arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.10399eess.SP
收藏

在无线边缘进行节能分类,并保证可靠性

Energy-Efficient Classification at the Wireless Edge with Reliability Guarantees

Mattia Merluzzi, Claudio Battiloro, Paolo Di Lorenzo, Emilio Calvanese Strinati

摘要:

从多个角度来看,边缘学习是一项具有挑战性的任务,因为数据必须由终端设备(例如传感器)收集,可能进行预处理(例如数据压缩),并最终远程处理以输出训练和/或推理阶段的结果。这涉及异构资源,例如无线电、计算和学习相关参数。在这种情况下,我们提出了一种算法,动态地选择数据编码方案,本地计算资源,上行链路无线电参数,和远程计算资源,以执行分类任务的最小平均终端设备的能量消耗,下E2 E延迟和推理可靠性的约束。我们的方法不假设任何先验知识的统计随时间变化的上下文参数,而它只需要解决低复杂度的每槽确定性优化问题,基于这些参数的瞬时观测值和适当定义的状态变量。基于卷积神经网络的图像分类的数值结果说明了我们的方法在能量,延迟和推理可靠性之间取得最佳平衡的有效性。

英文摘要:

Learning at the edge is a challenging task from several perspectives, since data must be collected by end devices (e.g. sensors), possibly pre-processed (e.g. data compression), and finally processed remotely to output the result of training and/or inference phases. This involves heterogeneous resources, such as radio, computing and learning related parameters. In this context, we propose an algorithm that dynamically selects data encoding scheme, local computing resources, uplink radio parameters, and remote computing resources, to perform a classification task with the minimum average end devices' energy consumption, under E2E delay and inference reliability constraints. Our method does not assume any prior knowledge of the statistics of time varying context parameters, while it only requires the solution of low complexity per-slot deterministic optimization problems, based on instantaneous observations of these parameters and that of properly defined state variables. Numerical results on convolutional neural network based image classification illustrate the effectiveness of our method in striking the best trade-off between energy, delay and inference reliability.

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。

↑