An Innovative Way of Resource Allocation Methods in 6G Networks in Cybertown Healthcare Systems with Fuzzy Neuro Models

Machine learning models are essential for enabling smart resource allocation decisions in healthcare systems within the framework of 6G edge networks of communications. But complex memory computations between layers that are hidden and the communication overhead during data transfer from care management tools to cloud centres via edge nodes cause a major barrier. In order to overcome these obstacles, task distribution plays a crucial role in mitigating complicated memory calculations and transmission charges. The main goal is to lower the costs of cloud computing and storage for neural networks, especially when the number of hidden layers in a network increases computational complexity. In order to function as a distributed advanced learning model in distributed assignment of environments, this work presents a modification towards federated learning. This modification improves the model's capacity to learn from data and allocates the best workloads in light of constrained resources, sluggish network connections, and an increased quantity of edge devices. Through the use of cybertwin, edge devices / nodes may independently communicate the current state of the network to cloud centres, guaranteeing that local information can be updated regularly for computations involving global data. Comparing this technique of resource management on allocation to conventional ways, simulations show that it is more successful, with greater success rates and resource utilisation. Fuzzy logic, healthcare, computational biology, cybertwin, artificial intelligence, neural networks, and cutting-edge technology are among the main index phrases.