Xiangyu Zou

Xiangyu Zou, Amir Reza Nikzad, Ilyas Farhat et al.

Power system restoration following blackouts must ensure frequency stability throughout the recovery process. This paper proposes a frequency-constrained mixed-integer linear programming (MILP) framework for black-start restoration planning in transmission systems with synchronous machines and energy storage systems. To prevent excessive frequency deviations caused by restorative actions, a frequency nadir prediction method is developed for power systems with energy storage system (ESS) integration and incorporated into a multiperiod optimization framework. The formulation ensures that frequency deviations resulting from restorative actions remain within prescribed safe limits. Furthermore, the presented framework leverages ESSs to enhance frequency security and recovery speed. Case studies on a modified IEEE 9-bus system demonstrate that the computed restoration plan maintains frequency security, as validated through MATLAB and PSS/E simulations, while reducing restoration time through ESS coordination.

Haisen He, Xiangyu Zou, SongLin Dong et al.

Real-world image degradation is often unknown, spatially non-uniform, and compositional, requiring all-in-one restoration models to adapt a single set of weights to diverse local corruption patterns without test-time degradation labels. Existing methods typically modulate a shared backbone with global prompts or degradation descriptors, or route features through predefined expert pools. However, compact global conditioning can bottleneck localized degradation evidence, while static expert routing may produce homogeneous updates or rely on unstable sparse assignments. We propose \textbf{Continuous Expert Assembly} (CEA), a token-wise dynamic parameterization framework for all-in-one image restoration. CEA employs a lightweight \textbf{Cross-Attention Hyper-Adapter} to probe intermediate spatial features and synthesize instance-conditioned low-rank routing bases and residual directions. Each spatial token then assembles its own residual update via dense signed dot-product affinities over the generated rank-wise components, avoiding external prompts, static expert banks, and discrete Top- selection. The resulting assembly rule also admits a linear-attention perspective, making its dense token-wise routing behavior transparent. Experiments on AIO-3, AIO-5, and CDD-11 show that CEA improves average restoration quality over strong prompt-, descriptor-, and expert-based baselines, with the clearest gains on spatially varying and compositional degradations, while maintaining favorable parameter, FLOP, and runtime efficiency.