Search

This paper proposes a reactive power coordination control scheme between voltage source converter based HVDC (VSC-HVDC) system and filter switching of line commutated converter based HVDC (LCC-HVDC) system for a hybrid multi-infeed VSC/LCC HVDC system. The conventional reactive power control strategies of filter switching of LCC-HVDC system and VSC-HVDC system are analyzed, and the limitations of them are pointed out. To reduce the filter switching, a control module is designed for the coordination control scheme. A hybrid multi-infeed system model was built in PSCAD/EMTDC for simulation verification. The simulation results showed that the performance of the reactive power coordinated control is better than that of the reactive power independent control between VSC-HVDC system and LCC-HVDC system.

Intelligent recognition of switch state based on computer vision is one of the important research contents of power intelligence. For solving the problem of low recognition rate under poor imaging environment, this paper presents an improved VGG19 network. There are 3 improved aspects: 1) in the first convolutional layer, the convolution features are extracted from the RGB image and the LBP image of the switch, and then the two convolution features are averaged as the output result of the first convolution layer, in order to enhance the adaptability of features to illumination changes and the ability to extract detailed features; 2) in the subsequent 15 convolution layers, the convolution feature output of each layer is averaged with the original input, and then convolved again, so as to extract detail features by secondary convolution; 3) we selects CReLU instead of ReLU as activation function for reducing the redundancy of the convolution kernel. Experiments show that the new method can greatly improve the performance of switch state recognition.

Compared with traditional substation, smart substations has process layer network, which functions as the secondary circuit of traditional substation protection an d is actually equivalent to relay protection and automatic safety devices. Once an exception occurs in the network traffic of process layer, the reliability, rapidity and agility of relay protection action will be affected instantly. According to the characteristics of network traffic of smart substations, a network traffic prediction model, which is based on improved particle swarm wavelet neural network, is proposed in this paper to assist decision-making for the network performance analysis and prediction, network failures and virus invasion warning of smart substations. Experiments have been carried out and validated the high accuracy and fast convergence of the prediction model, which could improve the accuracy and rapidity of smart substation network traffic prediction and ensure the safe operation of grid.