Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Edge end time series prediction method based on improved knowledge distillation ESN

A technology of time series and forecasting methods, applied in forecasting, neural learning methods, data processing applications, etc., can solve problems such as limited forecasting performance, insufficient long-term memory ability, and reduced ESN computing overhead, so as to improve long-term memory ability and reduce computing costs. Overhead, the effect of optimizing the structure of the reserve pool

Pending Publication Date: 2022-07-12
NANJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, while ESN has strong short-term memory ability, its long-term memory ability is slightly insufficient, which limits the further improvement of its prediction performance.
On the other hand, limited by the computing and storage capabilities of edge devices, the computing overhead of ESN needs to be further reduced

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
  • Edge end time series prediction method based on improved knowledge distillation ESN
  • Edge end time series prediction method based on improved knowledge distillation ESN
  • Edge end time series prediction method based on improved knowledge distillation ESN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0075] The technical solutions of the present invention will be further described in detail below with reference to the accompanying drawings.

[0076] Edge-side time series prediction method based on improved Knowledge Distillation (KD) Echo State Network (ESN), refer to figure 1 ,Specific steps are as follows:

[0077] Step 1: Construct a time series prediction model based on improved knowledge distillation ESN, such as figure 2 shown. Specific steps are as follows:

[0078] Step 1-1: Take LSTM as the teacher network and set its parameters. LSTM is responsible for teaching long-term memory ability. It consists of input layer, hidden layer, and output layer. The hidden layer adopts a double-layer structure; the input layer and the hidden layer, the hidden layer and the hidden layer, and the output layer and the hidden layer are fully connected; set The number of neurons in the input layer and output layer of LSTM is K and L respectively; the number of neurons in the firs...

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 end time sequence prediction method based on an improved knowledge distillation ESN, and the method comprises the steps: firstly combining an echo state network ESN with knowledge distillation KD, and constructing a time sequence prediction model based on the improved knowledge distillation ESN; a training algorithm is put forward, the model is trained at a server side, the structure of the reserve pool is optimized, the long-term memory ability of the reserve pool is improved, and the calculation overhead of the reserve pool is reduced; and finally, performing time sequence prediction at the edge end by using the trained time sequence prediction model based on the improved knowledge distillation ESN. According to the method, the long-term memory ability of the reserve pool can be improved, the calculation overhead is reduced, and the ESN is more suitable for being deployed at an edge end to complete a time sequence prediction task.

Description

technical field [0001] The invention belongs to the technical field of computer applications, and in particular relates to an edge-end time series prediction method based on improved knowledge distillation ESN. Background technique [0002] With the advent of the Internet of Everything era and the popularization of wireless network devices, the number of devices at the edge of the network and the data generated have grown rapidly, increasing the workload on the server side. Edge intelligence can allocate computing tasks to the edge end close to the data source, effectively reducing the workload of the server end and improving the data processing speed. However, devices on the edge generally have limited computing and storage capabilities. This limits the application of edge intelligence in specific production practices. [0003] Time series forecasting, by modeling the time series, allows forecasting of time series values ​​in the future. Time series forecasting has alway...

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
IPC IPC(8): G06Q10/04G06Q10/06G06Q50/20G06N3/04G06N3/08
CPCG06Q10/04G06Q10/06393G06Q50/205G06N3/049G06N3/082
Inventor 周剑蒋余文严筱永李鑫李群张伯雷肖甫
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com