Scholarlink

<p>The Internet of Things (IoT) has opened its wide spectrum of applications in various fields like Smart health care, Industry 4.0 and even intelligent transportation system. With the growth of the population, data generated by IoT devices grows exponentially every day, causing a scarcity of computing and energy resources. Also, the distance between the IoT devices and the Cloud Data Centres (CDC) is another significant challenge towards supporting high Quality of Service (QoS) to technology-hungry users. Fog Computing (FC) provides a new solution to inherent challenges of traditional cloud-based IoT systems in terms of bandwidth, delay, security and storage mechanisms. To maximize the potential of the fog-based IoT networked applications in attaining low latency, high throughput and better performance, the proposed research article proposes a multi-objective Fog-IoT service placement scheme to optimize important parameters of the QoS such as latency, energy consumption, throughput, as well as cost. The proposed framework uses the Henon Evoked Rhinopithecus Swarm Optimization (HERSOA) model to reach greater performance even in the non-convex nature that continues to exist in the Fog-IoT environment. Comprehensive experimentation was conducted using a Fog simulator with data volumes ranging from 100 to 500&#xa0;MB, thereby analysing the performance of the suggested swarm optimization model concerning average delay time (ADT), packet delivery ratio (PDR), energy (E), and throughput (T). Furthermore, the proposed swarm optimization model is statistically validated against other SOTA models. To prove the excellence of the recommended approach, the achieved QoS parameters have been examined with various cutting-edge swarm models. The outcomes demonstrate that the recommended HERSOA outperforms existing cutting-edge approaches. Experimentation depicts that the recommended model is realistic and effective in optimizing the exact mapping of IoT applications and computing resources using Fog deployment.</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

An enhanced meta-heuristic algorithm for multi-objective Internet of Things (IoT) in Fog environment

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月20日

查看全文
  • G. Prabhakar,
  • Meeravali Shaik

摘要

The Internet of Things (IoT) has opened its wide spectrum of applications in various fields like Smart health care, Industry 4.0 and even intelligent transportation system. With the growth of the population, data generated by IoT devices grows exponentially every day, causing a scarcity of computing and energy resources. Also, the distance between the IoT devices and the Cloud Data Centres (CDC) is another significant challenge towards supporting high Quality of Service (QoS) to technology-hungry users. Fog Computing (FC) provides a new solution to inherent challenges of traditional cloud-based IoT systems in terms of bandwidth, delay, security and storage mechanisms. To maximize the potential of the fog-based IoT networked applications in attaining low latency, high throughput and better performance, the proposed research article proposes a multi-objective Fog-IoT service placement scheme to optimize important parameters of the QoS such as latency, energy consumption, throughput, as well as cost. The proposed framework uses the Henon Evoked Rhinopithecus Swarm Optimization (HERSOA) model to reach greater performance even in the non-convex nature that continues to exist in the Fog-IoT environment. Comprehensive experimentation was conducted using a Fog simulator with data volumes ranging from 100 to 500 MB, thereby analysing the performance of the suggested swarm optimization model concerning average delay time (ADT), packet delivery ratio (PDR), energy (E), and throughput (T). Furthermore, the proposed swarm optimization model is statistically validated against other SOTA models. To prove the excellence of the recommended approach, the achieved QoS parameters have been examined with various cutting-edge swarm models. The outcomes demonstrate that the recommended HERSOA outperforms existing cutting-edge approaches. Experimentation depicts that the recommended model is realistic and effective in optimizing the exact mapping of IoT applications and computing resources using Fog deployment.