Search

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.

Energy Internet has been considered as a promising alternative to the traditional power grid. In order to improve the energy efficiency of an Energy Internet, energy routers are treated as a significant power conversion device to increase the penetration of renewable sources. Different from previous studies which only consider the shortest path for energy routers, a virtual energy routing strategy involving renewable energy integration is proposed in this paper to reduce the network loss, considering both transmission and conversion efficiency. To address above, the discrete particle swarm optimization (DPSO) algorithm is studied and applied. The effectiveness of the proposed virtual energy routing strategy is validated by an Energy Internet platform integrated with photovoltaic (PV) generation and energy-storage.

this paper proposed a method of monitoring typical load and analyzing load composition using disturbance data of substation. Firstly, correlation analysis method is used to analyze the correlation between substation power quality index fluctuation and user switching equipment, typical users with positive correlation will be screened out. Then, the harmonic index feature library of typical users is established by hierarchical clustering, and the monitoring of typical users is realized by using Bayesian classifier. Finally, the validity of the method is verified by real data.