Power Allocation for Multiple Transmitter-Receiver Pairs Under Frequency-Selective Fading Based on Convolutional Neural Network

Abstract

For multiple transmitter-receiver pairs communication in a frequency-selective environment, typical power allocation method is the Iterative-Waterfilling (IW) algorithm. Main drawback of IW is its poor convergence performance, including low convergence probability and slow convergence speed in certain scenarios, which lead to high computational load. Large-scale network significantly magnifies the above drawback by lowering the convergence probability and convergence speed, which is difficult to satisfy real-time requirements. In this work, we propose a power allocation scheme based on convolutional neural network (CNN). The design of loss function takes into account the Sum Rate (SR) of all users. The output layer of the CNN model is replaced by several Softmax blocks, and the output of each Softmax block is the ratio of the transmission power of each user on the sub-carrier to the total power. Numerical studies show the advantages of our proposed scheme over IW: with the constraint of not lowering SR, there is no convergence problem and the computational load is significantly reduced.

Keywords

• Power allocation
• convolutional neural network
• sum rate
• iterative waterfilling