Federated learning (FL) has been recognized as a promising paradigm to support distributed AI model training among wireless devices (WDs) under the coordination of an edge server (ES) without sharing local datasets. To alleviate computation burden of resource-limited WDs, model partitioning that leverages computing capability at the ES is further integrated into FL, yielding the split (S) FL framework. In this paper, we study online bandit model partitioning and resource allocation for SFL over dynamic wireless networks, aiming to minimize overall energy-latency cost (ELC). Unlike prior works focusing on offline static or online gradient-based model splitting and resource allocation, we consider a practical setting where the analytical expression of ELC function is unavailable, and instead only the function values at queried points are revealed. To tackle such a challenging mixed-integer non-linear programming problem in the online bandit context, novel Bayesian optimization (BO)-based approaches are put forth by relying on a Gaussian process (GP)-based surrogate model to actively select the model splitting points and resource allocation decisions per round via the low-complexity acquisition. Besides incorporating training model-specific structural information in the kernel design of the GP surrogate, an ensemble of GP models with data-adaptive weights is further leveraged to capture system dynamics. To cope with the challenging combinatorial nature and strong coupling over mixed action space during acquisition, an efficient alternating optimization approach is proposed building upon a novel contextual local search method. Numerical tests demonstrate that the proposed BO-based approaches outperform the contemporary baselines under various practical SFL settings.

Power electronic transformer (PET) is an emerging new type of power converter in recent years. It has not only the basic functions of power transformation and isolation, but also the extra functions of power quality control. A novel power electronics transformer for distribution system named flexible power distribution unit is proposed in this paper, and the energy exchange mechanism between the network and load is revealed. Finally, a 100kW 600Vac/220Vac/110Vdc medium frequency isolated prototype is developed and demonstrated in laboratory. The experimental results show that the proposed structure and control strategy are feasible.

Solid State Power electronic transformer (PET) is an emerging new type of power converter in recent years. It has not only the basic functions of power transformation and isolation, but also the extra functions of power quality control. This paper presents the key control strategies of solid state PET for electrical distribution system application, especially under voltage disturbance conditions. Several critical grid voltage disturbances are generated by a disturbance voltage source based on a three phase PWM inverter. And the solid state PET prototype is tested and passed voltage disturbance ride through function. The experimental results verify the PET power quality control abilities.