Energy-Efficient Complexity-Aware Scheduling in Cloud-Edge Computing

Cloud-edge computing has become a revolutionary paradigm to assist the design of latency-dense and computationintensive applications like Internet of Things (IoT), smart healthcare, autonomous systems, and real-time analytics. Nevertheless, methods of managing workloads, energy efficiency, and computational complexity, as well as the heterogeneity of both cloud and edge resources, create a considerable problem in the task scheduling. The current paper suggests an Energy-Efficient Complexity-Aware Scheduling (EECAS) system in cloud-edge scenarios, which is used to combine forces to minimize energy consumption/ usage, execution time and computational overhead. The suggested model describes the tasks according to the complexity of calculation, time constraints, and the resources used and allocates dynamically to the edge or cloud node with the help of a hybrid optimization strategy. Complexity-sensitive decision engine reduces the redundant offloading and optimizes the distributed resources. The structure is a combination of adaptive workload balancing, energy-aware resource scheduling, and latency-sensitive scheduling to increase overall system performance. The simulation outcomes have shown that the suggested EECAS method contributes to a substantial decrease in total energy consumption and scheduling overhead with the enhancement of the rate of task completion and system throughput in comparison with the traditional methods of scheduling. The model offers a next-generation sustainable and scalable approach to cloud-edge infrastructures to support the emerging real-time and AI-driven workloads.