Data-driven online anomaly detection device and method for distribution network under multi-hop d2d networking

Abstract

The invention relates to a data-driven on-line abnormality detection device and method for a distribution network under a multi-hop D2D networking. The device includes: a data collection unit for collecting power consumption data measured by a smart meter; a data transmission unit for reporting the collected power consumption data to an edge server through a multi-hop D2D networking for online analysis; The distribution network data analysis unit for real-time analysis of electrical data and the multi-hop D2D network data analysis unit responsible for online traffic monitoring; the decision-making unit, which respectively determines the operating status of the distribution network and multi-hop D2D network in real time according to the results of the data analysis unit. The data-driven on-line abnormality detection method and device for distribution network provided by the present invention can not only save a large amount of computing and storage space, but also improve the abnormality detection speed and have high effectiveness and robustness.

Description

technical field [0001] The invention belongs to the technical field of data analysis, and in particular relates to a data-driven distribution network online anomaly detection device and method under multi-hop D2D networking. Background technique [0002] As an important link in the power network that directly supplies power to users, the operating status of the distribution network directly affects the quality and experience of power users. With the rapid development of social economy, the current power users' requirements for power supply reliability are becoming higher and higher, and fast and efficient anomaly detection methods are one of the important means to ensure power supply reliability. At this stage, with the popularization of smart meters and the upgrading and improvement of the electricity consumption information collection system, the data information of the distribution network has increased dramatically. Although the current distribution network monitoring f...

AI Technical Summary

Problems solved by technology

However, the existing anomaly detection methods based on machine learning all need to store relevant measurement data for a period of time for offline training. This method not only has a slow detection speed but also takes up a large amount of storage space, and cannot locate abnormal power distribution and traffic abnormalities. specific moment

Images