Energy storage system (ESS) management benefits the operation of all-electric ships (AESs) since its ability to balance the generation and demand. However, current works rarely consider the influence of navigation uncertainties, i.e., uncertain water waves and winds, and fail to address two characteristics of shipboard ESS, i.e., redundant capacity and distributed locations. In this paper, a two-stage robust optimal shipboard microgrid operation method is proposed to mitigate the pre-voyage and intra-voyage navigation uncertainties. The first stage is to regulate the onboard generation and voyage variables for addressing the worst pre-voyage navigation uncertainties and the second stage is an on-line recourse action which acts on intra-voyage uncertainty realization. To address the characteristics of shipboard ESS, the onboard batteries are separated into two groups and a multi-battery management strategy is proposed for the battery lifetime extension. An AES with 4 DGs and 4 batteries is used in the case studies. The simulation results show that the proposed method can well adapt to the navigation uncertainties and the multi-battery management can extend the battery lifetime by iteratively using different battery groups.

Coordinately embedding machine learning and optimization in the Monte Carlo simulation is proposed as a new framework for reliability evaluation, which is becoming more challenging due to the joining of variability and intermittency of the renewable generation and components' ageing. As a machine learning method, the dynamic Bayesian belief network predicts the renewable outputs by generating their probability distributions through historical data to overcome the defect of rarely grasping the low-probability events of the traditional methods which either predict a single-point value or presume a parametric probability distribution. As the internal operation module of the framework, the rolling-horizon unit commitment maintains the complexity of the operation model and meantime punctually updates the predicted renewable generation and the components' ageing. The dynamic Bayesian belief network and the rolling-horizon unit commitment traverse time step after time step throughout the horizon, and thus form one bid of Monte Carlo simulation. In each time step, the dynamic Bayesian belief network extracts the probability distributions of the renewable generation, from which the boundary of the commitment is sampled, and the impact of scheduling the generators on their ageing is then accumulated from the commitment. The proposed framework has its effectiveness proved on a microgrid.