The advances in wireless communication techniques, mobile cloud computing, automotive and intelligent terminal technology are driving the evolution of vehicle ad hoc networks into the Internet of Vehicles (IoV) paradigm. This leads to a change in the vehicle routing problem from a calculation based on static data towards real-time traffic prediction. In this paper, we first address the taxonomy of cloud-assisted IoV from the viewpoint of the service relationship between cloud computing and IoV. Then, we review the traditional traffic prediction approached used by both Vehicle to Infrastructure (V2I) and Vehicle to Vehicle (V2V) communications. On this basis, we propose a mobile crowd sensing technology to support the creation of dynamic route choices for drivers wishing to avoid congestion. Experiments were carried out to verify the proposed approaches. Finally, we discuss the outlook of reliable traffic prediction.

Electric vehicles (EVs) can behave as distributed energy storage devices for providing on-demand smart grid support service, that is an emerging Vehicle-to-Grid (V2G) technology. A high-performance and easy-implementation current control strategy for V2G Three-phase four-leg inverter with LCL filter is proposed. It consists of a deadbeat (DB) controller and a paralleled repetitive controller (RC). The DB controller is based on weighted average inductor current (WAIC) scheme, which simplifies the third-order LCL filter to be an equivalent 1st order L filter. The stability of the DB controlled inverter with the unmodelled system time delay is analyzed. DB controller is of very fast response and easy implementation, but is not immune to system time delay and various uncertainties. To overcome the disadvantages, a plug-in RC is added to reinforce the DB controller to remove harmonic distortion from the feed-in current in the presence of parameter uncertainties. A lab prototype of 10kW grid-connected three-phase four-leg inverter has been built up to validate the proposed current control strategy. The simulations and experiments are provided to demonstrate the validity of the proposed control strategy.

Durability is considered as one of the main technical obstacles to the large-scale commercialization of proton exchange membrane fuel cells (PEMFCs), which can be effectively improved through degradation prediction techniques. This article proposes a stacked echo state network (ESN) based on the genetic algorithm (GA) to predict the future degradation trend of PEMFCs. By alternately using the projection layer and the encoding layer, the proposed method can make full use of the temporal kernel property of the ESN to encode the multiscale and multilevel dynamics of the stack voltage, thereby obtaining more robust generalization performance and higher accuracy than the existing methods. Specifically, a stack voltage time series of PEMFCs is projected into the high-dimensional echo state space of the reservoir. Then, an autoencoder projects the echo state representation into the low-dimensional feature space. After that, the GA is utilized to optimize the hyperparameters of the developed model. Based on two open-source datasets of PEMFCs with different accelerated test conditions, this article systematically tested the proposed degradation prediction methods based on different model structures. Test results demonstrate that the proposed method is superior to traditional prediction methods in terms of accuracy and generalization performance.

A repetitive controller (RC) is one of the most promising candidates for harmonic compensation when designing the current controller of grid-connected inverters. The discrete-time closed-loop transfer function based frequency response method can be used to shape RC, which is applicable for a single inverter connecting to well-known inductive-impedance grids, but cannot guarantee the stability in the case of capacitive-impedance grids or complex systems, such as microgrids. To address this issue, this article presents a new passivity-based design method for an RC for LCL-type grid-connected inverters with either inverter-side or grid-side current control. With the proposed design guidelines, the output admittance of the RC-controlled inverter is tuned to be passive in all frequencies, so that it can be plug and play connected to a grid regardless of grid impedance. Meanwhile, thanks to infinite gains of an RC at the fundamental frequency and its multiples as the high-quality grid injected current in accordance with IEC 61000-3-4 standard is ensured even in the presence of distorted grid conditions. Finally, experimental results with an established lab prototype are provided to verify the effectiveness of the proposed approach.