An Efficient Correlation-Based Cache Retrieval Scheme at the Edge for Internet of Things.

Area of Science:

• Computer Science
• Data Science
• Network Engineering

Background:

• Traditional caching mechanisms treat content objects individually, ignoring semantic relationships.
• This is inefficient for Internet of Things (IoT) deployments due to data redundancy and acceptable approximation in applications.
• Existing methods lead to redundant caching and inefficient resource utilization.

Purpose of the Study:

• To propose a novel caching retrieval scheme that incorporates semantic information correlation among content objects.
• To demonstrate the advantages of semantic-aware caching in edge computing environments for IoT data.
• To enhance the efficiency and performance of IoT data caching systems.

Main Methods:

• Developed a caching retrieval scheme considering semantic information correlation between content objects.
• Applied and evaluated the scheme to IoT data caching at the network edge.
• Conducted experiments and analysis to quantify performance improvements.

Main Results:

• Semantic correlated caching significantly improves caching efficiency.
• The proposed method leads to a higher cache hit rate.
• Resource consumption on IoT devices is substantially reduced.

Conclusions:

• Considering semantic correlation in caching is crucial for efficient IoT data management.
• The developed scheme offers a practical solution for optimizing IoT edge caching.
• This approach enhances overall system performance and reduces operational costs.