Litcius/Paper detail

A Method to Select Optimal Deep Neural Network Model for Power Amplifiers

Xiaofei Yu, Xin Hu, Zhijun Liu, Chaowei Wang, Weidong Wang, Fadhel M. Ghannouchi

2020IEEE Microwave and Wireless Components Letters43 citationsDOI

Abstract

The power amplifier (PA) behavior models based on deep neural networks (DNNs) have been widely used. However, it is challenging to balance the network depth, the number of neurons, and the combination of input terms. Accordingly, how to obtain a suitable DNN model becomes a problem. This letter proposes a method to acquire the corresponding optimal DNN structure balancing multiple aspects for a PA by decoupling the relationship of the three factors mentioned above. The algorithm first chooses the optimal input combinations, and then utilizes the inputs to select the DNN structure with excellent capability to fit nonlinear functions and fewer coefficients. Experimental results verify that the DNN model acquired by the algorithm proposed can maintain superior performance with low complexity.

Topics & Concepts

Decoupling (probability)Artificial neural networkComputer scienceAmplifierNonlinear systemPower (physics)Control theory (sociology)AlgorithmArtificial intelligenceControl engineeringEngineeringBandwidth (computing)TelecommunicationsQuantum mechanicsControl (management)PhysicsAdvanced Power Amplifier DesignGaN-based semiconductor devices and materialsRadio Frequency Integrated Circuit Design