Abstract
As an important part of power infrastructure, a power monitoring system provides real-time data acquisition, state detection, and remote control of power equipment for the power grid and can deal with sudden anomalies in time. The operation and maintenance of the power monitoring system are very important to ensure the stable operation of power grid. The current mainstream remote operation and maintenance mode has internal threats such as misoperation of operation and maintenance personnel or malicious damage caused by attackers stealing operation and maintenance authority. Meanwhile, the existing operation and maintenance audit has the problems of high human resource cost and limited supervision of operation and maintenance personnel. To solve this problem, this paper proposes a collaborative filtering method for operation and maintenance behavior of power monitoring system called CFomb. Exploiting a keyword matching algorithm, CFomb determines the power resources accessed by operation and maintenance users from multiple operation instructions and extracts operation and maintenance behaviors. Referring to the collaborative filtering idea, the feature matrix decomposition scheme is introduced to train the access probability model based on the historical normal behavior of multiple operation and maintenance users, which provides a basis for real-time prediction of the access behavior probability of target operation and maintenance users. The OTSU binarization technique is used to determine the probability threshold of abnormal operation and maintenance behaviors, identify abnormal behaviors through threshold comparison, and send real-time alarms to operation and maintenance audit. The simulation experiment results show that the method in this paper can effectively identify the abnormal behavior of operation and maintenance users, reduce the overhead of manual audit, and help improve the power monitoring system’s ability to respond to internal threats of operation and maintenance.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
