.png){kind=icon}
返回
Versatile Cloud Resource Scheduling Based on Artificial Intelligence in Cloud-Enabled Fog Computing Environments
.png){kind=icon}
PRE
AI
DOI：10.22967/HCIS.2023.13.054.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In order to meet the ubiquitous requirements of cloud computing users (real-time, low energy cost, and quick response time), fog computing has widely been used as a viable alternative for the central cloud computing system, which supports real-time applications of the Internet of Things (IoT) and the industrial IoT. In cloud enabled fog computing environments, however, the efficient management and scheduling of cloud resources (hosts, virtual machines, and containers) are not trivial tasks due to limited processing, storage, and network capabilities compared to the central cloud computing system. Heuristic algorithms or artificial intelligence techniques can be used to overcome these constraints. However, implementing cloud resource scheduling based on heuristic algorithms does not guarantee the optimal solution and often introduces unavoidable errors and performance degradation. Hence, we adopt artificial intelligence techniques to the cloud resource and task scheduling problems. Existing studies using artificial intelligence techniques have potential barriers to achieving cloud users' ubiquitous requirements for IoT applications. In this paper, we propose a versatile cloud resource scheduling method based on artificial intelligence in cloud-enabled fog computing environments, which supports multi-user requirements. The proposed resource and task schedulers are able to deal with dynamic workloads effectively in heterogeneous environments. Performance results show that the proposed cloud resource and task schedulers outperform the state-of-the-art studies while meeting cloud users' requirements and service-level objectives.
Keyword:
Cloud Computing
Fog Computing
Edge Computing
Artificial Intelligence
Resource Management
Task
Scheduling
期刊
IF:
3
论文数:
555
被引数:
1.4K
机构
引用论文
暂无论文信息