公开(公告)号：US11916755B2

公开(公告)日：2024-02-27

申请号：US17703296

申请日：2022-03-24

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jyotirmoy Karjee ,  Kartik Anand ,  Vanamala Narasimha Bhargav ,  Praveen Naik S ,  Ramesh Babu Venkat Dabbiru ,  Srinidhi N ,  Anshuman Nigam ,  Rishabh Raj Jha

IPC: G06F15/16 ,  H04L41/16 ,  H04L43/0888 ,  H04L67/10

CPC classification number: H04L41/16 ,  H04L43/0888 ,  H04L67/10

Abstract: A method and device for execution of deep neural network (DNN) in an internet of things (IoT) edge network are provided. In an embodiment, at least one edge device within communication range of an IoT device are selected. Further, a network for connecting the IoT device with the at least one selected edge device is identified. A split ratio is determined based on an inference time of the DNN and a transmission time required for transmitting output of each layer of DNN from the IoT device to the selected at least one edge device. Finally, a plurality of layers of the DNN are split into a first part and a second part based on the split ratio, and the second part is transmitted to the selected at least one edge device through the identified network. The first part is executed on the IoT device, and the second part is executed on the selected at least one edge device.