 Redispatch & curtailment operations 🔹 Idle & recovery heuristics 🔹 CMDP-based constraints (overload, islanding, load shedding) 010
Enrico Marchesini @emarche.bsky.social · 01/07/2025📦 RL2Grid is a benchmark for training & evaluating RL agents on a multitude of realistic grid control tasks, modeling: ✅ AC power flow ✅ Multi-step physics simulation ✅ Operator heuristics ✅ Real-time contingencies ✅ Safety constraints 110
Enrico Marchesini @emarche.bsky.social · 01/07/2025Why power grids? 📊 Complex, dynamic, hierarchical systems 📉 Traditional solvers hit scalability walls 🌪️ Control challenges driven by VRE, demand-side volatility RL is promising for grid control, but it must be grounded and advanced realistic benchmarks! 100
Enrico Marchesini @emarche.bsky.social · 01/07/2025🚨 Excited to share RL2Grid! A standardized suite of RL tasks for realistic power grid operations ⚡ Built with TSOs, RL2Grid aims to bring RL closer to real-world critical infrastructure. 📄 Preprint: arxiv.org/abs/2503.23101 💻 Code: github.com/emarche/RL2G... Details below 👇 193
