作者：Hanna Bogucka Bartosz Kopras Filip Idzikowski Bartosz Bossy Paweł Kryszkiewicz
雾计算允许解决具有严格时间限制的计算量大的问题，即使终端设备的计算资源有限，并且云计算引起的延迟过高。如何在遵守延迟限制的同时节省雾计算所消耗的能量，不仅考虑计算，还考虑通过无线和有线链路的传输？这项工作考察了信息网络的延迟和能耗来源，并讨论了描述各种技术的这些成本的模型。接下来，考虑到在这样一个复杂的系统中可用的各种自由度，以及它们对能量消耗和延迟的影响，讨论了资源分配策略。最后，提出了一种未来分布式、人工智能驱动的资源分配策略，并对其进行了论证。
Fog computing allows computationally-heavy problems with tight timeconstraints to be solved even if end devices have limited computationalresources and latency induced by cloud computing is too high. How can energyconsumed by fog computing be saved while obeying latency constraints andconsidering not only computations but also transmission through wireless andwired links? This work examines the latency and energy consumption sources infog networks and discusses models describing these costs for varioustechnologies. Next, resource allocation strategies are discussed consideringthe various degrees of freedom available in such a complex system, and theirinfluence on energy consumption and latency. Finally, a vision for a futuredistributed, AI-driven resources allocation strategy is presented andjustified.
论文链接：http://arxiv.org/pdf/2303.13493v1
更多计算机论文：http://cspaper.cn/