Task unloading mechanism under information asymmetry and uncertainty in internet of things fog computing

Abstract

Along with the rapid development of intelligent equipment and computing intensive applications, fog computing becomes a promising solution meeting ever-increasing computing requirements. In particular, at peak times, computing tasks can be offloaded from an overload base station (BS) to a fog server by utilizing computing resources that are not fully utilized on the demand side. However, there aretwo main obstacles that hinder the wide deployment of fog computing in the Internet of Things (IoT), i.e., lack of effective incentive mechanisms and task offload algorithms. In the invention, a taskunloading mechanism under information asymmetry and uncertainty in internet of things fog computing is developed by combining a contract theory with computing intelligence. In the first stage, an effective incentive mechanism is provided, and the server is encouraged to share the remaining computing resources through the contract theory. In the second stage, a distributed task unloading algorithmis provided by utilizing the online learning capability of a multi-arm gambling machine (MAB). Specifically, we propose a fluctuation confidence interval algorithm with distance perception, server occurrence time perception and task attribute perception to minimize long-term delay task unloading.

Description

technical field [0001] The invention belongs to the field of wireless communication, and specifically relates to an optimization algorithm for resource sharing under asymmetric information and task offloading under uncertain information in the fog computing of the Internet of Things. In the scenario, use limited budget to recruit more fog servers for resource sharing; use machine learning to ensure that in scenarios with uncertain information, users can only explore and obtain the best server through local information, so as to obtain the best delay performance . Background technique: [0002] Through the seamless integration of 5G communication and the Internet of Things, various items, including smartphones, tablets, sensors, vehicles and other physical objects, will be interconnected to support the acquisition, processing, and sharing of real-time information. This integration will spur a range of unprecedented applications such as autonomous driving, augmented reality a...

AI Technical Summary

Problems solved by technology

However, in reality, not only the network topology and channel state change over time, but also the computing resources and load of the fog server fluctuate over time

As a result, centralized methods suffer from significant performance degradation once global information is not a priori or evolved over time

Images