The voltage sags' caused recognition is the basis for formulating governance plans and clarifying liabilities for accidents. The diversification of smart grid equipment, the grid-connected power generation of new energy sources and the regional differentiation of power consumption modes pose new challenges to the traditional methods. In this study, a method based on deep learning hybrid model is proposed. The convolutional neural network is used to flexibly receive the voltage after two-dimensional transformation, so as to automatically obtain the time series and spatial characteristics of the voltage sag signals. The deep belief network is used to replace the fully connected layers in convolutional neural network, thereby enhancing the multi-label classification ability of the model. The parameters obtained by the unsupervised training of the stacked sparse denoising auto-encoder are used to initialise the weight of deep belief network, thereby improving the convergence speed and the anti-noise performance of the model. Iterative training and repeated testing of the network using pre-processed simulation data and actual recorded data verify the high recognition accuracy and strong anti-noise performance of the hybrid model. Compared with the traditional methods, the hybrid model also has good generalisation ability and can be effectively applied in practical engineering.
Summary
The fading characteristics of 60 Ah decommissioned electric vehicle battery modules were assessed employing capacity calibration, electrochemical impedance spectroscopy, and voltage measurement of parallel bricks inside modules. The correlation between capacity and internal resistance or voltage was analyzed. Then, 10 consistent retired modules were packed and configured in a photovoltaic (PV) power station to verify the practicability of their photovoltaic energy storage application. The results show that the capacity attenuation of most retired modules is not severe in a pack while minor modules with state of health (SOH) less than 80% bring about the retirement of the whole pack as a result of the buckets effect. There is no obvious correlation between capacities of retired battery modules and their lithium‐ion diffusion coefficients or charge transfer resistance or ohmic resistance, whose reliability is low as the consistency indexes of decommissioning battery modules. The maximum off load voltage difference ΔUmax at low state of charge (SOC) values has a good negative linear correlation with the capacity of retired modules, suggesting that the ΔUmax value at low SOC values can be considered as a characteristic index for fast classification of retired battery modules for large‐scale second‐life application. A PV power station equipped with retired battery energy storage system (RBESS) can maximize the photovoltaic self‐utilization rate. It is an important way to reutilization of retired battery that RBESSs are configured with distributed PV power stations.
Properly deployed public charging stations are important foundations for the large-scale operation of electric taxis. This paper proposes a novel framework for the deployment of public charging stations, which takes into consideration the effects of passengers, taxi drivers, electricity retailers, transportation network, distribution network, and power consumers. First, on the premise that public charging stations have already been deployed, an agent-based model is constructed to simulate the charging demands of each station, considering passengers' travel demands and retailers' mutual competition. Second, to obtain candidate sites for public charging stations, the critical node index is put forward based on the massive trajectory data of taxis. Finally, a multi-objective optimizing model for public charging station deployment is proposed with charging demand simulation embedded. By traversing candidate sites and quantities of charging spots at each station using a modified genetic algorithm, the optimal deployment results are obtained. The framework and models are demonstrated and verified by a test case. The results indicate that the proposed framework could minimize the costs of charging stations, electric utilities, electric taxi drivers, and passengers while lowering the load heterogeneity in the distribution network at the same time. INDEX TERMS Electric taxi, load heterogeneity, multi-agent simulation, pricing strategy, public charging station planning, trajectory data mining.
Energy reforms advance development of human civilizations. As environmental problems go increasingly severe, hydrogen energy which is featured by zero carbon emissions, high efficiency, easy storage and other advantages has won attention from researchers from around the world. China has rich hydrogen energy, and in the next energy reform, hydrogen will play an important role. This paper will introduce the application of hydrogen energy in industries, fuel-driven and electric cars, hydrogen storage and heat-power joint production in hybrid energy systems as well as the current development conditions. Typical study cases from different countries have been analyzed and interpreted. On that basis, the problems and bottlenecks for development of hydrogen energy in China are concluded.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.