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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 
