Enhancing Cybersecurity in IIoT Smart Grids: Leveraging HGAMPO for PMU Data Manipulation Detection

The integration of Industrial Internet of Things (IIoT) technology into smart grid systems has resulted in unprecedented advantages in terms of effectiveness and dependability. Nevertheless, this interconnectivity also brings about fresh cybersecurity obstacles, specifically with the identification and prevention of Phasor Measurement Unit (PMU) data manipulation threats. Efficient feature selection is vital in improving the robustness of IIoT smart grids against such attacks. The Hybrid Green Anaconda and Marine Predictor Optimization (HGAMPO) algorithm is a promising strategy for choosing significant features in the detection of manipulation in PMU data. This paper presents a comprehensive examination of PMU data manipulation attacks, emphasises the significance of feature selection, and introduces the HGAMPO algorithm. HGAMPO is a revolutionary approach that combines the Green Anaconda Optimization Algorithm (GAOA) and Marine Predictor Optimization (MPO) to optimise feature subsets. It draws inspiration from nature to provide an innovative solution. The effectiveness of HGAMPO in IIoT smart grid contexts is proved through real-world examples and compared with older approaches. The evaluation metrics and experimental results clearly demonstrate the exceptional performance of HGAMPO in detecting attacks that manipulate PMU data. This article provides an overview of upcoming study areas and the possible influence of HGAMPO on cybersecurity in IIoT smart grids.