The smart grid in the twenty-first century is constantly innovated by the big data technology and the Internet of Things (IoT) technology. As the second generation of a power network, the smart grid keeps developing towards automation and intelligence, driving the energy conversion rate, power utilization rate, and energy supply rate to increase. However, in the smart grid, the power terminal has a pivotal role in controlling, monitoring, and regulating the production process of electricity, which is currently facing many security challenges. The most critical aspect of smart grid security management is to ensure the security of power terminals. Existing solutions generally monitor power terminal devices by monitoring power terminal traffic; however, such security policies can only monitor attacks with characterization properties at the traffic level and cannot be used to monitor power terminal devices directly. Based on this, this paper reviewed the literature on intelligent operation and maintenance and deep learning at home and abroad and comprehensively analyzed the research progress of intelligent operation and maintenance, and in the comparative analysis of deep learning methods, because the convolutional neural network has fewer connections and parameters and can control the capacity by controlling its depth and width, it is convenient to establish a model with larger learning capacity, so a convolutional neural network is chosen for data analysis. In this study, we choose to use the convolutional neural network to analyze the data, combine the monitoring, management, and fault location of operation and maintenance work organically through some deep learning algorithms, reduce the number of model layers through a deep learning-based security monitoring technology for electric power terminals to improve the training speed and efficiency, and achieve all-round protection for electric power terminals at the device level and the network level. The management of urban smart grid dispatching operation also requires strict implementation of relevant technical standards to ensure the standardized operation and enhance the safety and stability of grid operation.
CITATION STYLE
You, H. (2022). Safe Operation Management of Urban Smart Grid Based on Deep Learning. Mobile Information Systems. Hindawi Limited. https://doi.org/10.1155/2022/4184941
Mendeley helps you to discover research relevant for your work.