arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.09123cs.LGcs.AI
收藏

资源受限边缘设备的卷积神经网络延迟记忆优化分裂

Latency-Memory Optimized Splitting of Convolution Neural Networks for Resource Constrained Edge Devices

Delhi Technological University(德里理工大学);University of Cambridge(剑桥大学);UQIDAR, IIT Delhi(UQIDAR,印度理工学院德里分校)

Tanmay Jain, Avaneesh, Rohit Verma, Rajeev Shorey

摘要:

随着用户对智能设备的日益依赖,在边缘进行必要的计算已成为任何类型业务的关键要求。许多这样的计算利用卷积神经网络(CNN)来执行AI任务,具有高资源和计算要求,这对于边缘设备是不可行的。拆分CNN架构以在边缘上执行部分计算并保留在云上是一个研究领域,该领域的兴趣越来越大。在本文中,我们断言在边缘设备和云之间运行CNN是解决资源受限优化问题的同义词,该问题可以最大限度地减少延迟并最大限度地提高边缘的资源利用率。我们制定了一个多目标优化问题,并提出了LMOS算法,以实现帕累托有效的解决方案。在真实世界边缘设备上进行的实验表明,LMOS确保了在边缘执行不同的CNN模型,并改进了现有的最先进的方法。

英文摘要:

With the increasing reliance of users on smart devices, bringing essential computation at the edge has become a crucial requirement for any type of business. Many such computations utilize Convolution Neural Networks (CNNs) to perform AI tasks, having high resource and computation requirements, that are infeasible for edge devices. Splitting the CNN architecture to perform part of the computation on edge and remaining on the cloud is an area of research that has seen increasing interest in the field. In this paper, we assert that running CNNs between an edge device and the cloud is synonymous to solving a resource-constrained optimization problem that minimizes the latency and maximizes resource utilization at the edge. We formulate a multi-objective optimization problem and propose the LMOS algorithm to achieve a Pareto efficient solution. Experiments done on real-world edge devices show that, LMOS ensures feasible execution of different CNN models at the edge and also improves upon existing state-of-the-art approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑