Decentralized and Equilibrium-Set-Oriented Stability Analysis and Control for Power Systems
arXiv:2609.00497
2026
Dynamics
1 ideas extracted · analyzed Sep 2, 2026
What the math gives to ML
The paper provides a transferable compositional stability mechanism: input-output differential passivity (IODP), certified using local Jacobian inequalities and a quadratic differential storage matrix. Unlike equilibrium-specific Lyapunov analysis, IODP is defined over a domain of state-input pairs and therefore certifies an entire equilibrium set, making it suitable for neural modules whose operating point changes during training or inference. The most direct transfer is a passivity-constrained neural block: estimate or bound its Jacobians, enforce the local matrix inequality with a differentiable penalty or projection, and compose blocks while monitoring the resulting contraction or incremental-gain margin.
Ideas from this paper
✗ Failed on benchmark
2026
Replace selected residual, recurrent, or state-space blocks by modules whose input-output Jacobians satisfy an IODP inequality throughout a prescribed activation domain. The constraint controls incremental amplification between two trajectories without requiring either trajectory to remain near one fixed equilibrium, so it should improve robustness to changing contexts and prevent exploding long-horizon sensitivities.
Useful8/10
Difficulty6/10
Novelty6/10