Novel cyber-physical architecture for optimal operation of renewable-based smart city considering false data injection attacks: Digital twin technologies for smart city infrastructure management

Smart grid is considered a cyber-physical system, which is a combination of physical devices and computational processes. Since there are lots of interactions between the cyber layer and the physical layer, the operation, management, and security of the entire system are crucial topics that must be taken into account. In this regard, this paper tackles two problems in AC MGs, as a special case of smart cities. Firstly, a framework is proposed to solve the optimal scheduling problem in these systems. In this stage, the optimal management and scheduling of the system are structured and modeled as an optimization problem. The dragonfly is utilized as a powerful optimization technique to solve this optimization problem. It is worth noting that in this paper different renewable energy sources, as well as batteries are considered. Since cyber-attacks are among the greatest threats to the system and can cause disruption and outage in smart grids, in this paper a deep-learning-based method called long short-term memory along with the concept of prediction interval is utilized to develop a cyber-attack detection model for false data injection attacks on smart meters. The proposed cyber-attack detection model is first trained using historical data and then is used in real-time for detection. In order to investigate the effectiveness of the proposed optimal scheduling scheme, the modified IEEE 33-bus test system is utilized. Also, for testing the proposed cyber-attack detection model a real-world dataset is used. The simulation results show the great performance and effectiveness of both proposed methodologies. It should be noted that all model are simulated in digital twin simulator. The novel LSTM-based cyber-attack detection model enhances security in electric grids, demonstrating remarkable accuracy.