Dear Bakhit Amine Adoum,

this ETSI document may help you:

ETSI White Paper No. 59:

Enabling Multi-access Edge Computing in Internet-of- Things: how to deploy ETSI MEC and oneM2M; June 2023

https://www.etsi.org/images/files/ETSIWhitePapers/ETSI-WP59-Enabling-Multi-access-Edge-Computing-in-iot.pdf

Best regards

Anatol Badach

Federated meta-learning (FML) is a machine learning technique that allows multiple devices to learn a shared model while keeping their data locally. This is done by transferring the knowledge learned from one device to the others, without actually sharing the data.

FML can be used to enable joint management of resources in the MEC in the following ways:

• Device selection: FML can be used to select a subset of devices to participate in the joint resource management task. This is important because not all devices have the same resources or capabilities. By selecting the right devices, FML can ensure that the joint resource management task is performed efficiently.
• Resource allocation: FML can be used to allocate resources to the different devices participating in the joint resource management task. This is important because different devices may have different needs for resources. By allocating resources in a way that is fair and efficient, FML can help to ensure that all devices are able to participate in the task and that the task is completed successfully.
• Task scheduling: FML can be used to schedule tasks to the different devices participating in the joint resource management task. This is important because different tasks may have different resource requirements. By scheduling tasks in a way that is efficient and fair, FML can help to ensure that all tasks are completed on time and that the resources are used in the most optimal way.

In addition to these applications, FML can also be used to enable other types of joint resource management tasks in the MEC, such as load balancing, caching, and security.

Here is a research paper that discusses the use of FML for joint resource management in the MEC:

• Federated Meta-Learning for Joint Resource Management in Mobile Edge Computing: https://arxiv.org/abs/2205.13892