Group Lasso-based neural network cutting method for power amplifier

A power amplifier and neural network technology, applied in the field of communication, can solve problems such as difficult hardware resource overhead, easy over-fitting, weak robustness, etc., to improve pre-distortion effect, suppress over-fitting, improve fitting performance and The effect of precision
CN110414565AActive Publication Date: 2019-11-05BEIJING UNIV OF POSTS & TELECOMM +1
4 Cites 4 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
BEIJING UNIV OF POSTS & TELECOMM
Publication Date
2019-11-05

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a Group Lasso-based neural network cutting method for a power amplifier, and belongs to the technical field of communication. The method comprises the following steps: for an original neural network structure, dividing all output weights connected to the same neuron in other layers except an output layer into one group; carrying out l2 norm constraint on each group of weights after grouping; taking the sum of L2 norms of the weights of all groups in the original neural network structure as a Group Lasso penalty term, and adding the Group Lasso penalty term to the original loss function Loss1 to obtain a new loss function Loss2; carrying out minimization training on the Loss2 through a BP algorithm; searching for weight groups with convergence close to 0, removing neurons connected with the weight groups to obtain a simplified neural network, training an original loss function Loss1 by adopting a BP algorithm to obtain a trained simplified neural network model, and modeling or pre-distorting the power amplifier by utilizing the model. Overfitting in the training process can be inhibited, the pre-distortion effect is improved, the calculated amount is reduced,and engineering application is facilitated.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of communication, in particular to a Group Lasso-based neural network cutting method for power amplifiers. Background technique

[0002] With the continuous development of communication technology, in order to use limited spectrum resources more efficiently, new modulation techniques with high spectrum efficiency are used in communication standards. However, these new modulation methods make the peak-to-average ratio of the signal higher and the envelope fluctuation larger, causing the signal to be seriously distorted after passing through the RF power amplifier; not only the EVM before and after the signal output is seriously deteriorated, but also serious out-of-band distortion .

[0003] In order to correct the distortion produced by the signal passing through the power amplifier, the power amplifier needs to be linearized. Among the current linearization technologies, the predistortion technology is wi...

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