Design of Resources Allocation in 6G Cybertwin Technology Using the Fuzzy Neuro Model in Healthcare Systems

Area of Science:

• * 6G Wireless Communication and Edge Computing
• * Machine Learning and Neural Networks
• * Healthcare Systems and Bioinformatics

Background:

• * Machine learning in 6G edge networks enables intelligent decision-making for healthcare resource allocation.
• * Sophisticated memory calculations and communication costs between edge devices and cloud centers create bottlenecks.
• * Increasing neural network complexity exacerbates storage and cloud computing demands.

Purpose of the Study:

• * To reduce storage and cloud computing costs associated with complex neural networks in 6G edge healthcare systems.
• * To modify federated learning for distributed resource allocation in edge computing environments.
• * To improve data learning capacity and optimize workload assignment based on resource constraints.

Main Methods:

• * Implementation of a distributed deep learning model using modified federated learning.
• * Integration of cybertwin for autonomous transmission of network status from edge devices to cloud centers.
• * Development of an intelligent workload assignment strategy considering limited resources and network conditions.

Main Results:

• * The proposed method demonstrates superior resource management and allocation compared to standard approaches.
• * Achieved higher resource utilization and success rates in simulations.
• * Effectively addresses challenges of complex memory calculations and data transmission costs.

Conclusions:

• * The modified federated learning approach with cybertwin is effective for 6G edge healthcare systems.
• * Optimized resource allocation leads to improved efficiency and reduced computational overhead.
• * The study provides a scalable solution for intelligent decision-making in resource-constrained edge environments.