A Unified Mamba--MoE Surrogate for Closed-Loop Simulation and Measurement-Window Forecasting of Inverter Transients

2026-08-15

AI Summary

This study addresses the architectural independence and parameter redundancy inherent in separate inverter transient simulation and window prediction models by proposing a unified Mamba-MoE surrogate model. Integrating state space models with a mixture-of-experts mechanism, the framework employs task-conditioned routing to enable dual-task adaptation within a single backbone, while incorporating an adaptive conformal layer to quantify uncertainty. As the inaugural application of this architecture to inverter transient modeling, hardware-in-the-loop validation demonstrates that the proposed method reduces model parameters by 13% and achieves superior dynamic accuracy compared to non-MoE baselines. Furthermore, it attains a prediction interval coverage probability of 94–96%, effectively balancing computational efficiency with high reliability for power electronics applications.

Abstract

This paper proposes a Mamba surrogate model with mixture-of-experts (MoE) routing to represent the transient dynamics of inverter-based resources. A Mamba surrogate model is a predictive machine learning model built on the Mamba architecture. MoE routing uses a router network to assign data-dependent weights to specialized subnetworks (experts). The resulting Mamba--MoE surrogate can perform two tasks: (i) closed-loop simulation and (ii) measurement-window forecasting of inverter transients. A single Mamba backbone with task conditioning and expert routing serves both tasks, replacing two separate specialists. Task-matched objectives fit each prediction form, and an adaptive conformal layer provides prediction intervals for both tasks. For the considered grid-following inverter, the unified surrogate model remains in the same low-error regime as a Mamba specialist pair while using 13% fewer parameters. The prediction intervals achieve 94--96% empirical mean marginal coverage across the two tasks. For transient dynamics---that is, beyond the vicinity of an equilibrium point---our surrogate model with MoE routing yields lower errors across all outputs in both tasks compared to a shared Mamba backbone without expert routing. A controller hardware-in-the-loop simulation validates our results and shows that adapting only the shared output head with limited measured data reduces held-out forecasting error.

Problem

• Inverter Transients
• Surrogate Model
• Closed-Loop Simulation
• Measurement-Window Forecasting

Innovation

• Mamba-MoE
• Unified Surrogate Model
• Task Conditioning
• Adaptive Conformal Layer
• Inverter Transients