Composition of caching and classification in edge computing based on quality optimization for SDN-based IoT...

Area of Science:

• Internet of Things (IoT) in healthcare
• Network optimization
• Data caching strategies

Background:

• E-health systems generate vast amounts of data requiring efficient management.
• Existing network architectures struggle with the latency and bandwidth demands of real-time e-health applications.
• The integration of IoT devices in healthcare necessitates advanced caching and network management solutions.

Purpose of the Study:

• To propose a novel spectral clustering approach for grouping e-health IoT devices.
• To implement an efficient caching mechanism at the Software-Defined Networking (SDN) edge.
• To enhance the Quality of Service (QoS) for e-health applications through optimized resource allocation.

Main Methods:

• Utilizing spectral clustering to group patients based on device data similarity and network proximity.
• Connecting identified clusters to SDN edge nodes for localized data caching.
• Employing the MFO-Edge Caching algorithm for intelligent selection of data for caching.
• Prioritizing emergency and on-demand requests for faster cache response.

Main Results:

• The proposed approach demonstrated superior performance compared to existing methods.
• Achieved a significant decrease in average data retrieval delays.
• Reported a cache hit rate of 76% for prioritized requests.
• Observed a cache hit ratio of 35% for periodic requests, indicating effective resource allocation.

Conclusions:

• The integration of SDN-edge caching and spectral clustering effectively optimizes e-health network resources.
• The MFO-Edge Caching algorithm enhances QoS by reducing latency and improving data accessibility.
• This approach offers a scalable and efficient solution for managing data in e-health IoT environments.