<scp>SCEN</scp>‐<scp>SCADA</scp> Security: An Enhanced Osprey Optimization‐Based Cyber Attack Detection Model in Supervisory Control and Data Acquisition System Using Serial Cascaded Ensemble Network

ABSTRACT A significant role of Supervisory Control and Data Acquisition (SCADA) systems is to support the operation of the energy system, where Information and Communication Technology (ICT) is utilized to interconnect devices, and this increases the system complexity. The interconnection of SCADA systems increases complexity and the potential for cybersecurity vulnerabilities. In addition, the SCADA networks with legacy devices are affected by inherent cybersecurity deliberation that has provided severe cybersecurity vulnerable points. With the adoption of local‐area networks and Internet Protocol (IP)‐driven proprietary, malicious or unauthorized user accesses the information from outside sources, and hence, the SCADA systems are weakened by the elaborate attacks. SCADA systems need to deliberate the Denial of Service (DoS) and catastrophic failure and maloperation, which may subsequently compromise the safety and stability of the operations in the power system. Therefore, the pertinent priority in SCADA is to strengthen cybersecurity to guarantee reliable operation, and also, the system stability is governed concerning communications integrity. The smart grid features are used in the conventional machine learning approaches for identifying cyber attacks. Hence, implementing an efficient and accurate cyber attack detection approach with less computational overhead is still a crucial research problem in SCADA. So, a novel and secure model for cyber attack detection in the SCADA system using advanced deep learning techniques together with the heuristic algorithm is executed in this research work. The SCADA data are collected from various power grids. The features from these data are optimally selected and fused with the optimal weights to obtain the weighted optimal features. The weighted optimal feature selection is done using the Enhanced Osprey Optimization Algorithm (EOOA). These optimally selected weighted features are given to the Serial Cascaded Ensemble Network (SCEN) to obtain the final detection output. The developed SCEN is made with the cascading of Autoencoder, Dilated Bidirectional Long Short Term Memory (Bi‐LSTM), and Bayesian classifier. The parameters in the SCEN are tuned using the executed IOOA. The final detection of the presence or absence of a cyber attack is evaluated by this SCEN. The performance and the efficiency of the developed framework are confirmed and contrasted by conducting various experiments.