By exploiting the spatial diversity of global navigation satellite system based passive multistatic radar, this article proposes a novel joint detection and localization method for maritime moving ships. First, for each bistatic baseline, the weak target energy is concentrated in the range-Doppler map over the long integration time with a motion compensation technique that needs to search the unknown Doppler frequency rate value. Then, the range-Doppler maps pertaining to all bistatic baselines are projected into the Cartesian planes that represent the surveyed area. The projection processing needs to search the unknown X- and Y-axis components of the target velocity vector. A quadratic equation is derived to describe the relationship between the Doppler frequency rate and target velocity vector. Therefore, one of the velocity vector components does not require to be searched, leading to improved computational efficiency. Finally, multistatic integration is performed to combine all Cartesian planes via an objective function, which cannot only focus the target energy for joint detection and localization but also exclude the invalid solution induced by the quadratic equation. Numerical results against the simulations and real experiments demonstrate that the proposed method has close detection, positioning, and velocity estimation capabilities to the existing method, but with a much higher computational efficiency.

The current uneven deployment of charging stations for electric vehicles (EVs) requires a reliable prediction solution for smart grids. Existing traffic prediction assumes that users’ charging durations are constant in a given period and may not be realistic. In fact, the actual charging duration is affected by various factors including battery status, user behavior, and environment factors, leading to significant differences in charging duration among different charging stations. Ignoring these facts would severely affect the prediction accuracy. In this paper, a Transformer-based prediction of user charging durations is proposed. Moreover, a data aggregation scheme with privacy protection is designed. Specifically, the Transformer charging duration prediction dynamically selects active and reliable temporal nodes through a truncated attention mechanism. This effectively eliminates abnormal fluctuations in prediction accuracy. The proposed data aggregation scheme employs a federated learning framework, which centrally trains the Transformer without any prior knowledge and achieves reliable data aggregation through a dynamic data flow convergence mechanism. Furthermore, by leveraging the statistical characteristics of model parameters, an effective model parameter updating method is investigated to reduce the communication bandwidth requirements of federated learning. Experimental results show that the proposed algorithm can achieve the novel prediction accuracy of charging durations as well as protect user data privacy.