Abstract
With the continuous evolution of microservice architecture and containerization technology, the challenge of efficiently and reliably scheduling large-scale cloud services has become increasingly prominent. In this paper, we present a cost-optimized scheduling approach with resource configuration for microservice workflows in container environments, taking into account deadline and reliability constraints. We introduce a graph deep learning model (DeepMCC) that automatically configures containers to meet various service quality (QoS) requirements. Additionally, we propose a reliability microservice workflow scheduling algorithm (RMWS), which incorporates heuristic leasing and deployment strategies to ensure reliability while reducing cloud resource leasing cost. Experiments on four scientific workflow datasets show that the proposed approach achieves an average cost reduction of 44.59% compared to existing reliability scheduling algorithms, with improvements of 26.63% in the worst case and 73.72% in the best case.