Reinforcement learning based task scheduling for environmentally sustainable federated cloud computing
Abstract The significant energy consumption within data centers is an essential contributor to global energy consumption and carbon emissions. Therefore, reducing energy consumption and carbon emissions in data centers plays a crucial role in sustainable development. Traditional cloud computing has...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-12-01
|
| Series: | Journal of Cloud Computing: Advances, Systems and Applications |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13677-023-00553-0 |
| _version_ | 1827590321351950336 |
|---|---|
| author | Zhibao Wang Shuaijun Chen Lu Bai Juntao Gao Jinhua Tao Raymond R. Bond Maurice D. Mulvenna |
| author_facet | Zhibao Wang Shuaijun Chen Lu Bai Juntao Gao Jinhua Tao Raymond R. Bond Maurice D. Mulvenna |
| author_sort | Zhibao Wang |
| collection | DOAJ |
| description | Abstract The significant energy consumption within data centers is an essential contributor to global energy consumption and carbon emissions. Therefore, reducing energy consumption and carbon emissions in data centers plays a crucial role in sustainable development. Traditional cloud computing has reached a bottleneck, primarily due to high energy consumption. The emerging federated cloud approach can reduce the energy consumption and carbon emissions of cloud data centers by leveraging the geographical differences of multiple cloud data centers in a federated cloud. In this paper, we propose Eco-friendly Reinforcement Learning in Federated Cloud (ERLFC), a framework that uses reinforcement learning for task scheduling in a federated cloud environment. ERLFC aims to intelligently consider the state of each data center and effectively harness the variations in energy and carbon emission ratios across geographically distributed cloud data centers in the federated cloud. We build ERLFC using Actor-Critic algorithm, which select the appropriate data center to assign a task based on various factors such as energy consumption, cooling method, waiting time of the task, energy type, emission ratio, and total energy consumption of the current cloud data center and the details of the next task. To demonstrate the effectiveness of ERLFC, we conducted simulations based on real-world task execution data, and the results show that ERLFC can effectively reduce energy consumption and emissions during task execution. In comparison to Round Robin, Random, SO, and GJO algorithms, ERLFC achieves respective reductions of 1.09, 1.08, 1.21, and 1.26 times in terms of energy saving and emission reduction. |
| first_indexed | 2024-03-09T01:15:14Z |
| format | Article |
| id | doaj.art-02d992fc9ade4897b2f7c8024a3d0550 |
| institution | Directory Open Access Journal |
| issn | 2192-113X |
| language | English |
| last_indexed | 2024-03-09T01:15:14Z |
| publishDate | 2023-12-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Cloud Computing: Advances, Systems and Applications |
| spelling | doaj.art-02d992fc9ade4897b2f7c8024a3d05502023-12-10T12:31:49ZengSpringerOpenJournal of Cloud Computing: Advances, Systems and Applications2192-113X2023-12-0112111710.1186/s13677-023-00553-0Reinforcement learning based task scheduling for environmentally sustainable federated cloud computingZhibao Wang0Shuaijun Chen1Lu Bai2Juntao Gao3Jinhua Tao4Raymond R. Bond5Maurice D. Mulvenna6School of Computer and Information Technology, Northeast Petroleum UniversitySchool of Computer and Information Technology, Northeast Petroleum UniversitySchool of Electronics, Electrical Engineering and Computer Science, Queen’s University BelfastSchool of Computer and Information Technology, Northeast Petroleum UniversityState Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing Normal UniversitySchool of Computing, Ulster UniversitySchool of Computing, Ulster UniversityAbstract The significant energy consumption within data centers is an essential contributor to global energy consumption and carbon emissions. Therefore, reducing energy consumption and carbon emissions in data centers plays a crucial role in sustainable development. Traditional cloud computing has reached a bottleneck, primarily due to high energy consumption. The emerging federated cloud approach can reduce the energy consumption and carbon emissions of cloud data centers by leveraging the geographical differences of multiple cloud data centers in a federated cloud. In this paper, we propose Eco-friendly Reinforcement Learning in Federated Cloud (ERLFC), a framework that uses reinforcement learning for task scheduling in a federated cloud environment. ERLFC aims to intelligently consider the state of each data center and effectively harness the variations in energy and carbon emission ratios across geographically distributed cloud data centers in the federated cloud. We build ERLFC using Actor-Critic algorithm, which select the appropriate data center to assign a task based on various factors such as energy consumption, cooling method, waiting time of the task, energy type, emission ratio, and total energy consumption of the current cloud data center and the details of the next task. To demonstrate the effectiveness of ERLFC, we conducted simulations based on real-world task execution data, and the results show that ERLFC can effectively reduce energy consumption and emissions during task execution. In comparison to Round Robin, Random, SO, and GJO algorithms, ERLFC achieves respective reductions of 1.09, 1.08, 1.21, and 1.26 times in terms of energy saving and emission reduction.https://doi.org/10.1186/s13677-023-00553-0Cloud computingFederated cloudReinforcement learningEnergy efficiencyCarbon emissionsTask scheduling |
| spellingShingle | Zhibao Wang Shuaijun Chen Lu Bai Juntao Gao Jinhua Tao Raymond R. Bond Maurice D. Mulvenna Reinforcement learning based task scheduling for environmentally sustainable federated cloud computing Journal of Cloud Computing: Advances, Systems and Applications Cloud computing Federated cloud Reinforcement learning Energy efficiency Carbon emissions Task scheduling |
| title | Reinforcement learning based task scheduling for environmentally sustainable federated cloud computing |
| title_full | Reinforcement learning based task scheduling for environmentally sustainable federated cloud computing |
| title_fullStr | Reinforcement learning based task scheduling for environmentally sustainable federated cloud computing |
| title_full_unstemmed | Reinforcement learning based task scheduling for environmentally sustainable federated cloud computing |
| title_short | Reinforcement learning based task scheduling for environmentally sustainable federated cloud computing |
| title_sort | reinforcement learning based task scheduling for environmentally sustainable federated cloud computing |
| topic | Cloud computing Federated cloud Reinforcement learning Energy efficiency Carbon emissions Task scheduling |
| url | https://doi.org/10.1186/s13677-023-00553-0 |
| work_keys_str_mv | AT zhibaowang reinforcementlearningbasedtaskschedulingforenvironmentallysustainablefederatedcloudcomputing AT shuaijunchen reinforcementlearningbasedtaskschedulingforenvironmentallysustainablefederatedcloudcomputing AT lubai reinforcementlearningbasedtaskschedulingforenvironmentallysustainablefederatedcloudcomputing AT juntaogao reinforcementlearningbasedtaskschedulingforenvironmentallysustainablefederatedcloudcomputing AT jinhuatao reinforcementlearningbasedtaskschedulingforenvironmentallysustainablefederatedcloudcomputing AT raymondrbond reinforcementlearningbasedtaskschedulingforenvironmentallysustainablefederatedcloudcomputing AT mauricedmulvenna reinforcementlearningbasedtaskschedulingforenvironmentallysustainablefederatedcloudcomputing |