Unlock instant, AI-driven research and patent intelligence for your innovation.

A system and method for time series forecasting of Internet of Things based on edge cloud

A prediction system and time series technology, applied in the field of the Internet of Things, to achieve the effect of improving prediction accuracy, low delay, and reducing the number of updates

Active Publication Date: 2022-06-24
莫毓昌
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a system and method for forecasting time series of Internet of Things based on edge cloud, so as to solve the aforementioned problems existing in the prior art

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A system and method for time series forecasting of Internet of Things based on edge cloud

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] In this embodiment, an edge cloud-based IoT time series prediction system is provided, and the prediction system includes:

[0037] Data acquisition terminal; used to collect industrial field data, and transmit the collected industrial field data to the 5G base station through 5G;

[0038] 5G base station; used to receive the industrial field data transmitted by the data acquisition terminal, and transmit the industrial field data to the remote cloud platform through the communication network;

[0039] Industrial control terminal; used to receive industrial control commands sent by the 5G base station, and implement corresponding industrial control according to the industrial control commands;

[0040] Cloud platform; used to train the prediction model according to the received historical industrial field data, obtain the trained prediction model, and transfer the trained prediction model to the edge cloud; construct a new training set based on incremental samples, and ...

Embodiment 2

[0047] like figure 1 As shown, in this embodiment, an edge cloud-based IoT time series prediction method is provided, and the prediction method is implemented by using the prediction system; the prediction method includes the following steps:

[0048] S1. The data collection terminal transmits the collected industrial field data to the 5G base station through 5G;

[0049] S2 and 5G base stations transmit industrial field data to the remote cloud platform through the communication network;

[0050] S3. The cloud platform constructs a training set according to the collected industrial time series data Seq={D1,D2,D3,...,DT};

[0051] S4. The cloud platform uses the training set to train the prediction model, and transmits the standard deviation delta of the prediction error E of the trained prediction model MODEL and the trained prediction model MODEL on the training set to the edge cloud through the communication network;

[0052] S5. The edge cloud uses the trained training m...

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

No PUM Login to View More

Abstract

The invention discloses an edge cloud-based Internet of Things time series prediction system and method. The prediction system includes a data collection terminal, a 5G base station, an industrial control terminal, a cloud platform, and an edge cloud; The historical industrial site data collected by the incoming data collection terminal trains the forecasting model, and passes the trained forecasting model to the edge cloud; the edge cloud is used to receive the trained forecasting model delivered by the cloud platform, and utilize the trained The predictive model predicts the new industrial field data, uses the predicted results to generate industrial control commands, and transmits the industrial control commands to the 5G base station. The advantage is: the prediction model training is separated from the prediction model application, that is, the prediction model training is realized on the remote high-performance cloud platform, and the prediction model application is realized on the edge cloud closer to the industrial control scene, thereby reducing communication costs and Processing delay.

Description

technical field [0001] The invention relates to the technical field of the Internet of Things, in particular to an edge cloud-based Internet of Things time series prediction system and method. Background technique [0002] In the context of 5G, the amount of data is large and there are many computing tasks. If the classical centralized cloud computing method is adopted, due to the long data transmission distance, it will bring a large delay. To this end, an edge cloud technology is proposed, that is, a server is placed in a 5G base station, and an edge cloud is deployed on the server, so as to realize the nearby processing of data and avoid the transmission of massive data to the remote cloud server. The data collected by the IoT data collection device is aggregated to the edge cloud, usually a time series. The edge cloud analyzes the time series and sends control commands to the IoT control device for industrial control. In order to better control the equipment, the edge c...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04L67/12H04L67/125G08C17/02G16Y10/00G16Y40/30
CPCH04L67/12H04L67/125G08C17/02G16Y10/00G16Y40/30
Inventor 莫毓昌
Owner 莫毓昌