当前位置: X-MOL 学术IEEE Trans. Parallel Distrib. Syst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Energy-Aware Inference Offloading for DNN-Driven Applications in Mobile Edge Clouds
IEEE Transactions on Parallel and Distributed Systems ( IF 5.6 ) Pub Date : 2021-04-01 , DOI: 10.1109/tpds.2020.3032443
Zichuan Xu , Liqian Zhao , Weifa Liang , Omer F. Rana , Pan Zhou , Qiufen Xia , Wenzheng Xu , Guowei Wu

With increasing focus on Artificial Intelligence (AI) applications, Deep Neural Networks (DNNs) have been successfully used in a number of application areas. As the number of layers and neurons in DNNs increases rapidly, significant computational resources are needed to execute a learned DNN model. This ever-increasing resource demand of DNNs is currently met by large-scale data centers with state-of-the-art GPUs. However, increasing availability of mobile edge computing and 5G technologies provide new possibilities for DNN-driven AI applications, especially where these application make use of data sets that are distributed in different locations. One fundamental process of a DNN-driven application in mobile edge clouds is the adoption of “inferencing” – the process of executing a pre-trained DNN based on newly generated image and video data from mobile devices. We investigate offloading DNN inference requests in a 5G-enabled mobile edge cloud (MEC), with the aim to admit as many inference requests as possible. We propose exact and approximate solutions to the problem of inference offloading in MECs. We also consider dynamic task offloading for inference requests, and devise an online algorithm that can be adapted in real time. The proposed algorithms are evaluated through large-scale simulations and using a real world test-bed implementation. The experimental results demonstrate that the empirical performance of the proposed algorithms outperform their theoretical counterparts and other similar heuristics reported in literature.

中文翻译:

移动边缘云中 DNN 驱动应用程序的能量感知推理卸载

随着对人工智能 (AI) 应用的日益关注,深度神经网络 (DNN) 已成功用于许多应用领域。随着 DNN 中的层数和神经元数量迅速增加,需要大量的计算资源来执行学习的 DNN 模型。DNN 不断增长的资源需求目前由配备最先进 GPU 的大型数据中心满足。然而,移动边缘计算和 5G 技术的可用性不断提高,为 DNN 驱动的 AI 应用程序提供了新的可能性,尤其是在这些应用程序使用分布在不同位置的数据集的情况下。移动边缘云中 DNN 驱动应用程序的一个基本过程是采用“推理”——基于来自移动设备的新生成的图像和视频数据执行预训练 DNN 的过程。我们研究了在支持 5G 的移动边缘云 (MEC) 中卸载 DNN 推理请求,目的是承认尽可能多的推理请求。我们针对 MEC 中的推理卸载问题提出了精确和近似的解决方案。我们还考虑了推理请求的动态任务卸载,并设计了一种可以实时调整的在线算法。所提出的算法通过大规模模拟和使用真实世界的测试台实现进行评估。
更新日期:2021-04-01
down
wechat
bug