Enhancing Efficiency and Security in Healthcare IoT: a Novel Approach for Fog Computing Resource Optimization Using TGA-RNN

Abstract

Fog computing, a new computing paradigm that has gained popularity, brings calculations closer to data sources from healthcare facilities. The health care industry is the driving force behind the growth of Internet of Things (IoT) driven Fog computing that improves network performance and efficiency, particularly when it comes to the safe and effective aggregation and transmission of healthcare data. This requires optimizing resource allocation and addressing overflow issues.  This study introduces a novel approach that combines Task Group Aggregation (TGA) with a Recurrent Neural Network (RNN) to assess Quality of Service (QoS) characteristics and detect overloaded servers. The TGA method is utilized to effectively manage data movement to Virtual Machines (VMs), thereby alleviating congestion and improving system stability. Furthermore, it uses Chaotic Fruit Fly Optimization Algorithm (CFOA), a neural computing system, to optimize service and user separation based on individual qualities in the context of secure healthcare data aggregation and transmission within IoT networks. The integration of TGA with CFF enhances the detection of overflow problems within the RNN framework, enabling proactive management of resource allocation. The proposed work is evaluated by using the Java programming language and the results demonstrate the effectiveness of the Fog computing overflow control model in mitigating congestion and optimizing resource scheduling, thereby facilitating the efficient and secure aggregation and transmission of healthcare data within IoT networks.