Interference Mitigation in HetNets to Improve the QoS Using Q-Learning

Abstract

Small cells (SCs) based ultra-dense heterogeneous networks (HetNets) are one of the promising solutions for increased coverage and capacity in 5G cellular networks. However, in multi-tiered architecture, co-tier and cross-tier interferences are both performance-limiting factors. Efficient resource allocation techniques can handle interferences effectively, however, their complexity linearly increases with the density of the HetNets resulting from dynamic and unplanned deployment of SCs. Therefore, HetNets can be implemented only through an algorithm that is self-organizing and adaptive to the dynamic conditions. In this research paper, a Q-Learning (QL) based adaptive resource allocation scheme is proposed and evaluated for SC-based ultra-dense HetNets. This QL scheme allocates optimal power to the small cell base station (SBS) to meet the minimum required capacity of macrocell user equipment (MUEs) and the small cell user equipment (SUEs) to provide quality of service (QoS). The proposed QL scheme not only maintains the minimum required capacities of the MUEs and SUEs but has also shown a significant improvement in the capacities of MUEs and SUEs in high interference scenarios as compared to the prior works. In the high co-tier and cross-tier interference scenario, where the state of the art schemes fail to maintain the minimum required capacity of the MUE, the proposed scheme provides a minimum MUE capacity of 2 b/s/Hz, which is twice the minimum required QoS threshold. In a similar way, the proposed solution guarantees QoS up to 16 SCs which are 37.5% more SC than the previously reported works in high interference scenario while maintaining a minimum SUE capacity of 1.5 b/s/Hz, which is 33% higher than the minimum required QoS threshold. By simultaneously mitigating co-tier and cross-tier interferences in ultra-dense HetNets, the proposed solution not only improved the minimum capacities of MUEs and SUEs but also sets a new benchmark for minimum QoS threshold.

Improving the QoS in 5G HetNets Through Cooperative Q-Learning

“…To mitigate the CoI and CrI simultaneously, in multi-tiered 5G HetNets, we proposed a self-adaptive framework by considering each BS s as an agent in the MDP in a distributed manner in our previous work [10]. To provide the minimum required SINR to UE m and UE s , we systematically developed a RF to optimally allocate transmission power to each BS s in the HetNets and successfully achieved QoS requirements by effectively mitigating interferences in and among the tiers.…”

“…In this paper, we have investigated the cooperative implementation of the QL algorithm proposed in our previous work [10] The paper is organized as follows: in section II, the system model for exploring CQL for adaptive power allocation in HeNets is presented followed by the problem formulation in section III. In section IV, the RL based RRM using CQL is discussed to model the SC HetNets as the multiagent MDP.…”

“…Interferences due to multi-tier HetNets architecture severely degrade EE, QoS, and QoE. Therefore, to ensure the EE, QoS, and QoE in 5G SC HetNets, effective interference management is vital [7], [10]. Several approaches for interference mitigation have been proposed in the literature based on efficient spectrum utilization, antenna patterns, adaptive power control, and a combination of these schemes.…”

Reliability Assurance Dynamic SSC Placement Using Reinforcement Learning

“…The Q-learning algorithm usually solves complex decision optimization problems with less prior knowledge [25]. The agent Q agent first senses the environment state selects an action a, and executes it according to the Q function on the basis of the current state s. When moving to the next state s , the agent calculates the reward function R(s, a) and updates the Q function Q(s, a) based on the environmental feedback, then selects the next action based on the new Q value and the current environmental state and iteratively proceeds until the optimal strategy is obtained [26].…”

A Survey on HetNet to Enhance QoS in 5G Network Using Various Techniques

“…Muhammad usman Iqbal et.al [9] proposed that HetNets can only be used if an algorithm that is adaptive and self-organizing the current conditions is used. SC-based ultra-dense HetNets are evaluated using a QL (Q-Learning) based adaptive resource allocation scheme.…”