A cyber-physical system (CPS) is a promising paradigm in 5G and future 6G networks that controls physical components through computing and communication while ensuring efficacy, intelligence, and security. The number of smart mobile devices or sensors in smart cities is growing very fast. These devices can process applications in real-time only for a short time due to limited resource capacity. The Mobile Edge Computing (MEC) paradigm is a prominent solution that allows devices to offload intensive tasks and allocate resources. However, the terrestrial MEC servers will be overwhelmed and unable to meet the requirements of 6G technologies for ultra-low-latency applications and mobile devices. Aerial-borne MEC servers have recently supported ultra-reliable, low-latency communication applications and mobile devices in an emergency scenario by providing resources and relaying them to a cloud server. In the intelligent aerial-enabled smart city CPS (S2CPS), decisionmaking tasks such as resource allocation, association, and ensuring trust between links are challenging, and the optimization problem is multi-objective. Therefore, we proposed a hierarchical, deep federated learning-empowered, energy-efficient resource allocation for aerial-enabled S2CPS to minimize the overall energy consumption while considering the quality of service of user devices and the privacy of task offloading in a dynamic environment. We validated the proposed framework through extensive simulations, proving it outperformed the baseline algorithms.