Scholarlink

<p>The increasing demand of latency-sensitive IoT applications necessitates efficient task mapping in decentralized Fog–Cloud environments. This paper presents Joint Energy-and-Resource–aware Optimization (JointERO), a heuristic-based framework for the Task Mapping Problem (TMP) that jointly minimizes makespan, energy consumption, and resource wastage under heterogeneous Fog–Cloud infrastructures. JointERO employs a two-stage strategy that prioritizes energy-efficient nodes and performs resource-wastage-aware task assignment to achieve balanced CPU–memory utilization and reduced node activation. Pareto-front and weighted-sum analyses are used to study trade-offs among conflicting objectives. The framework is evaluated using iFogSim over CloudSim and compared against state-of-the-art schedulers. Results show that JointERO achieves up to 26% lower makespan, 23% reduced energy consumption, and 17% improved resource utilization, with statistical significance confirmed via ANOVA (p &lt; 0.05). The findings demonstrate the effectiveness of JointERO for energy- and resource-efficient task mapping in dynamic Fog–Cloud systems.</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

A joint energy and resource aware task mapping in fog assisted cloud ecosystems

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月29日

查看全文
  • Suresh Kumar Srichandan,
  • Sudarson Jena,
  • Santosh Kumar Majhi,
  • Kaushik Mishra

摘要

The increasing demand of latency-sensitive IoT applications necessitates efficient task mapping in decentralized Fog–Cloud environments. This paper presents Joint Energy-and-Resource–aware Optimization (JointERO), a heuristic-based framework for the Task Mapping Problem (TMP) that jointly minimizes makespan, energy consumption, and resource wastage under heterogeneous Fog–Cloud infrastructures. JointERO employs a two-stage strategy that prioritizes energy-efficient nodes and performs resource-wastage-aware task assignment to achieve balanced CPU–memory utilization and reduced node activation. Pareto-front and weighted-sum analyses are used to study trade-offs among conflicting objectives. The framework is evaluated using iFogSim over CloudSim and compared against state-of-the-art schedulers. Results show that JointERO achieves up to 26% lower makespan, 23% reduced energy consumption, and 17% improved resource utilization, with statistical significance confirmed via ANOVA (p < 0.05). The findings demonstrate the effectiveness of JointERO for energy- and resource-efficient task mapping in dynamic Fog–Cloud systems.