Surplus electricity energy from renewable sources can be efficiently utilized by converting it into other forms of energy in the integrated energy system (IES). Local electricity energy sharing can be realized through effective dispatching and independent transaction between producers and consumers. This features the merits on energy consumption and operational cost reduction. In this paper, a novel energy scheduling regime is proposed for the electricity-hydrogen-heat IES clusters under a peer-to-peer (P2P) electricity and heat energy transaction structure. To instantly control the robustness of the scheduling decisions, a weighted MPC strategy is newly proposed for online decision-makings. Furthermore, an adaptive alternating direction method of multipliers (ADMM) with varying penalties algorithm that can effectively preserve prosumer privacy is proposed, which enables the operators to coordinate various parties in the multi-energy microgrids. Extensive case studies based on a typical testing system are carried out, of which the simulation results demonstrate the effectiveness of the proposed scheduling regime and suggest potential for practical application.

With the popularity of electric vehicles (EVs), vehicle-to-grid (V2G) technology is attracting increasing attention due to its crucial merit of enabling bidirectional power flows between EVs and grid, so as to enhance the grid security and stability by regulated dispatching. However, the existing V2G approaches are confronted with several unrealizable challenges because of high computational complexity for large-scale EVs and impracticality for future power data acquisition. In this article, an edge computing framework is proposed in a distributed manner to ensure the dispatching efficiently and provide the raw dataset flexibly. Meanwhile, the long short-term memory network is applied to prediction merely by the past and present power data. Moreover, attention mechanism and data clustering are utilized to improve the prediction accuracy and operation robustness. Experiments involving real dataset demonstrated that the proposed V2G scheme is able to achieve very satisfactory dispatching performance with the prediction accuracy up to 98.89%.

An accurate electrical load forecast is essential for the effective implementation of vehicle-to-grid (V2G) technology to achieve optimal electric vehicle (EV) charging decisions, consequently, ensuring the security and stability of power grid. While prevailing evaluation metrics prioritize forecast quality, they often overlook the significant influence a forecast exerts when integrated into the V2G scheduling optimization. In this paper, a reliable metric is proposed for forecasts in the context of V2G scheduling from the perspective of forecast value. Firstly, we conducted meticulously designed experiments to expose the limitations of forecast quality metrics in the context of V2G scheduling, as well as reveal three key findings. Subsequently, to address computational challenges and enhance representativeness of scheduling results, statistical features of EV charging are used to construct the aggregate model of EV fleet. Then, a reliable metric called V2G scheduling value error (V2G-SVE) is proposed to evaluate the degradation rate of scheduling performance as the score for forecasting performance. Finally, extensive case studies provide compelling evidence for the effectiveness and broad applicability of V2G-SVE. Beyond proposing an evaluation metric, this paper also aims to provide valuable insights about potential direction of improvement for future load forecasting technology.

This work proposes an information security vehicleto- grid (V2G) scheduling solution, which combines Federated deep learning with distributed edge computing for V2G operation. In this framework, each charging point is equipped with an intelligent computing module to conduct distributed edge scheduling for the connected electric vehicle (EV), so that not only the computation of inference process is efficient, but also the privacy-preserving of EV users is guaranteed. Besides, the desensitized V2G data of charging points are used to train the deep neural network model in each charging station. Therefore, the accurate future data acquisition problem and the uncertainty handling challenges under traditional optimization methods is avoided. At the same time, the spatial-based and time-based clustering methods are applied to improve the accuracy of prediction. Finally, through federated learning, each charging station uploads the local model to the cloud server, and a stochastic client selection pattern is designed to improve the scalability of model aggregation in the cloud server. In this way, the digital assets of each charging station are protected, and computing and communication costs are reduced. Simulation results on real datasets show that the proposed framework has superior performance in terms of training accuracy, communication burden, and computing performance, while maintaining the privacy of EV users and the digital assets of charging stations.