Low fault diagnosis accuracy in case of insufficient and imbalanced samples is a major problem in the wind turbine fault diagnosis. The imbalance of samples refers to the large difference in the number of samples of different categories or the lack of a certain fault sample, which requires good learning of the characteristics of a small number of samples. Sample generation in the deep learning generation model can effectively solve this problem. In this study, we proposed a novel multiclass wind turbine bearing fault diagnosis strategy based on the conditional variational generative adversarial network (CVAE-GAN) model combining multisource signals fusion. This strategy converts multisource 1-D vibration signals into 2-D signals, and the multisource 2-D signals were fused by using wavelet transform. The CVAE-GAN model was developed by merging the variational autoencoder (VAE) with the generative adversarial network (GAN). The VAE encoder was introduced as the front end of the GAN generator. The sample label was introduced as the model input to improve the model’s training efficiency. Finally, the sample set was used to train encoder, generator, and discriminator in the CVAE-GAN model to supplement the number of the fault samples. In the classifier, the sample set is used to do experimental analysis under various sample circumstances. The results show that the proposed strategy can increase wind turbine bearing fault diagnostic accuracy in complex scenarios.

The fault characteristics of the rolling bearings of wind turbine gearboxes are unstable under actual operating conditions. Problems such as inadequate fault sample data, imbalanced data types, and noise labels (error labels) in historical data occur. Consequently, the accuracy of wind turbine gearbox bearing fault diagnosis under actual operating conditions is insufficient. Hence, a new method for the fault diagnosis of wind turbine gearbox bearings under actual operating conditions is proposed. It uses an improved label-noise robust auxiliary classifier generative adversarial network (rAC-GAN) driven by limited data. The improved rAC-GAN realizes a batch comparison between the generated and real data to ensure the quality of the generated data and improve the generalization capability of the model in scenarios of actual operating conditions. It can be used to generate a large number of multitype fault data that satisfy the characteristics of the probability distribution of real samples and displays higher robustness to label noises. Experiments indicate that compared with other methods, the new method exhibits a higher accuracy in the multistate classification of rolling bearings under actual operating conditions when driven by limited data with noise labels.

Virtual synchronous generator technology can effectively improve the anti‐interference characteristics of the system frequency and bus voltage in the microgrid, and solve the problems of insufficient damping and low inertia of the system. However, in an islanded microgrid with multiple distributed generation, the difference in line impedance will cause local voltage deviations, which in turn leads to a series of problems, such as reducing power distribution accuracy and increasing bus voltage drop. Therefore, for the island‐type microgrid multi‐inverter distributed power generation parallel system, in order to solve the problem of low power distribution accuracy and large frequency oscillation caused by system parameters in virtual synchronous generator control, an improved virtual synchronous generator control algorithm based on adaptive droop coefficient is proposed in this paper, which not only eliminates the resistance component of the line impedance, makes the system impedance characteristic present a purely inductive nature, but also realises real‐time adjustment of active and reactive power. While maintaining the stability of the bus voltage and system frequency, it maintains high power distribution accuracy and improves the dynamic performance and operational stability of the power grid system.

To study the impact of personal carbon trading (PCT) mechanism on the economy and reliability of the power distribution system operation, this paper proposes an orderly charging and discharging strategy for electric vehicles (EVs) that integrates a dynamic update mechanism of charging tariff and carbon revenue, taking into account the travel characteristics of EVs and users’ willingness to respond. First, the probability density of the travel time parameters for EVs is calculated based on an improved kernel density estimation method. Second, the carbon emissions at each stage of the lifecycle of electric vehicles are calculated using a life cycle assessment approach (LCA), and a model for electric vehicle carbon quota and carbon revenue is constructed. Then, based on the net load data of the power distribution system, a dynamic updating model for the pricing of ordered charging and discharging is established. Finally, with the objective of reducing the dispatching cost for electric vehicle users and stabilizing the load fluctuation of the power distribution network, an optimization model for electric vehicle charging and discharging load dispatching is constructed. Based on the dynamic charging and discharging tariff information and state of charge (SOC) at the time of access to the grid, an evaluation model of the economic benefits of EV participation in orderly regulation is constructed. The response willingness of electric vehicle users to the dispatching strategy is inferred using the fuzzy logic control algorithm. The simulation results validate the effectiveness of this dispatching strategy in reducing the dispatching cost for EV users and stabilizing the net load fluctuation of the power distribution system. Furthermore, it is observed that as carbon prices increase, the optimization dispatching effect becomes more pronounced.

Inertial support for hybrid AC/DC microgrid systems is provided by the virtual synchronous generator (VSG). However, the fast performance of the system is neglected while enhancing the stability of the system. To address this problem, an adaptive virtual inertia control strategy based on VSG technology is proposed. This control approach adaptively adjusts the system virtual inertia when the system operation deviates from the nominal value, by slowing down the rate of change of AC frequency and DC voltage and improving the deviation of AC frequency and DC voltage. Meanwhile, when the AC frequency and DC voltage restore back to the rated value, the rate of change of AC frequency is accelerated and the DC voltage fluctuation is reduced by dynamically adjusting the virtual inertia of the system. The proposed adaptive virtual inertia control method combines the advantages of large and small inertia to effectively improve the dynamic response of the system voltage and frequency in both rectifier and inverter modes. Finally, the simulation and experimental results verify the effectiveness of the proposed control algorithm.