LEARNING-BASED RESOURCE ALLOCATION WITH DYNAMIC DATA RATE CONSTRAINTS

In this paper, we address the problem of resource allocation (RA) in wireless communication networks, where each user has a dynamic data rate constraint. The objective of RA is to maximize the sum rate (SR) of the users while satisfying the data rate constraints in expectation. For a given set of data rate constraints, a suitable probability distribution for the activation of users is found iteratively with a stochastic gradient descent (SGD) approach to satisfy the data rate constraints in expectation. At each time instant, RA amongst the randomly activated users is performed noniteratively by a centralized deep neural network (DNN). Simulations show that the proposed approach is convergent and not only can consider dynamic data rate constraints accurately, but also that it achieves a SR higher than that of the conventional geometric programming (GP) method. The proposed approach can open up a direction of research for cross-layer RA in the current deep learning-based RA context.