Edge computing optimization: an enhanced algorithm for efficient caching and latency reduction

Abstract

Digital transformation in the healthcare sector has witnessed a tremendous change in the last few years, which has allowed health care professionals to access and remotely monitor patient status using connected devices. Although digital healthcare is more convenient to patients, saves time and is more cost-effective, it also creates a problem of latency as the processing and storage of data is done on centralized cloud servers. Edge Computing (EC) presents an exciting opportunity as it brings data processing too near the source, and is challenged by limited storage capacity and complex infrastructure. To solve these problems, simulation research is proposed in this paper, called Dove Swarm Optimization-based Edge Caching (DSOA-EC), which combines the edge caching mechanism and swarm intelligence to reduce the latency cost and enhance the Quality of Service (QoS). The DSOA-EC is unique by having an intelligent caching strategy that can dynamically pick the best data point according to set caching criteria and current network conditions. The architecture consists of three layers: device, edge and cloud, each optimized to support data processing and transmission efficiency within the constraints of operational environment. Simulation results demonstrate that the DSOA-EC model significantly outperforms conventional caching protocols, achieving a 92% cache hit rate, 0.22-second sensing delay, 99% data freshness, 0.0021-second data retrieval latency, and energy efficiency of 155 J. The performance demonstrates that the DSOA-EC successfully reduces the latency of buffers and improves the QoS. Here its potential as a scalable, real time edge computing solution to a health care environment is demonstrated. These findings provide strong proof-of-concept evidence, and establish a strong footing in large multi-center trials and real-world application.