A method and device for allocating edge computing tasks based on deep neural network
A deep neural network and edge computing technology, applied in the computer field, can solve problems such as latency and privacy issues, and insufficient computing performance, so as to achieve full utilization, avoid computing bottlenecks, and improve processing efficiency.
Active Publication Date: 2021-06-25
中科大数据研究院
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In the face of neural network reasoning tasks, although the edge computing delay is low enough, its overall computing performance is not high enough, and the computing power of cloud servers is strong enough, but uncontrollable delay and privacy issues have become the biggest hidden dangers
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0100] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0101] The terminology used in the present invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein and in the appended claims, the singular forms "a", "the", and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It should also be understood that the term "and / or" as used herein refers to and includes any and all possible combinations o...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present invention provides a method for allocating edge computing tasks based on a deep neural network, the steps of which include: obtaining parameter quantity data, respectively calculating the parameter quantity of the network layer to be calculated in the neural network; obtaining the calculation quantity data, according to the network to be calculated According to the parameter quantity of the layer, the calculation data is obtained; the calculation task is allocated, and the calculation task of the terminal device is obtained according to the calculation data; the calculation task of the edge server is obtained according to the calculation task of the terminal device; and it is judged whether the remaining calculation tasks need to be performed on the cloud server. In addition, the present invention also provides an edge computing task distribution device and storage medium based on a deep neural network, which can fully consider the real-time remaining computing resources of each layer of equipment, and calculate the parameters and computing resources of each layer on this basis. The corresponding deployment plan can be obtained to realize the full utilization of the computing power of each layer of equipment.
Description
Technical field: [0001] The present invention relates to the field of computer technology, in particular to a method and device for allocating edge computing tasks based on a deep neural network. Background technique: [0002] In recent years, artificial intelligence has made great progress, and its application has gradually penetrated into life with the maturity of related technologies. As a commonly used method in artificial intelligence, neural network has good performance (accuracy, etc.), but its training and derivation require a lot of calculation. Under the edge computing framework, as far as a single terminal device is concerned, It is difficult to quickly complete training or get inference (one-time execution) results. Especially the convolutional neural network (CNN), due to its large number of parameters and large demand for inference computing resources, it is difficult for general terminal devices to quickly obtain inference results. [0003] Distributed techn...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F9/48G06F9/50G06N3/04G06N3/08
CPCG06F9/4881G06F9/5016G06F9/5027G06F9/5072G06N3/084G06N3/045
Inventor 王煜炜李叙晶孙胜刘敏王元卓
Owner 中科大数据研究院