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

Model training method and device, energy efficiency prediction method and device and storage medium

A model training and model technology, applied in the field of machine learning, can solve the problems of low determination coefficient, easy loss of information, poor accuracy, etc., to achieve the effect of accurate energy consumption efficiency and high prediction accuracy

Pending Publication Date: 2020-03-06
TENCENT TECH (SHENZHEN) CO LTD +1
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] During the research and practice of the prior art, the inventors of the present invention found that, in the existing way of predicting the efficiency of energy consumption, part of the information is easy to be lost in the process of predicting the efficiency of energy consumption, and its decision Coefficients are lower compared to ordinary regression methods, resulting in poor overall forecast accuracy

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
  • Model training method and device, energy efficiency prediction method and device and storage medium
  • Model training method and device, energy efficiency prediction method and device and storage medium
  • Model training method and device, energy efficiency prediction method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0133] The embodiment of the present invention also provides an energy efficiency prediction method, which can be applied to an energy efficiency prediction device, and the energy efficiency prediction device can be integrated in a network device with a memory and a processor installed with computing capability, for example, the network The device can receive the energy consumption efficiency prediction request for the data center; collect the energy consumption efficiency related data of the data center according to the energy consumption efficiency prediction request; call the pre-trained energy usage efficiency prediction model; integrate the energy consumption efficiency related data Input the energy consumption efficiency prediction model for prediction, and obtain the energy consumption efficiency of the data center. Among them, the energy consumption efficiency prediction model is obtained by training using the model training method of the embodiment of the present invent...

Embodiment 3

[0156] In order to better implement the above model training method, an embodiment of the present invention also provides a model training device, which can be specifically integrated in a network device.

[0157] For example, such as Picture 9 As shown, the model training device may include a data acquisition module 401, a sample construction module 402, a model training module 403, a model verification module 404, and a model training module 405, as follows:

[0158] The data acquisition module 401 is used to acquire the historical energy consumption usage efficiency of the data center and acquire corresponding historical energy consumption usage efficiency related data;

[0159] The sample construction module 402 is used to construct a time series training set and a time series test set according to historical energy consumption usage efficiency and historical energy consumption usage efficiency related data;

[0160] The model training module 403 is used to construct a cyclic neur...

Embodiment 4

[0181] In order to better implement the above energy efficiency prediction method, an embodiment of the present invention also provides an energy efficiency prediction device, and the energy efficiency prediction device may specifically be integrated in a network device.

[0182] For example, such as Picture 10 As shown, the energy efficiency prediction device may include a request receiving module 501, a data collection module 502, a model calling module 503, an efficiency prediction module 504, and a issuing module 505, as follows:

[0183] The request receiving module 501 is configured to receive a request for predicting the energy consumption efficiency of the data center;

[0184] The data collection module 502 is configured to obtain data related to the energy consumption efficiency of the data center according to the energy consumption efficiency prediction request;

[0185] The model calling module 503 is used to call a pre-trained energy consumption efficiency prediction mode...

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 embodiment of the invention discloses a model training method and device, an energy efficiency prediction method and device and a storage medium. The model training method comprises the steps: obtaining historical energy consumption use efficiency of a data center, obtaining the corresponding historical energy consumption use efficiency related data, and constructing a time sequence training set and a time sequence test set; constructing a recurrent neural network model based on a long-term and short-term memory network structure, and training the recurrent neural network model according to the time sequence training set until the recurrent neural network model converges; and finally, verifying the converged recurrent neural network model according to the time sequence test set, and when the verification is passed, taking the converged recurrent neural network model as an energy consumption use efficiency prediction model for predicting the energy consumption use efficiency of thedata center. Compared with the prior art, the prediction accuracy of the energy consumption use efficiency prediction model obtained through training is high, and therefore the energy consumption useefficiency of the data center can be predicted more accurately.

Description

Technical field [0001] The present invention relates to the technical field of machine learning, in particular to a model training method, device, energy efficiency prediction method, device and storage medium. Background technique [0002] As energy costs continue to rise and people pay more attention to environmental protection, the demand for energy saving in data centers is increasing. In order to better control the energy consumption of the data center, it is first necessary to predict the energy consumption efficiency of the data center. [0003] In the prior art, the prediction of energy consumption efficiency is under preliminary development. For example, the ridge regression algorithm can be used to predict the energy consumption efficiency of data centers, which is based on the different characteristics of the main energy consumption components of different data centers. Domain adaptation model fusion, as well as the differences between different data centers, make targe...

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): G06N3/04G06N3/08G06Q10/04
CPCG06N3/084G06Q10/04G06N3/044G06N3/045
Inventor 夏恒夏俐赵千川贾庆山管晓宏杨震朱华高江岳上韩建军栗权林森赵静洲徐东黄现东郑焕琼
Owner TENCENT TECH (SHENZHEN) CO LTD