Cloud-network integration integrates cloud computing with space-air-ground-sea communication networks, enabling highly collaborative edge environments. Nevertheless, due to the restricted hardware capabilities of mobile devices and edge servers, energy consumption has become a crucial issue in composite service reconfiguration. We propose an energy-aware multi-objective reconfiguration approach. A clustering mechanism based on service functionality and 3D geographic location reduces the candidate search space. An energy model is then constructed to quantify invocation costs across heterogeneous edge nodes. Combined with QoS attributes, particle swarm optimization is used to generate reconfiguration plans that balance service quality and energy efficiency. The experimental results show that the proposed method reduces energy consumption by an average of 26.7% compared to the baseline approaches, demonstrating superior scalability and performance.