Journal of Engineering Research

In the context of multi-department collaboration and big data-driven operations, government cloud platforms face heightened demands for efficient computing resource scheduling and energy consumption control. This paper develops a real-time monitoring and predictive optimization model for dynamic resource scheduling in government cloud platforms. By incorporating task prioritization, node load balancing, and energy consumption feedback mechanisms, the proposed approach enables dynamic allocation of computing, storage, and network resources. Combining multi-objective optimization algorithms with energy consumption constraints, we present a scheduling strategy that balances performance and energy efficiency. Experimental results demonstrate that this strategy significantly reduces overall energy consumption while maintaining service quality, thereby improving resource utilization and platform operational efficiency.

Government cloud platform; Dynamic resource scheduling; Energy consumption optimization; Multi-objective optimization; Load balancing