According to the situation of power production safety and existing problems, this paper proposed a security intelligent monitoring solution for power grid based on Internet of things. The solution integrates the perception, communication and analysis technologies with the characteristics of the Internet of things. In the field, intelligent mobile terminals, intelligent security tools and other multi-source sensing equipment are used for on-site safety monitoring information collection, and data communication is realized by integrated application of 4G and narrowband Internet of things (NB-IoT). On this basis, cloud computing and edge computing are used to jointly analyse and evaluate security risk big data.
With the increasing demand for data, mobile operator face the challenge of resource reuse and cost reduction, while also needing to improve network performance and support dynamic scaling. In this paper, we propose a Virtualized Network Function (VNF) scaling ratio prediction model based on an additional momentum BP neural network to optimize the performance of VNF instances in the context of public cloud Network Function Virtualization (NFV) scenarios. We model performance monitoring data and optimize the BP neural network model using the additional momentum method, resulting in specific VNF scaling strategies. The results show that the additional momentum BP neural network is highly effective in predicting the number of VNF scaling instances, with an error rate of only 0.0009 and an accuracy of 98%. Compared to the unimproved model, the additional momentum method leads to smaller errors and notable improvements in both convergence speed and accuracy.
Preprocessing the data stored in the smart grid cloud platform can greatly improve the quality of the data, thereby improving the efficiency of data analysis. Based on the distributed architecture of cloud computing, this paper uses the improved GMM model to design a power grid data preprocessing method. This method first builds a smart grid cloud platform based on the cloud computing architecture. Then perform data cleaning on the stored grid data on the cloud platform. Finally, the improved GMM model is used to classify and store the grid data to complete the preprocessing of the data. Finally, the effect of this method is verified through experiment.