用于逆变器暂态的闭环仿真与测量窗口预测的统一Mamba-MoE代理模型
A Unified Mamba--MoE Surrogate for Closed-Loop Simulation and Measurement-Window Forecasting of Inverter Transients
- Purdue University（普渡大学）
- Powermore Ltd.（宝电科技有限公司）
- New Jersey Institute of Technology（新泽西理工学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出带MoE路由的统一Mamba代理模型，可同时完成逆变器暂态的闭环仿真与测量窗口预测，参数减少13%且误差更低，经硬件在环仿真验证有效。
AI中文摘要：
本文提出一种带混合专家（Mixture-of-Experts，MoE）路由的Mamba代理模型，用于表征基于逆变器的资源的暂态动力学。Mamba代理模型是基于Mamba架构构建的预测机器学习模型，MoE路由使用路由器网络为专用子网络（专家）分配依赖数据的权重。由此得到的Mamba-MoE代理模型可执行两项任务：（i）逆变器暂态的闭环仿真；（ii）测量窗口预测。单个带任务条件和专家路由的Mamba主干网络可同时服务两项任务，替代两个独立的专用模型。任务匹配目标适配每种预测形式，自适应保形层为两项任务提供预测区间。对于所考虑的电网跟随逆变器，该统一代理模型与Mamba专用模型对保持相同的低误差水平，同时参数减少13%。预测区间在两项任务中实现94%–96%的经验平均边际覆盖率。对于暂态动力学（即超出平衡点附近范围的情况），带MoE路由的代理模型在两项任务的所有输出上，误差均低于不带专家路由的共享Mamba主干网络。控制器硬件在环仿真验证了本文结果，表明仅用有限测量数据调整共享输出头可降低预留样本的预测误差。
英文摘要：
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.
