Deep Learning Based Resource Allocation : How Much Training Data is Needed?
We consider artificial neural networks based energy-efficient power control for interference networks. The influence
of different training set sizes and data augmentation is evaluated. It is shown that as few as 15,000 data points obtained from 300 channel realizations are sufficient to adequately predict almost globally optimal power allocations in a 4 user network. Moreover, we observe that, especially for larger scenarios, data augmentation is essential for successful training and far outweighs the effect of increasing the training data set size.
License Holder: © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Use and reproduction:
All rights reserved