In recent times, fog computing becomes an emerging technology that can exhilarate the cloud services towards the network edge for increasing the speeds up of various Internet-of-Things (IoT) applications. In this context, integrating priority-aware scheduling and data offloading allow the service providers to efficiently handle a large number of real-time IoT applications and enhance the capability of the fog networks. But the energy consumption has become skyrocketing, and it gravely affects the performance of the fog networks. To address this issue, in this paper, we introduce an Energy-Efficient Task Offloading (EETO) policy combined with a hierarchical fog network for handling energy-performance trade-off by jointly scheduling and offloading the real-time IoT applications. To achieve this objective, we formulate a heuristic technique for assigning a priority on each incoming task and formulate a stochastic-aware data offloading issue with an efficient virtual queue stability approach, namely the Lyapunov optimization technique. The proposed technique utilizes the current state information for minimizing the queue waiting time and overall energy consumption while meeting drift-plus-penalty. Furthermore, a constraint restricted progressive online task offloading policy is incurred to mitigate the backlog tasks of the queues. Extensive simulation with various Quality-of-Service (QoS) parameters signifies that the proposed EETO mechanism performs better and saves about 23.79% of the energy usage as compared to the existing ones.

中文翻译：

---

雾网络中物联网应用的联合计算卸载和调度优化

近年来，雾计算成为一种新兴技术，可以将云服务推向网络边缘，以提高各种物联网 (IoT) 应用程序的速度。在这种情况下，集成优先级感知调度和数据卸载使服务提供商能够有效地处理大量实时物联网应用并增强雾网络的能力。但是能耗已经暴涨，严重影响了雾网的性能。为了解决这个问题，在本文中，我们引入了一种节能任务卸载 (EETO) 策略，结合分层雾网络，通过联合调度和卸载实时物联网应用程序来处理能源性能权衡。为了实现这一目标，我们制定了一种启发式技术，用于为每个传入任务分配优先级，并使用有效的虚拟队列稳定性方法（即 Lyapunov 优化技术）制定随机感知数据卸载问题。所提出的技术利用当前状态信息来最小化队列等待时间和整体能耗，同时满足漂移加惩罚。此外，引入了约束限制的渐进式在线任务卸载策略以减轻队列的积压任务。具有各种服务质量 (QoS) 参数的广泛模拟表明，与现有机制相比，所提出的 EETO 机制性能更好，并节省了约 23.79% 的能源使用。