Neural Network-Based Adaptive LFC Approach for Multi-Area Power Systems Vulnerable to Hybrid Attacks

Due to the open communication architecture and the ever-expanding network connections of modern power systems, cybersecurity has become increasingly important. For this reason, this paper tackles the load frequency control (LFC) problem in multi-area power systems (MAPSs) that are vulnerable to both time-constrained denial-of-service (DoS) attacks and unknown false-data-injection (FDI) attacks. First, unlike existing research that relies on randomly generated DoS attacks, this paper proposes a detection algorithm aimed at identifying DoS attacks based on network traffic analysis. Moreover, to address unknown FDI attack, we employ neural networks (NNs) to learn the characteristics of the attack signals and construct an approximation model. Then, an NN-based attack compensation controller is developed to mitigate or eliminate the negative impact of unknown maliciously FDI information on system performance. By carefully constructing Lyapunov functional, the exponential asymptotically stability condition with anH∞performance index is derived under hybrid attacks. We also determined the relationship between the performance index of the compromised LFC system and the minimum allowable sleep time and maximum allowable active time under DoS attacks. Finally, a simulation example is illustrated to substantiate the validity of the proposed approach.