دانلود رایگان مقاله انگلیسی بهینه سازی منابع در گسترش اینترنت اشیا مبتنی بر مه - نشریه IEEE

Abstract

Internet of Things (IoT) devices are typically deployed in resource (energy, computational capacity) constrained environments. Connecting such devices to the cloud is not practical due to variable network behavior as well as high latency overheads. Fog computing refers to a scalable, distributed computing architecture which moves computational tasks closer to Edge devices or smart gateways. As an example of mobile IoT scenarios, in robotic deployments, computationally intensive tasks such as run time mapping may be performed on peer robots or smart gateways. Most of these computational tasks involve running optimization algorithms inside compute nodes at run time and taking rapid decisions based on results. In this paper, we incorporate optimization libraries within the Robot Operating System (ROS) deployed on robotic sensor–actuators. Using the ROS based simulation environment Gazebo, we demonstrate case-study scenarios for runtime optimization. The use of optimized distributed computations are shown to provide significant improvement in latency and battery saving for large computational loads. The possibility to perform run time optimization opens up a wide range of use-cases in mobile IoT deployments.

VII. Conclusion

IoT deployments with limited computation and energy resources require runtime optimization over multiple parameters. To overcome the limitations of IoT devices in terms of computation power, we use Fog computing, in which computationally intensive tasks are offloaded to Edge/Fog nodes with high computational capacities. In this paper, we have developed a Fog computing architecture for IoT scenarios for cooperative communication between peer nodes. We use ROS to demonstrate our model and integrate NLopt optimization libraries within ROS for deploying optimization algorithms during runtime. We believe that the developed framework, with integration of optimization within ROS, can be used to address wide range of application problems in the IoT world. Significant improvements in latency and battery usage are shown over non-optimal deployment of computations.

In this work, we have performed computations such as Bubble Sorting coordinate data to test our deployment. However, our future work involves extending this work to GMapping and creating a distributed global map in an optimal fashion.