Method, device and readable storage medium for detecting false data injection attack

Abstract

The present application discloses a method, device and computer-readable storage medium for detecting false data injection attacks. Applied to a three-layer smart grid framework consisting of PMU layer, local aggregation layer, and control layer, the local aggregation layer pre-trains multiple fuzzy neural network models that are independent of each other and are used to detect false data in the aggregated data of the local aggregator; Receive the measurement data and estimated state values ​​sent by each local aggregator and input them into the corresponding fuzzy neural network model to obtain the false data information of each local aggregator; if there is at least one target local aggregator whose false data value is greater than the threshold, then determine the bus Suffering from false data injection attacks; the local aggregator aggregates the measurement data collected by the PMUs in the corresponding area and performs state estimation to obtain the estimated state value, and sends the data to the control layer after the identity legality verification request is passed. This application can effectively resist false data injection to attack the grid and ensure the security of grid communication.

Description

technical field [0001] The present application relates to the technical field of power grid security, in particular to a method, device and computer-readable storage medium for detecting false data injection attacks. Background technique [0002] In a distributed SE (state estimation, state estimation) system, the state estimator executes SE on each branch and bus in a distributed manner. Distributed SE systems support high R / X (resistance / reactance) ratios, low actual measurement availability, better scalability and minimized complexity. When applied to high-voltage direct current (HVDC) systems, distributed SE achieves better performance in smart grids than centralized SE systems, which occupy the high computational overhead and high complexity burden of the control center. [0003] Based on the advantages of distributed SE, the existing technology mostly adopts a three-layer smart grid framework, which includes a PMU layer, a local aggregation layer, and a control layer....

AI Technical Summary

Problems solved by technology

But there are the following problems: First, only the measured values ​​in specific PMUs are reliable in this method

Secondly, if an attacker attacks a specific PMU and modifies its measurement value, the PMU in the protection method may be in a dangerous state, and the state estimation may take a great risk, and it is still unable to effectively resist the false data injection attack. poor communication security

Images