Dynamic Coverage Optimization for 5G Ultra-dense Cellular Networks Based on Their User Densities

Abstract

This paper has proposed a user-density-based coverage optimization technique for ultradense cellular networks. Antenna tilting is a promising coverage optimization technique to be used in 5G networks that significantly improve the signal to interference plus noise ratio (SINR) by choosing the appropriate angle of tilt. In this paper, the cellular coverage has been optimized for scattered user densities/user-hotspots using an adaptive antenna tilting mechanism that steers the beams towards the temporal hot spot in the coverage area. The proposed method has the competence to improve the desired SINR level and coverage area for a group of the user rather than a single user. In this work, a reinforcement learning (RL) algorithm has been implemented to optimize the tilt angle. The performance of the proposed technique has been evaluated in the simulation platform considering a three-sectored multicellular mobile network where the groups of user clusters are distributed randomly. The result confirms the improvement in RSS and SINR value in the group of users having high density with maximum user satisfaction.

A Differentiable Throughput Model for Load-Aware Cellular Network Optimization Through Gradient Descent

“…This allows us to quantify further outage reductions possible by optimally reassigning UEs across available cells. While several initial values are possible for Ã, we found that the RSRP-based assignment 10 for the considered network configuration γ( * ) worked sufficiently well in our scenario. By definition, the optimization in ( 13) requires the loadaware objective.…”

“…Typically, CCO centers around antenna parameters that can be controlled remotely, hence offering the possibility to retune the network configuration after deployment [1]. Specifically the optimal setting of the transmit power and the antenna downtilt is of interest [2], [3], [5], [10]- [21]. Overall, we can distinguish two strategies, either approaching the topic from a model-based or a model-free perspective.…”

“…In [2], the authors successfully utilize such MDT data for automated tuning of the antenna downtilt based on a RL approach. Similarly, the use of RL variants has further been validated in [10]- [12], with multi-agent systems gaining more interest to address the high dimensional action space required for joint optimization over large areas [13]- [16]. Despite these advances, the required training phase of such model-free approaches still poses a severe practical limitation, most notably in terms of sample-efficiency and risk-aversion, which are ongoing research topics [5], [24].…”

“…In fact, the load aspect is often omitted in CCO, with methods like [3], [6], [11], [13], [19], [20] solely considering interference management. Similarly, this also applies for the theoretical empty cell throughput, as in [10], [14], [17], [18], which omits the possibility of congestion and is thus inherently load-unaware. However, the importance of an adequate distribution of UEs among the available cells is apparent from the design of load balancing and handover algorithms [31]- [33].…”