Research on Resource Scheduling Algorithm Optimization in Cloud Computing Environment Based on Deep Learning

With the rapid advancement of cloud computing technology, user demands for Quality of Service (QoS) are continuously increasing. As a crucial link between user requirements and resource provisioning, resource scheduling has become a key focus in algorithm optimization research. Deep learning, a core technique in artificial intelligence, has been widely adopted to improve the efficiency of resource allocation in cloud computing, enabling intelligent and dynamic solutions. This paper provides a comprehensive review of deep learning-based resource scheduling algorithms, analyzing current progress and identifying existing challenges. It begins by introducing the fundamental concepts of resource scheduling and its pivotal role in maintaining service quality. Common deep learning models and their application scenarios in this domain are summarized. Next, recent research advances are discussed in detail, covering design principles, model training techniques, optimization strategies, and real-world outcomes. The strengths and limitations of various algorithms are compared, with a particular focus on metrics such as real-time responsiveness, accuracy, and computational complexity. Furthermore, this paper explores ongoing challenges, including data imbalance, limited generalization capabilities, constraints in real-time performance, and the need for energy efficiency. Finally, it envisions future research directions, emphasizing the potential of reinforcement learning and transfer learning to address these challenges. It is posited that continuous breakthroughs in deep learning will drive novel approaches for resource scheduling, advancing cloud computing services toward greater intelligence and efficiency.