Scholarlink

<p>In smart transportation systems, real-time services and data transmission have been emerged through enhanced vehicular communication, interactions between the infrastructure and vehicles. The modern computing paradigm referred to as fog computing enables advanced services, including augmented reality, autonomous vehicles, and navigation, in order to cope up with vehicular networks for delivering better transportation solutions. This integration leads to the development of fog-enabled Vehicular Ad-Hoc Networks (VANETs) that allow smart vehicles, providing reliable communications over Fog Nodes (FNs) with the help of association policies based on signal strength and/or user-defined preferences. Nevertheless, vehicle overcrowding within the network can lead to load imbalance across FNs, thereby causes a significant decrease in resource utilization efficiency and overall service capability. Therefore, a novel resource management model for VANETs is accurately designed to overcome the challenges faced by traditional approaches. This work implemented a Software-Defined vehicular Fog Computing (SDFC) model and novel optimization technique named Stochastic Position-upgraded Single Candidate Optimizer (SPSCO) to execute the resource allocation and task distribution in the VANET. The SDFC framework for VANET employed an intelligent controller to place the decision-making entities in the network. This framework helps to enhance the resource distribution and data flow. Further, the implemented model performs the optimal resource allocation and task distribution using SPSCO to maximize scalability and minimize the time, resource utilization, and energy consumption. Moreover, the control placement is also performed using SPSCO framework to reduce the communication overheads among the FNs and the controller, and the FNs' response time in clusters. Later, different performance validations are executed in the developed technique over various performance measures to validate its efficiency under different conditions. Here, the developed model’s computational overhead is 0.59&#xa0;min, energy consumption is 0.013&#xa0;J, and execution time is 200&#xa0;s, which is lesser than the other existing frameworks such as Golden Eagle Optimizer, Flamingo Search Algorithm, African Bison Optimization Algorithm and Single Candidate Optimizer, respectively. Thus, the result demonstrated that the proposed framework can boost its effectiveness in improving network performance and reducing latency during data transmission. Moreover, the developed framework guarantees that the tasks are distributed efficiently, enhancing the rate of task completion and minimizing the risk of task failures.</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

Intelligent resource allocation and task distribution framework for vehicular Ad-Hoc networks using multiple constraints with software-defined fog computing technology

  • 期刊论文

  • 发表日期：

    2026年6月1日

查看全文
  • Rayroth Shashank,
  • S. V. Aswin Kumer,
  • P. Jona Innisai Rani,
  • A. Karthikayen,
  • M. Venkatesan,
  • E. Mohan

摘要

In smart transportation systems, real-time services and data transmission have been emerged through enhanced vehicular communication, interactions between the infrastructure and vehicles. The modern computing paradigm referred to as fog computing enables advanced services, including augmented reality, autonomous vehicles, and navigation, in order to cope up with vehicular networks for delivering better transportation solutions. This integration leads to the development of fog-enabled Vehicular Ad-Hoc Networks (VANETs) that allow smart vehicles, providing reliable communications over Fog Nodes (FNs) with the help of association policies based on signal strength and/or user-defined preferences. Nevertheless, vehicle overcrowding within the network can lead to load imbalance across FNs, thereby causes a significant decrease in resource utilization efficiency and overall service capability. Therefore, a novel resource management model for VANETs is accurately designed to overcome the challenges faced by traditional approaches. This work implemented a Software-Defined vehicular Fog Computing (SDFC) model and novel optimization technique named Stochastic Position-upgraded Single Candidate Optimizer (SPSCO) to execute the resource allocation and task distribution in the VANET. The SDFC framework for VANET employed an intelligent controller to place the decision-making entities in the network. This framework helps to enhance the resource distribution and data flow. Further, the implemented model performs the optimal resource allocation and task distribution using SPSCO to maximize scalability and minimize the time, resource utilization, and energy consumption. Moreover, the control placement is also performed using SPSCO framework to reduce the communication overheads among the FNs and the controller, and the FNs' response time in clusters. Later, different performance validations are executed in the developed technique over various performance measures to validate its efficiency under different conditions. Here, the developed model’s computational overhead is 0.59 min, energy consumption is 0.013 J, and execution time is 200 s, which is lesser than the other existing frameworks such as Golden Eagle Optimizer, Flamingo Search Algorithm, African Bison Optimization Algorithm and Single Candidate Optimizer, respectively. Thus, the result demonstrated that the proposed framework can boost its effectiveness in improving network performance and reducing latency during data transmission. Moreover, the developed framework guarantees that the tasks are distributed efficiently, enhancing the rate of task completion and minimizing the risk of task failures.