Scholarlink

<p>The rapid growth of Internet of Healthcare Things (IoHT) applications has led to a surge of healthcare data, demanding efficient and intelligent placement strategies across cloud-fog infrastructures. Fog computing extends cloud capabilities to the network edge, enabling low-latency services for critical IoHT systems. Nevertheless, real-time data accessibility remains a major challenge owing to limited fog resources, dynamic device mobility, and the need for timely response. To address these challenges, this paper introduces an innovative Hybrid Classical-Fuzzy Heuristic (HCFH) protocol aimed at optimizing real-time data placement in cloud-fog environments. HCFH combines two fuzzy inference systems with classical heuristics to handle layer selection (fog vs. cloud), domain selection, data replication, removal, and mobility-aware placement. To boost adaptability, an evolutionary tuning mechanism is introduced based on a genetic algorithm, automatically adjusting heuristic parameters according to time-dependent network conditions and application-specific quality-of-service (QoS) requirements. The optimization process considers multiple objectives, including resource utilization, load balancing, data availability, response time, and energy efficiency. Simulation findings across varying network topologies and application scenarios indicated that the proposed HCFH protocol significantly outperformed state-of-the-art heuristic and metaheuristic approaches—achieving up to 28% reduction in mean response time, 22% improvement in service acceptance rate, and 17% lower energy consumption.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Evolutionary-based hybrid classical-fuzzy heuristic protocol for real-time data availability of IoHT devices in cloud-fog computing

  • 期刊论文

  • 发表日期：

    2025年9月30日

查看全文
  • Zahra Nasiri Aghdam,
  • Ali Rezaee,
  • Amir Masoud Rahmani,
  • Mehdi Hosseinzadeh

摘要

The rapid growth of Internet of Healthcare Things (IoHT) applications has led to a surge of healthcare data, demanding efficient and intelligent placement strategies across cloud-fog infrastructures. Fog computing extends cloud capabilities to the network edge, enabling low-latency services for critical IoHT systems. Nevertheless, real-time data accessibility remains a major challenge owing to limited fog resources, dynamic device mobility, and the need for timely response. To address these challenges, this paper introduces an innovative Hybrid Classical-Fuzzy Heuristic (HCFH) protocol aimed at optimizing real-time data placement in cloud-fog environments. HCFH combines two fuzzy inference systems with classical heuristics to handle layer selection (fog vs. cloud), domain selection, data replication, removal, and mobility-aware placement. To boost adaptability, an evolutionary tuning mechanism is introduced based on a genetic algorithm, automatically adjusting heuristic parameters according to time-dependent network conditions and application-specific quality-of-service (QoS) requirements. The optimization process considers multiple objectives, including resource utilization, load balancing, data availability, response time, and energy efficiency. Simulation findings across varying network topologies and application scenarios indicated that the proposed HCFH protocol significantly outperformed state-of-the-art heuristic and metaheuristic approaches—achieving up to 28% reduction in mean response time, 22% improvement in service acceptance rate, and 17% lower energy consumption.