Intelligent operation and maintenance data exception detection method and device based on 5G core network

Abstract

The invention discloses an intelligent operation and maintenance data exception detection method and device based on a 5G core network. The operation and maintenance data exception detection method comprises the steps of obtaining time series data of network performance indexes; determining a period length based on a local peak value of the time series data; STL decomposition being carried out according to the period length, and obtaining trend features, period features and random fluctuation features of the time series data; and according to the random fluctuation characteristics, calculatinga data exception interval of the network performance index, and when the network performance index exceeds the data exception interval, determining that the network performance index is data exception. The cycle length is determined by acquiring time series data of network performance indexes, STL decomposition is performed to acquire trend features, cycle features and random fluctuation features, a data exception interval is finally obtained, and when data acquired subsequently in real time falls into the data exception interval, it is indicated that the data is exceptional. The abnormal data is detected by combining artificial intelligence with network performance indexes, so that the operation and maintenance efficiency and quality of the 5G core network are improved.

Description

technical field [0001] The present invention relates to the field of electronic information technology, in particular to a 5G core network-based intelligent operation and maintenance data anomaly detection method and device. Background technique [0002] The core network is located at the center of network data interaction and is mainly responsible for end user mobility management, session management and data transmission. The 4G core network mainly includes MME (Mobility Management Entity), SGW (Serving GateWay, Serving Gateway), PGW (PDN GateWay, PDN Gateway), HSS (Home Subscriber Server) and other network elements. SGW and PGW not only have to process and forward user plane data, but also are responsible for control plane functions such as session management and bearer control. This shortcoming of interleaving the user plane and control plane leads to complex service changes, difficult to optimize efficiency, and difficult deployment and maintenance. The problem. [000...

AI Technical Summary

Problems solved by technology

Most of the early operation and maintenance work was done manually by operation and maintenance personnel. This operation and maintenance mode is not only inefficient, but also consumes a lot of human resources

Limited by human's own physiological limits and limited understanding, it is impossible to continuously provide high-quality operation and maintenance services for large-scale and high-complexity systems, and it is impossible to perform abnormal detection of performance indicators in real time

Images