Energy-Aware Task Offloading in Green Cloud Computing EnvironmentsThrough Reinforcement Learning Based Adaptive Workload Balancing

Sharon Ruth,

Authors

Sharon Ruth, USA Author

Keywords:

Green Cloud Computing, Task Offloading, Reinforcement Learning, Energy Efficiency, Adaptive Load Balancing,, Edge-Cloud Systems, Workload Optimization, Resource Management, Sustainable Computing

Abstract

The rapid adoption of cloud computing has significantly amplified energy consumption, necessitating sustainable and energy-efficient solutions. This paper presents a reinforcement learning-based adaptive workload balancing mechanism tailored for energy-aware task offloading in green cloud computing environments. We analyze how dynamic workload shifts, when guided by intelligent policies, reduce power usage while maintaining service quality. The paper also surveys key contributions made before 2022 and illustrates optimization models, datasets, and visual comparisons of task offloading strategies. The findings highlight that reinforcement learning (RL) algorithms can effectively learn energy-optimal offloading policies under real-time constraints.

References

Kang, K., Ding, D., Xie, H., Yin, Q. (2021). Adaptive DRL-based task scheduling for energy-efficient cloud computing. IEEE Transactions on Services Computing.

Ke, H., Wang, J., Wang, H., Ge, Y. (2019). Joint optimization for IoT offloading with renewable energy awareness. IEEE Access.

Sheta, S.V. (2021). Artificial Intelligence Applications in Behavioral Analysis for Advancing User Experience Design. International Journal of Artificial Intelligence (ISCSITR-IJAI), 2(1), 1–16.

Sellami, B., Hakiri, A., Yahia, S.B., Berthou, P. (2021). Energy-aware task scheduling using DRL in SDN-IoT. Computer Networks.

Manogaran, G., Rawal, B.S., Song, H., Wang, H. (2020). Resource offloading for green IoT. ACM Transactions on Internet Technology.

Sheta, S.V. (2019). The Role and Benefits of Version Control Systems in Collaborative Software Development. Journal of Population Therapeutics and Clinical Pharmacology, 26(3), 61–76. https://doi.org/10.53555/hxn1xq28

Jayanetti, A., Halgamuge, S., Buyya, R. (2022). DRL for energy-efficient scheduling in edge-cloud. Future Generation Computer Systems.

Sheta, S.V. (2021). Security Vulnerabilities in Cloud Environments. Webology, 18(6), 10043–10063.

Liu, Q., Xia, T., Cheng, L. (2021). DRL for load-balancing in IoT edge systems. IEEE Transactions on Parallel and Distributed Systems.

Gamage, T.A., Perera, I. (2020). Review of energy-efficient architectures for edge computing. IJACSA.

Lin, W., Wu, W., Li, K. (2022). Efficient task scheduling via RL in fog-cloud. Cluster Computing.

Navimipour, N.J., Heidari, A., Jamali, M.A.J. (2021). Secure offloading with deep intelligence. Sustainable Computing.

Sheta, S.V. (2022). A Study on Blockchain Interoperability Protocols for Multi-Cloud Ecosystems. International Journal of Information Technology and Electrical Engineering, 11(1), 1–11. https://ssrn.com/abstract=5034149

Abbasi, M., Yaghoobikia, M., Rafiee, M., Jolfaei, A. (2020). Resource allocation in fog-cloud with learning classifier systems. Computer Communications.

Anghel, I., Cioara, T., Salomie, I. (2016). RL-based green cloud load balancing. Advances in High-Performance Computing.

Sheta, S.V. (2020). Enhancing Data Management in Financial Forecasting with Big Data Analytics. International Journal of Computer Engineering and Technology (IJCET), 11(3), 73–84.

Shen, W., Wu, H., Wu, W., Lin, W. (2021). RL-based heterogeneous task scheduling. Cluster Computing.