Scholarlink

<p>The service requirements of the Internet of Things (IoT) are fulfilled by the Fog-Cloud system. Service placement in fog-integrated cloud environment is NP-class problem due to dynamism in resource availability and workload. In recent, Deep Reinforcement Learning (DRL) algorithms have gained popularity for addressing service scheduling problems due to their adaptability to the dynamic environment. This work proposes a DRL-based Twin Delayed Deep Deterministic Policy Gradient (TD3) model for service offloading in a fog-integrated cloud. While the standard TD3 model exhibits certain limitations, this work addresses those by incorporating few key enhancements. Additionally, Transfer Learning (TL) is applied to minimize the computational complexity of multi-agent based TD3 model. The proposed model has been simulated in Python platform using Google trace-2019 data. The efficacy is measured on various Quality of Service (QoS) metrics such as latency, energy, computing cost, and deadline violation, where it produces on average 14% 12%, 16%, and 1.5% better results respectively as compared to state-of-art models.</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 Self-learning Approach for Service Offloading in Heterogeneous Fog-Integrated Cloud System

  • 期刊论文

  • 发表日期：

    2025年6月4日

查看全文
  • Supriya Singh,
  • Deo Prakash Vidyarthi

摘要

The service requirements of the Internet of Things (IoT) are fulfilled by the Fog-Cloud system. Service placement in fog-integrated cloud environment is NP-class problem due to dynamism in resource availability and workload. In recent, Deep Reinforcement Learning (DRL) algorithms have gained popularity for addressing service scheduling problems due to their adaptability to the dynamic environment. This work proposes a DRL-based Twin Delayed Deep Deterministic Policy Gradient (TD3) model for service offloading in a fog-integrated cloud. While the standard TD3 model exhibits certain limitations, this work addresses those by incorporating few key enhancements. Additionally, Transfer Learning (TL) is applied to minimize the computational complexity of multi-agent based TD3 model. The proposed model has been simulated in Python platform using Google trace-2019 data. The efficacy is measured on various Quality of Service (QoS) metrics such as latency, energy, computing cost, and deadline violation, where it produces on average 14% 12%, 16%, and 1.5% better results respectively as compared to state-of-art models.