Zero-Trust Security Strategy for Renewable Power Plant Clusters Under Integrated Satellite-Terrestrial Networks

The efficient and secure operation of renewable power plant (RPP) clusters in remote areas is supported by reliable communication services offered by integrated satellite-terrestrial networks (ISTNs). Conventional static network boundary is seriously threatened by false data injection attacks (FDIAs) due to the wide attack surface of RPP cluster and open access of ISTNs. Accordingly, this paper proposes a zero-trust security strategy with customizable access control policies against FDIAs in RPP cluster under ISTNs. First, a streamlined lightweight blockchain without a consensus mechanism is utilized to rapidly authenticate and record participating plants’ identities and historically exchanged data in the ledger, forming a dynamic network boundary with enhanced data immutability and traceability. Second, identities and data features of participating plants are extracted and classified by a convolutional neural network (CNN) to enhance detection precision. Last, comprehensive belief scores are calculated by Dempster-Shafer theory, which integrates the designed blockchain and CNN model evaluations, achieving high-precise and timely detection of FDIAs. Simulations and hardware-in-loop experiments are conducted to validate the effectiveness of the proposed strategy in RPP cluster under ISTNs against FDIAs with various operating conditions.