Unified and Distributed QoS-Driven Cell Association Algorithms in Heterogeneous Networks

TLDR

The paper tackles the downlink cell‑association problem in multi‑tier heterogeneous networks, where base stations have limited resource blocks, with one formulation suited to slow‑fading and another to fast‑fading environments. The authors aim to maximize long‑term rate utility under QoS constraints and to minimize global outage probability under outage QoS constraints. They solve the problems in two phases—a low‑overhead distributed cell‑association algorithm derived via Lagrange dual decomposition, followed by an optional resource‑block distribution phase that allocates remaining RBs to users. The cell‑association phase is identical for both problems, and simulations show that the proposed distributed scheme outperforms conventional max‑SINR based approaches.

Abstract

This paper addresses the cell association problem in the downlink of a multi-tier heterogeneous network (HetNet), where base stations (BSs) have finite number of resource blocks (RBs) available to distribute among their associated users. Two problems are defined and treated in this paper: sum utility of long term rate maximization with long term rate quality of service (QoS) constraints and global outage probability minimization with outage QoS constraints. The first problem is well-suited for slow fading environments, while the second problem provides a framework to deal with environments with fast fading. The defined optimization problems in this paper are solved in two phases: cell association phase followed by the optional RB distribution phase. We show that the cell association phase of both problems have the same structure. Based on this similarity, we propose a unified distributed algorithm with low levels of message passing for the cell association phase. This distributed algorithm is derived by relaxing the association constraints and using Lagrange dual decomposition method. In the RB distribution phase, the remaining RBs after the cell association phase are distributed among the users. Simulation results show that our distributed cell association scheme outperforms schemes that are based on maximum signal to interference plus noise ratio (SINR).