Deep Unsupervised Learning for Network Resource Allocation Problems with Convex and Non-Convex Constraints

Deep neural networks (DNNs) are currently emerging as a potential solution to solve NP-hard wireless resource allocation problems. However, in the presence of intricate constraints, e.g., users' quality-of-service (QoS) constraints or base station quota, guaranteeing constraint satisfaction becomes a fundamental challenge. In this thesis, I propose a novel unsupervised learning framework to solve the classical power control and user assignment problem in a multi-user interference channel, where the objective is to maximize the network sum-rate with QoS, power budget, and base station quota constraints. The proposed method utilizes a differentiable projection function, defined both implicitly and explicitly, to project the output of the DNN to the feasible set of the problem. Extensive simulations depict that the proposed DNN solutions not only improve the achievable data rate, but also achieve zero constraint violation probability, compared to the existing DNNs, and also outperform the optimization-based benchmarks in computation time.