Mobile edge computing provides the radio access networks with cloud computing capabilities to fulfill the requirements of the Internet of Things services such as high reliability and low latency. Offloading services to edge servers can alleviate the storage and computing limitations and prolong the lifetimes of the IoT devices. However, offloading in MEC faces scalability problems due to the massive number of IoT devices. In this article, we present a new integration architecture of the cloud, MEC, and IoT, and propose a lightweight request and admission framework to resolve the scalability problem. Without coordination among devices, the proposed framework can be operated at the IoT devices and computing servers separately, by encapsulating latency requirements in offloading requests. Then a selective offloading scheme is designed to minimize the energy consumption of devices, where the signaling overhead can be further reduced by enabling the devices to be self-nominated or self-denied for offloading. Simulation results show that our proposed selective offloading scheme can satisfy the latency requirements of different services and reduce the energy consumption of IoT devices.

中文翻译：

---

用于绿色物联网的移动边缘计算中的选择性卸载

移动边缘计算为无线电接入网提供了云计算功能，可以满足物联网服务的要求，例如高可靠性和低延迟。将服务卸载到边缘服务器可以减轻存储和计算限制，并延长IoT设备的使用寿命。然而，由于大量的物联网设备，MEC中的卸载面临可扩展性问题。在本文中，我们提出了一种新的云，MEC和IoT集成架构，并提出了一种轻量级的请求和接纳框架来解决可伸缩性问题。在设备之间无需协调的情况下，通过将延迟要求封装在卸载请求中，可以在IoT设备和计算服务器上分别运行建议的框架。然后，设计选择性卸载方案以最小化设备的能量消耗，其中，通过使设备能够自提名或自拒绝进行卸载，可以进一步减少信令开销。仿真结果表明，我们提出的选择性卸载方案可以满足不同服务的时延要求，并降低物联网设备的能耗。