.png){kind=icon}
.png){kind=icon}
Return
Federated serverless cloud approaches: A comprehensive review
.png){kind=icon}
PRE
AI
DOI：10.1016/j.compeleceng.2025.110372.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The rise of serverless computing has transformed cloud services with its on-demand and eventdriven execution models. This paper extends the serverless paradigm through federated serverless clouds, which distribute functions across various domains, alleviating challenges such as vendor lock-in and scalability. We propose a taxonomy of federated serverless cloud approaches, categorized into four distinct methods: Artificial Intelligence (AI)-level, data-level, platform-level, and resource-level approaches. This systematic literature review shows the strengths and weaknesses of each method. We found that AI-level approaches increase learning capabilities and excel in resource efficiency while increasing complexity. Data-level approaches increase data governance and allow processing and analysis to be performed closer to the data source, thereby reducing latency, but suffer from some interoperability issues and difficulty maintaining data consistency and synchronization across multiple servers can be challenging. Platform-level approaches provide scalability, but may lead to vendor lock-in. Resource-level approaches improve scalability, and reduce overall costs, but scheduling and efficiently managing resources across multiple servers can be complex and require robust management strategies. The paper concludes by identifying key challenges and open research directions such as cost, latency, performance and Interoperability, legal issues and regulations in federated environments.
Keywords:
Serverless computing
Federated serverless clouds
Cloud computing
Multi-cloud
Hybrid cloud
Journal
C
IF:
4.9
Papers:
6.7K
Citations:
1.3W