Habibi Mohammad Reza, Guerrero Josep M, Vasquez Juan C
AAU Energy, Aalborg University, Aalborg, Denmark.
Department of Electronic Engineering, Center for Research on Microgrids (CROM), Technical University of Catalonia, Barcelona, Spain.
Sci Rep. 2024 Sep 27;14(1):22072. doi: 10.1038/s41598-024-72286-2.
Power electronic converters are widely implemented in many types of power applications such as microgrids. Power converters can make a physical connection between the power resources and the power application. To control a power converter, required data such as the voltage and the current of that should be measured to be used in a control application. Therefore, a communication-based structure including sensors and communication links can be used to measure the desired data and transmit that to the controllers. So, a power converter-based system can be considered as a type of cyber-physical system, and it can be vulnerable to cyber-attacks. Then, it can strongly be recommended to use a strategy for a power converter-based system to monitor the system and identify the existence of cyber-attack in the system. In this study, artificial intelligence (AI) is deployed to calculate the value of the false data (i.e., constant false data, and time-varying false data) and detect false data injection cyber-attacks on power converters. Besides, to have a precise technical evaluation of the proposed methodology, that is evaluated under other issues, i.e., noise, and communication link delay. In the case of noise, the proposed strategy is examined under noises with different signal-to-noise ratios . Further, for the case of the communication delay, the system is examined under both symmetrical (i.e., same communication delay on all inputs) and unsymmetrical communication delays (i.e., different communication delay/delays on the inputs). In this work, artificial neural networks are implemented as the AI-based application, and two types of the networks, i.e., feedforward (as a basic type) and long short-term memory (LSTM)-based network as a more complex network are tested. Finally, three important AI-based techniques (regression, classification, and clustering) are examined. Based on the obtained results, this work can properly identify and calculate the false data in the system.
电力电子变换器广泛应用于多种电力应用中，如微电网。电力变换器可在电源与电力应用之间建立物理连接。为了控制电力变换器，需要测量诸如其电压和电流等所需数据，以便用于控制应用。因此，可使用包括传感器和通信链路的基于通信的结构来测量所需数据并将其传输给控制器。所以，基于电力变换器的系统可被视为一种信息物理系统，并且它可能容易受到网络攻击。那么，强烈建议对基于电力变换器的系统使用一种策略来监测系统并识别系统中是否存在网络攻击。在本研究中，部署人工智能（AI）来计算虚假数据的值（即恒定虚假数据和时变虚假数据）并检测对电力变换器的虚假数据注入网络攻击。此外，为了对所提出的方法进行精确的技术评估，在其他问题（即噪声和通信链路延迟）下对其进行评估。在噪声情况下，在所提出的策略在具有不同信噪比的噪声下进行检验。此外，对于通信延迟情况，在对称（即所有输入上的通信延迟相同）和非对称通信延迟（即输入上的通信延迟不同）两种情况下对系统进行检验。在这项工作中，实现了人工神经网络作为基于AI的应用，并测试了两种类型的网络，即前馈网络（作为基本类型）和基于长短期记忆（LSTM）的网络（作为更复杂的网络）。最后，检验了三种重要的基于AI的技术（回归、分类和聚类）。基于所得结果，这项工作能够正确识别和计算系统中的虚假数据。
