The use of fog computing in the Internet of Things(IoT)has emerged as a crucial solution,bringing cloud services closer to end users to process large amounts of data generated within the system.Despite its advantages,...The use of fog computing in the Internet of Things(IoT)has emerged as a crucial solution,bringing cloud services closer to end users to process large amounts of data generated within the system.Despite its advantages,the increasing task demands from IoT objects often overload fog devices with limited resources,resulting in system delays,high network usage,and increased energy consumption.One of the major challenges in fog computing for IoT applications is the efficient deployment of services between fog clouds.To address this challenge,we propose a novel Optimal Foraging Algorithm(OFA)for task placement on appropriate fog devices,taking into account the limited resources of each fog node.The OFA algorithm optimizes task sharing between fog devices by evaluating incoming task requests based on their types and allocating the services to the most suitable fog nodes.In our study,we compare the performance of the OFA algorithm with two other popular algorithms:Genetic Algorithm(GA)and Randomized Search Algorithm(RA).Through extensive simulation experiments,our findings demonstrate significant improvements achieved by the OFA algorithm.Specifically,it leads to up to 39.06%reduction in energy consumption for the Elektroensefalografi(EEG)application,up to 25.86%decrease in CPU utilization for the Intelligent surveillance through distributed camera networks(DCNS)application,up to 57.94%reduction in network utilization,and up to 23.83%improvement in runtime,outperforming other algorithms.As a result,the proposed OFA algorithm enhances the system’s efficiency by effectively allocating incoming task requests to the appropriate fog devices,mitigating the challenges posed by resource limitations and contributing to a more optimized IoT ecosystem.展开更多
文摘The use of fog computing in the Internet of Things(IoT)has emerged as a crucial solution,bringing cloud services closer to end users to process large amounts of data generated within the system.Despite its advantages,the increasing task demands from IoT objects often overload fog devices with limited resources,resulting in system delays,high network usage,and increased energy consumption.One of the major challenges in fog computing for IoT applications is the efficient deployment of services between fog clouds.To address this challenge,we propose a novel Optimal Foraging Algorithm(OFA)for task placement on appropriate fog devices,taking into account the limited resources of each fog node.The OFA algorithm optimizes task sharing between fog devices by evaluating incoming task requests based on their types and allocating the services to the most suitable fog nodes.In our study,we compare the performance of the OFA algorithm with two other popular algorithms:Genetic Algorithm(GA)and Randomized Search Algorithm(RA).Through extensive simulation experiments,our findings demonstrate significant improvements achieved by the OFA algorithm.Specifically,it leads to up to 39.06%reduction in energy consumption for the Elektroensefalografi(EEG)application,up to 25.86%decrease in CPU utilization for the Intelligent surveillance through distributed camera networks(DCNS)application,up to 57.94%reduction in network utilization,and up to 23.83%improvement in runtime,outperforming other algorithms.As a result,the proposed OFA algorithm enhances the system’s efficiency by effectively allocating incoming task requests to the appropriate fog devices,mitigating the challenges posed by resource limitations and contributing to a more optimized IoT ecosystem.
