A Distributed SON-Based User-Centric Backhaul Provisioning Scheme

Abstract

5G definition and standardization projects are well underway, and governing characteristics and major challenges have been identified. A critical network element impacting the potential performance of 5G networks is the backhaul, which is expected to expand in length and breadth to cater to the exponential growth of small cells while offering high throughput in the order of gigabit per second and less than 1 ms latency with high resilience and energy efficiency. Such performance may only be possible with direct optical fiber connections that are often not available country-wide and are cumbersome and expensive to deploy. On the other hand, a prime 5G characteristic is diversity, which describes the radio access network, the backhaul, and also the types of user applications and devices. Thus, we propose a novel, distributed, selfoptimized, end-to-end user-cell-backhaul association scheme that intelligently associates users with candidate cells based on corresponding dynamic radio and backhaul conditions while abiding by users' requirements. Radio cells broadcast multiple bias factors, each reflecting a dynamic performance indicator (DPI) of the end-to-end network performance such as capacity, latency, resilience, energy consumption, and so on. A given user would employ these factors to derive a user-centric cell ranking that motivates it to select the cell with radio and backhaul performance that conforms to the user requirements. Reinforcement learning is used at the radio cells to optimise the bias factors for each DPI in a way that maximise the system throughput while minimising the gap between the users' achievable and required end-to-end quality of experience (QoE). Preliminary results show considerable improvement in users' QoE and cumulative system throughput when compared with the state-of-the-art user-cell association schemes.INDEX TERMS Backhaul, fronthaul, user-centric, user-cell association, SON, reinforcement learning, multiple attribute decision making.

Fuzzy Q-learning-based user-centric backhaul-aware user cell association scheme

“…The main contribution of this paper is the novel implementation methodology for user-centric backhaul-aware UA scheme presented in our previous work [5]. Unlike our basic implementation, which was computationally limiting, our proposed implementation is computationally efficient and hence has significant practical relevance since it allows numerous small cells, one of the key enablers of 5G, to take part in the UA optimization.…”

“…Repeat the process unless terminal state is reached or maximum allowed iterations are complete they may lead to unsatisfactory users' performance (as a result of the backhaul bottleneck) or to inefficient utilization of the network [5], [12]. Hence, various backhaul-aware UA schemes, showing convincing results, have been proposed recently in the literature.…”

“…Furthermore, cumulative perceived QoE of all users, UQ n,q , is to be kept below the minimum QoE threshold φ q , as expressed in (18), Q u,q is the QoE perceived by the user relative to its target QoE Q u,q for an attribute q. It is important to mention here that we measure users' satisfaction relative to various performance targets in terms of QoE, as was introduced in [5].…”

“…A game theoretic-based cache-aware UA algorithm that enables small cells, cognizant of their own caching capabilities and users' mobility patterns, to cache multimedia content in order to enhance users' quality of service (QoS) under backhaul capacity limitations is investigated in [18]. A novel user-centric backhaul-aware UA approach is introduced in [5], that enables users to select a cell that potentially meets their respective QoE requirements. Cells leverage Qlearning to virtually tailor their footprints in order to meet users' needs considering both backhaul capacity and delay constraints.…”

“…In this work we propose a novel approach to the user-centric backhaul-aware scheme introduced in [5], which aims at maximizing users' QoE through virtually tailored optimal cells ranges with regard to backhaul capacity and reliability constraints. In this work we address two shortcomings of the basic user-centric backhaul-aware scheme: the impractical increase in the process lead-time when the number of cells per cluster increases, and the limitation of the solution space to integer bias values.…”