The generation output of distributed power sources and the load possess periodic changes, which cause stability problems in the operation of the power grid. To ensure stability, energy storage devices are generally installed in the power grid, but their effectiveness is also limited by their fixed installation location and capacity. In this paper, to overcome the drawback of stationary energy storage devices, mobile energy storage devices are introduced to reduce power losses and enhance voltage stability. The installation location and capacity of these mobile energy storage devices can be changed with the generation output and load demands. Firstly, the influence of the mobile energy storage devices on power losses and voltage stability is analyzed. Next, a multi-objective optimization model is established to select the optimal installation location and the ideal capacity, which has optimization objectives including the improvement of voltage stability, the minimization of power losses, and the enhancement of utilization of energy storage devices. Finally, the particle swarm optimization algorithm is applied to solve the multi-objective optimization problem. The simulation results prove that the novel method of this paper enhances the dynamics of the power grid, i.e., the voltage vulnerability and power losses are reduced by 29% and 36%, respectively. In addition, it also increases the utilization rate of energy storage devices by 33.5% in different operating scenarios.

High-resolution wind-field prediction over complex terrain is important for wind-energy assessment, grid safety, and hazard mitigation. This study uses a coupled Weather Research and Forecasting–Computational Fluid Dynamics (WRF–CFD) workflow for the Askervein Hill benchmark. Driven by the fifth-generation European Centre for Medium-Range Weather Forecasts Reanalysis dataset, WRF provides mesoscale atmospheric conditions, and CFD resolves the terrain-induced flow features at high spatial resolution. Because repeated WRF and CFD simulations are computationally expensive, we develop a time-aware neural-network surrogate model, termed the multilayer perceptron-prior gated temporal correction (MLP-GTC) model, to predict the resulting three-component wind field. The model first learns the local wind response associated with terrain and inlet conditions, and it then applies a gated temporal correction based on recent inlet conditions and their corresponding pointwise predictions. The data are divided chronologically into 683 training, 146 validation, and 147 test time steps, with 5187 fixed spatial points evaluated at each time step. The coupled WRF–CFD simulations reproduce the observed wind structure with a maximum Pearson correlation coefficient of 0.96 and a 10 m wind-speed root mean square error of 0.84 m/s. For the three-component velocity field, MLP-GTC achieves validation/test root mean square errors of 0.282/0.310 m/s and mean absolute errors of 0.179/0.199 m/s. It improves on the multilayer perceptron model (0.486/0.516 m/s) and the matched five-step single-layer long short-term memory network (0.334/0.438 m/s).