Research Area:  Machine Learning
The use of cloud computing for delivering application services over the Internet has gained rapid traction. Since the beginning of the COVID-19 global pandemic, the work from home scheme and increased business presence online have created more demand for computing resources. Many enterprises and organizations are expanding their private data centres and utilizing hybrid or multi-cloud environments for their IT infrastructure. Because of the ever-increasing demand for computing resources, energy consumption and carbon emission have become a pressing issue. Renewable energy sources have been recognized as clean and sustainable alternatives to fossil-fuel based brown energy. However, due to the intermittent nature of availability of renewable energy sources, it brings many challenges to automatically and efficiently schedule tasks under renewable energy constraints and deadlines. Task scheduling with traditional heuristic algorithms are not able to adapt quickly with changing energy availability and stochastic task arrival. In this regard, this work aims at building a novel scheduling policy with deep reinforcement learning, which automatically applies scheduling techniques like workload shifting and cloud -bursting in a geographically distributed hybrid multi-cloud environment consists of multiple private and public clouds. Our primary goals are maximizing renewable energy utilization and avoiding deadline constraint violations. We also introduce user configurable hyper-parameters to enable multi-objective scheduling on cloud cost, makespan and utilization. Our experiment results show that the proposed scheduling approach can achieve the aforementioned objectives dynamically to varying renewable energy availability.
Keywords:  
Author(s) Name:  Jie Zhao; Maria A. Rodriguez; Rajkumar Buyya
Journal name:  IEEE 14th International Conference on Cloud Computing
Conferrence name:  
Publisher name:  IEEE
DOI:  10.1109/CLOUD53861.2021.00037
Volume Information:  
Paper Link:   https://ieeexplore.ieee.org/document/9582195