With the rapid development of artificial intelligence technology (AIT) and communication technology, China's traditional power grid (TPG) is developing in the direction of smart grid (SG). The application of power Internet of things based on Internet of things in SG is the proof of the development of information technology to a certain level. The main function of China's power grid is to monitor the daily operation of power consumption, collect and integrate the power consumption data of each household. However, with the rapid development of the current society, a large number of power consumption data makes the TPG start to operate under load, so the SG comes into being. After the reasonable operation of data collection and integration, how to screen bad data has become a new challenge for power Internet of things. The purpose of this paper is to study the bad data screening algorithm of power Internet of things based on AIT. This paper mainly expounds the types of power Internet of things data classification processing and analysis, and understands its batch processing and analysis, near real-time analysis and stream processing analysis. At the same time, this paper describes the process of data processing screening, analyzes the data screening process and the problems that the algorithm will encounter, makes algorithm analysis for the data screening of power Internet of things, and proves the reliability of the bad data screening algorithm. At the same time, the processing time and efficiency of TPG and SG are analyzed. It is proved that under the same workload, the efficiency of power Internet of things data algorithm based on AIT is much higher than that of TPG. The experimental results show that the working time of the power Internet of things is less than that of the TPG, but the working efficiency is far better than that of the TPG. When processing 500000 pieces of data, the working time of the TPG is 574 seconds, and the working efficiency is 1.52, while the working time of the power Internet of things is 162 seconds, and the working efficiency is 1.12.
Discussion(0)
No comments yet. Be the first to comment.