No abstract

No abstract

The latest results in Deep Neural Networks (DNNs) have greatly improved the accuracy and performance of a variety of intelligent applications. However, running such computation-intensive DNN-based applications on resource-constrained mobile devices definitely leads to long latency and huge energy consumption. The traditional way is performing DNNs in the central cloud, but it requires significant amounts of data to be transferred to the cloud over the wireless network and also results in long latency. To solve this problem, offloading partial DNN computation to edge clouds has been proposed, to realize the collaborative execution between mobile devices and edge clouds. In addition, the mobility of mobile devices is easily to cause the computation offloading failure. In this paper, we develop a mobility-included DNN partition offloading algorithm (MDPO) to adapt to user’s mobility. The objective of MDPO is minimizing the total latency of completing a DNN job when the mobile user is moving. The MDPO algorithm is suitable for both DNNs with chain topology and graphic topology. We evaluate the performance of our proposed MDPO compared to local-only execution and edge-only execution, experiments show that MDPO significantly reduces the total latency and improves the performance of DNN, and MDPO can adjust well to different network conditions.

With the popularity of IEEE 802.11 based wireless fidelity (Wi-Fi) portable devices, it becomes increasingly significant to support the mobile users carrying Wi-Fi devices to access the Internet of Things (IoT) so that the communications between the mobile users and the smart objects deployed in the IoT stay uninterrupted when the mobile users are in movement. A scheme using Extended Service Set (ESS) -based architecture is presented to implement the proxy mobile IPv6 protocol, i.e., PMIPv6, for IEEE 802.11 infrastructure Wireless Local Area Networks (WLANs). The key signaling packets together with their time sequences for the mobility management in the proposed scheme are proposed. Moreover, the handoff delay in the proposed scheme is derived, through which the performance of the proposed scheme is analyzed. Numerical analysis indicates the proposed scheme considerably outperforms the existing scheme using the Basic Service Set (BSS) -based architecture in terms of handoff delay in the case when the delay between Mobile Access Gateway (MAG) and Local Mobile Anchor (LMA) is relatively large.