Power measurement system network intrusion detection method based on federated learning framework

Abstract

The invention specifically discloses an electric power metering system network intrusion detection method based on a federated learning framework. The method comprises the following steps: S1, enabling a concentrator to obtain a local model and setting a target; s2, acquiring user electric meter data and sending the user electric meter data to a concentrator to construct a plurality of batches of training samples; s3, enabling each concentrator to download a global model weight parameter from the data center and carrying out training on the global model weight parameter and the selected batch of training samples to obtain a corresponding local model weight parameter; s4, transmitting the local model weight parameters to a data center for aggregation averaging to obtain a next round of global model parameters, feeding back the obtained next round of global model weight parameters to the concentrator, and optimizing respective local model weight parameters; s5, repeating the step S4 to obtain a detection model; and S6, judging whether network intrusion exists in the real-time operation system or not according to the obtained detection model. According to the method, the privacy of the user can be protected, the detection rate can be ensured, and the communication time and computing resources are reduced.

Description

technical field [0001] The invention relates to the technical field of power systems, in particular to a network intrusion detection method for a power metering system based on a federated learning framework. Background technique [0002] The development of smart grid and metering automation makes the data in AMI (Advanced metering infrastructure, advanced metering system) bidirectionally transmitted between users and grid companies. However, due to cost reasons, the power information network often does not have a proprietary communication network but uses a communication network provided by a third-party operator, and there is a potential risk of network attack. Failure to effectively detect and defend against these attacks will affect the data security and operational stability of the power grid. At present, the power grid metering system mainly uses traditional machine learning methods for centralized processing in the data center. During this process, the privacy conten...

AI Technical Summary

Problems solved by technology

[0004] In summary, there are obvious hidden dangers in the power metering system. Therefore, it is a technical problem to be solved by those skilled in the art to study a network intrusion detection method for power metering systems that ensures user data privacy and detects external malicious attacks.

Images