A deep learning computing system and method for cloud-edge computing fusion
A technology of deep learning and edge computing, which is applied in computing, computer components, program control design, etc., can solve the problem that computing and storage cannot be placed in the remote cloud, so as to ensure efficiency, improve execution efficiency, and reduce processing pressure. Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0045] This embodiment proposes a deep learning calculation method based on the integration of cloud and edge computing, which distributes deep learning calculations to the cloud, pipeline, and edge side, and the cloud is responsible for the basic model training of historical data with a large amount of calculation, which is personalized according to the needs of the edge side The model is distributed, and the learned deep learning model is deployed from the cloud to the edge side nodes to complete inference. The edge side continues to feedback the reasoning results, and then uploads to the cloud to continuously optimize the model.
[0046] In this embodiment, the deep learning calculation method of cloud edge computing fusion, the specific implementation process includes:
[0047] Step 1, the cloud (cloud node) generates the deep learning model of the pipeline and the edge side (several edge computing nodes), and sends the deep learning model to the pipeline and the edge side;...
Embodiment 2
[0053] This embodiment proposes a deep learning calculation method based on the integration of cloud and edge computing. On the basis of Embodiment 1, a detailed technical solution for step 2 is given to further improve the execution efficiency of real-time services, and at the same time, this embodiment adds Feasibility and practicality of technical solutions.
[0054] In the second step, the edge side performs reasoning and calculation based on the data collected by the intelligent sensor device, and combines the training set data according to the user feedback information and the reasoned original data; the specific implementation process is as follows:
[0055] Step 1. The intelligent sensing device collects environmental data from the outside world in real time;
[0056] Step 2. The smart sensor device sends the collected data to the edge side for reasoning;
[0057] Step 3. Perform inference calculation on the edge side;
[0058] Specifically, the edge side detects whe...
Embodiment 3
[0064] This embodiment proposes a deep learning calculation method based on the integration of cloud and edge computing. On the basis of Embodiment 1, a detailed technical solution for Step 1 and Step 3 is given, and data is uploaded during the idle bandwidth period to ensure that the network Transmission efficiency improves network utilization.
[0065] In the first step, the cloud (cloud node) generates the deep learning model of the pipeline and the edge side (edge computing node), and sends the deep learning model to the pipeline and the edge side; the specific implementation process is as follows:
[0066] Step 1. The cloud uses a large amount of collected historical data for deep learning model training, and finally generates a cloud deep learning model;
[0067] Step 2. The cloud optimizes the model according to the computing and storage capabilities of the application nodes that need to deploy the deep learning model, and generates the deep learning model on the pipe...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More