ENERGY-AWARE RESOURCE SCHEDULING IN GREEN CLOUD COMPUTING ENVIRONMENTS USING REINFORCEMENT LEARNING

Beura Maddukuri Veluri

ENERGY-AWARE RESOURCE SCHEDULING IN GREEN CLOUD COMPUTING ENVIRONMENTS USING REINFORCEMENT LEARNING

Authors

Beura Maddukuri Veluri

Green Cloud Computing Engineer, Malaysia.

Keywords:

Green Cloud Computing, Resource Scheduling, Energy-Aware, Reinforcement Learning, Data Centers, Sustainability, Cloud Environments

Synopsis

Purpose: The study aims to address the growing environmental concerns caused by the rising energy demands of data centers in cloud computing. It investigates the potential of reinforcement learning (RL)-based scheduling to enhance energy efficiency in cloud environments without compromising service quality.

Design/methodology/approach: This research adopts a reinforcement learning approach to energy-aware resource scheduling in cloud computing infrastructures. The model dynamically allocates resources by analyzing real-time factors such as workload variability, energy demand, and environmental conditions, ensuring optimal energy consumption during operations.

Findings: The proposed RL-based scheduling strategy significantly reduces energy usage in data centers while maintaining or improving service-level performance. It enables cloud systems to adapt to changing conditions in real-time, resulting in more efficient and sustainable operations.

Practical implications: The findings demonstrate a practical pathway for cloud service providers to integrate intelligent scheduling mechanisms that reduce operational costs and carbon footprint. This approach can be implemented across various data center architectures to support greener cloud computing practices.

Originality/value: This study contributes to the emerging field of green cloud computing by presenting a novel application of reinforcement learning for energy-aware resource management. It highlights the value of adaptive, intelligent systems in achieving sustainability goals in modern cloud infrastructure.

References

[1] Zhang, Yang, and Jun Li. "Energy-Efficient Resource Management in Cloud Computing: A Survey." Journal of Cloud Computing, vol. 9, no. 1, 2023, pp. 45-60.

[2] Chen, Ming, and Wei Xu. "A Survey of Energy-Aware Scheduling Techniques in Cloud Computing Environments." International Journal of Computer Science and Network Security, vol. 22, no. 8, 2022, pp. 33-47.

[3] Liu, Shuo, and Zhi Wang. "Reinforcement Learning-Based Resource Scheduling for Cloud Data Centers." Journal of Cloud Computing Research, vol. 8, no. 5, 2021, pp. 77-85.

[4] Gummad, V. P. K. (2025). Flex gateway, service mesh, and advanced API management evolution. International Journal of Applied Mathematics, 38(9s), 2199–2206. https://doi.org/10.12732/ijam.v38i9s.1643

[5] Kumar, Arun, and Rajesh Singh. "Green Cloud Computing: Issues and Challenges." International Journal of Cloud Computing and Services Science, vol. 10, no. 4, 2020, pp. 99-115.

[6] Gupta, Sachin, et al. "Energy-Aware Resource Allocation in Cloud Computing: A Review." Journal of Supercomputing, vol. 77, no. 8, 2021, pp. 2144-2167.

[7] Khan, Saeed, et al. "Cloud Resource Management and Scheduling for Energy-Efficiency: A Comprehensive Survey." Journal of Cloud Computing, vol. 11, no. 2, 2022, pp. 98-112.

[8] Yang, Xueqiang, et al. "Dynamic Scheduling and Energy Efficiency in Cloud Computing." International Journal of Cloud Applications and Computing, vol. 11, no. 1, 2023, pp. 45-60.

[9] Bhoi, Partha S., et al. "Energy-Aware Cloud Resource Scheduling Using Machine Learning Techniques." Journal of Computing and Information Technology, vol. 25, no. 4, 2021, pp. 375-389.

[10] Ahmed, Faisal, and Zubair Baig. "Reinforcement Learning Algorithms for Energy-Efficient Scheduling in Cloud Computing." International Journal of Cloud Computing and Services Science, vol. 9, no. 3, 2020, pp. 101-115.

[11] Sharma, Vikash, and Rishabh Agrawal. "Optimized Resource Scheduling for Energy-Efficient Cloud Computing." Cloud Computing and Big Data, vol. 6, no. 2, 2021, pp. 134-148.

[12] Singh, R. K., and Pradeep Kumar. "A Novel Approach to Energy Management in Cloud Data Centers Using Reinforcement Learning." Journal of Cloud Computing: Advances, Systems, and Applications, vol. 12, no. 3, 2020, pp. 60-75.

[13] Ahmed, Shams, et al. "A Comprehensive Review on Energy-Efficient Resource Scheduling in Cloud Environments." International Journal of Cloud Computing and Distributed Systems, vol. 9, no. 4, 2021, pp. 98-112.