Journal of Engineering, Project, and Production Management, 2026, 16(6), 2026-0054
Optimizing Resource Allocation Strategies of Multi-Tenant Cloud Platforms using Reinforce Algorithms
Senior Experimentalist, School of Information Engineering, Nanjing Polytechnic Institute, 188 Xinle Road, Jiangbei New District, Nanjing City, Jiangsu Province, China, E-mail: caoyue198447@126.com
Production Management
Received May 13, 2026; revised June 14, 2026; accepted June 22, 2026
Available online July 2, 2026
Abstract: The resource allocation strategy of multi-tenant cloud platforms lacks adaptability and is difficult to cope with dynamic load changes, resulting in a decrease in system operating efficiency and resource utilization. To improve the overall operating efficiency of the platform. This paper proposes an adaptive resource allocation optimization method based on Reinforce with a baseline, modeling resource scheduling as a sequential decision-making process and directly optimizing the allocation policy via policy gradient learning. Unlike value-function-based schedulers, the proposed method learns continuous resource allocation policies that jointly optimize throughput, response latency, and resource utilization, aligning policy optimization directly with operational efficiency objectives. Simulation-based evaluation results show that during the heavy load phase, the method achieves a resource utilization rate of 92.8%, reduces the average system response time to 1.38s, and increases the peak throughput to 483 tasks per second compared with traditional strategies.
Keywords: Cloud resource allocation; Reinforce algorithm; policy gradient optimization; multi-tenant architecture; adaptive scheduling strategy.
Copyright © Journal of Engineering, Project, and Production Management (EPPM-Journal).
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License.
Requests for reprints and permissions at eppm.journal@gmail.com.
Citation: Cao, Y. (2026). Optimizing Resource Allocation Strategies of Multi-Tenant Cloud Platforms using Reinforce Algorithms. Journal of Engineering, Project, and Production Management, 16(6), 2026-0054.
