Optimizing Coverage and Capacity in Cellular Networks using Machine Learning

Wireless cellular networks are large-scale networks in which asymptotic capacity investigation is no longer a cliche. A substantial body of work has been carried out to improve the capacity of cellular networks by introducing ad hoc communications, resulting in the so-called multihop cellular networks. Most of the previous research allows ad hoc transmissions between certain source and destination pairs to alleviate base stations' relay burden. However, since reports show that Internet data traffic is becoming more and more dominant in cellular networks, we explore in this paper the capacity of multihop cellular networks with all traffic going through base stations and ad hoc transmissions only acting as relay. We first investigate the capacity of regular multihop cellular networks where both nodes and base stations are regularly placed. By fully exploiting the link rate variability, we find that multihop cellular networks can have higher per-node throughput than traditional cellular networks by a scaling factor of log 2 n. Then, for the first time we extend our study to the capacity of heterogeneous multihop cellular networks where nodes are distributed according to a general Inhomogeneous Poisson Process and base stations are randomly placed. We show that under certain conditions multihop cellular networks can also outperform traditional cellular networks by a scaling factor of log 2 n. Moreover, both throughput-fairness and bandwidth-fairness are considered as fairness constraints for both kinds of networks.

New multimedia services such as HTTP live video streaming [1] demand for higher capacity, especially in mobile networks. In fact, about 50 % of data in mobile networks is currently video traffic, and this number is expected to increase to 70–80 % by 2015 [2]. To enhance the capacity in cellular networks even further, several study items were defined [3] to target peak data rates of up to 1 Gbit/s in the downlink and 500 Mbit/s in the uplink. The different techniques are currently being discussed within the 3GPP for LTEs evolution called LTE-Advanced (LTE-A). A promising approach to enhance the capacity in cellular access networks even further is to create smaller cells [4]. This represents a shift in paradigm from Macro cells to a more heterogeneous ecosystem consisting of a combination of different cell sizes and transmission powers and thus coverage, referred to as Macro-, Pico-, and Femto-cells.

The design and maintenance of the radio access network (RAN) in mobile telecommunications requires meticulous monitoring of network performance to ensure optimal quality and coverage.Drive testing is a prevalent methodology for collecting data on network status across delineated geographical areas.This process involves systematically traversing various routes, including streets and pathways, to assess network performance metrics such as Reference Signal Received Power (RSRP).Although drive testing provides essential insights for identifying regions with inadequate signal quality, it is inherently resource-intensive, involving considerable time and financial expenditures.This paper proposes an innovative optimization methodology aimed at enhancing the efficiency of data collection during drive tests.The proposed approach is organized into four fundamental steps: (1) partitioning the map into smaller sections, (2) selecting critical points within each section, (3) employing map-matching techniques to accurately align these points with actual streets and pathways, and (4) determining the optimal routefor traversing the critical points.A rectangular area of interest is selected and divided into K smaller sub-regions, within which M critical points are identified according to a predefined criterion.These points, which may not initially correspond with the existing street network, are corrected through mapmatching techniques to ensure feasible traversal paths.Lastly, an optimization algorithm is utilized to compute the shortest route that encompasses all identified critical points.The efficacy of the proposed method is assessed through experimental studies that manipulate key parameters K (denoting the number of sub-regions) and M (indicating the maximum critical points per zone).The evaluation emphasizes two critical metrics: the total distance traveled and the success rate in detecting areas with RSRP values below -100 dBm.Results indicate that the proposed approach significantly decreases the distance required for drive testing while achieving substantial coverage of areas with weak signals.For example, in an experiment where the optimized route covered only 18.54 kilometers-equivalent to 34% of the distance of an entire drive test-it successfully identified 70% of regions with poor RSRP.Furthermore, this paper introduces a criterion for assessing the effectiveness of drive test routes, highlighting the balance between route length and coverage of low-signal areas.The findings substantiate that adequate data for network performance analysis can be secured with considerable savings in both cost and time compared to conventional exhaustive drive testing.While this study concentrates on RSRP measurements within 4G networks, the proposed methodology is adaptable for other metrics, including Reference Signal Received Quality (RSRQ).Future research may also examine the integration of alternative data sources, such as satellite imagery, to further refine map partitioning and critical point selection, thereby enhancing the overall efficacy of the proposed method.

Mobility management is an essential process in mobile networks to ensure a high quality of service (QoS) for mobile user equipment (UE) during their movements. In fifth generation (5G) and beyond (B5G) mobile networks, mobility management becomes more critical due to several key factors, such as the use of Millimeter Wave (mmWave) and Terahertz, a higher number of deployed small cells, massive growth of connected devices, the requirements of a higher data rate, and the necessities for ultra-low latency with high reliability. Therefore, providing robust mobility techniques that enable seamless connections through the UE’s mobility has become critical and challenging. One of the crucial handover (HO) techniques is known as mobility robustness optimization (MRO), which mainly aims to adjust HO control parameters (HCPs) (time-to-trigger (TTT) and handover margin (HOM)). Although this function has been introduced in 4G and developed further in 5G, it must be more efficient with future mobile networks due to several key challenges, as previously illustrated. This paper proposes a Robust Handover Optimization Technique with a Fuzzy Logic Controller (RHOT-FLC). The proposed technique aims to automatically configure HCPs by exploiting the information on Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), and UE velocity as input parameters for the proposed technique. The technique is validated through various mobility scenarios in B5G networks. Additionally, it is evaluated using a number of major HO performance metrics, such as HO probability (HOP), HO failure (HOF), HO ping-pong (HOPP), HO latency (HOL), and HO interruption time (HIT). The obtained results have also been compared with other competitive algorithms from the literature. The results show that RHOT-FLC has achieved considerably better performance than other techniques. Furthermore, the RHOT-FLC technique obtains up to 95% HOP reduction, 95.8% in HOF, 97% in HOPP, 94.7% in HOL, and 95% in HIT compared to the competitive algorithms. Overall, RHOT-FLC obtained a substantial improvement of up to 95.5% using the considered HO performance metrics.

Beyond 5G (B5G) networks require advanced handover algorithms to guarantee seamless connectivity and optimum quality of service. Traditional handover methods are not sufficient to meet the stringent latency and reliability requirements of next-generation networks. To meet these challenges, the integration of fuzzy logic into handover algorithms offers a viable solution. The proposed approach utilizes parameters such as reference signal received power (RSRP), reference signal received quality (RSRQ), signal-to-interference plus noise ratio (SINR), and user equipment (UE) speed as inputs, while dynamically adjusting the time-to-trigger (TTT) and handover margin (HOM) as outputs. To assess the effectiveness of this algorithm, handover latency (HOL) and handover interruption time (HIT) are evaluated and compared with existing algorithms in the literature. The results show better and more efficient performance in both terms of latency and interruption time.

The millimeter-wave (mmWave) band offers the potential for high-bandwidth communication channels in cellular networks. It is not clear, however, whether both high data rates and coverage in terms of signal-to-noise-plus-interference ratio can be achieved in interference-limited mmWave cellular networks due to the differences in propagation conditions and antenna topologies. This article shows that dense mmWave networks can achieve both higher data rates and comparable coverage relative to conventional microwave networks. Sum rate gains can be achieved using more advanced beamforming techniques that allow multiuser transmission. The insights are derived using a new theoretical network model that incorporates key characteristics of mmWave networks.

The widespread use of wireless mobile communications in past years has resulted in a mass use of the 2 GHz band. As a consequence, the 3.5 GHz and 800 MHz bands have emerged as an excellent alternative for mobile operators. In this paper, we investigate such alternatives using the 3GPP 3-dimensional (3D) channel model. We show the impact of both 800 MHz and 3.5 GHz carrier frequencies not only in an urban but also in a rural environment. We consider indoor and outdoor users, as well as line-of-sight (LOS) and non line-of-sight (NLOS) users. We evaluate and compare the performance in terms of Signal-to-Interference-plus-Noise Ratio (SINR), Reference Signal Received Power (RSRP), Received Signal Strength Indicator (RSSI) and Reference Signal Received Quality (RSRQ).

H-HOME: A learning framework of federated FANETs to provide edge computing to future delay-constrained IoT systems

This paper aims at studying user association for uplink (UL) transmission in cooperative heterogeneous cellular networks, where small cell sum rate is limited by the backhaul (BH) capacity. The investigated architecture can be modeled as a multiple-access relay channel (MARC) channel where multiple users communicate with a final destination (the macro base station) with the help of a relay (the small cell base station). A network-coding-based MARC, which exploits both the direct and relayed transmissions, is introduced to deal with low-capacity BH. We assess the UL average system capacity for 1) the baseline association based on the strongest reference signal received power (RSRP) in downlink (DL) and 2) the optimized user association chosen to improve the overall network UL sum-rate. Our results show that the network-coding-based MARC scheme achieves significant gains with respect to the pure relaying strategy. We further show that the optimized user association provides significant gains in network UL sum-rate with respect to the RSRP association, for the same sum power constraint and without degrading DL performance, especially when the BH capacity is sufficiently large.

The exponential increase in high rate traffic driven by a new generation of wireless devices is expected to overload cellular network capacity in the near future. Femtocells have recently been proposed as an efficient and cost-effective approach to enhance cellular network capacity and coverage. However, dense and unplanned deployment of additional Base Stations and their uncoordinated operation may increase the system power consumption. Thus, efficient schemes are essential for managing femtocells activity and improving the system performance. In this paper, we investigate the effect of femtocell deployment on the cellular network energy efficiency. The goal is twofold: first, we aim to analyse how classic femtocell access schemes affect the system energy consumption; second, we propose a novel cell selection scheme for Open Access femtocells that allows the effective deployment of femtocells in the cellular network reducing power consumption and limiting the effect of interference.

Cellular operators have concluded that small cell deployments are a very cost-effective and quick solution to meet the ever growing demands on capacity and coverage in cellular networks for indoor and outdoor environments. While traveling in public transit vehicles, cellular subscribers usually experience poor signal reception and low bandwidth. We hence consider deploying small cells onboard (i.e., mobile small cells) such vehicles. This should enhance subscribers' quality of experience (QoE). We consider a Small Base Station (SBS) mounted in a public transit bus (i.e., mobile SBS) to serve onboard users. The mobile SBS aggregates users' traffic to and from the macroBSs. To further extract the underlying rich multipath-Doppler diversities resulting from the fast mobility and the associated selective fading channel, a pre-coded transmission is deployed in the mobile SBS.We examine the achievable gain from enabling aggregation through mobile SBS in terms of the outage probability. We derive a tight-bound closed-form expression for the outage probability in the downlink (DL). Our results indicate that significant gain in outage probability and coverage are achievable.

This paper evaluates the hard handover performance based on the different hard handover algorithms for UTRAN LTE system. The focus is on the impact that two kinds of hard handover algorithms compare to A3 event based on reference signal received power (RSRP) and reference signal received Quality (RSRQ) measurements in different velocity environment. These have been designed and implemented in a dynamic system level simulator and have been studied for different parameter sets in a high-speed railway (HSR) simulation scenario. RSRP and RSRQ parameter have been simulated in a dynamic link level simulation and have been investigated the influence factors via the simulation. The results suggest that optimized hard handover algorithms have higher handover success rate than the classical A3 event in different velocity environment.

Offloading mobile data traffic to Wireless Local Area Network (WLAN) is one of the widely accepted solution to improve the achievable capacity in cellular networks. In this paper, we propose a Signal-to-Interference-plus-Noise Ratio (SINR) based novel HandOver (HO) procedure to facilitate the Long Term Evolution (LTE)-WLAN interworking. We illustrate the significance of other handover parameters in addition to SINR in achieving improved system performance. Furthermore, we propose a self-configured vertical HO algorithm which determines an optimal configuration of these mobility parameters. We have obtained the results by performing extensive simulations in ns-3, which we have enhanced to support LTE-WLAN interworking as per the Third Generation Partnership Project (3GPP) standard.

This paper investigates the capacity of the cooperative cellular networks and proposes to use the 2-D nested deployment on the base stations. Further analysis of sum-rate capacity and spectrum efficiency shows that this approach provides significant improvement. The study leverages the traditional model of regarding the coverage of base stations as the hexagonal blocks and views each hexagon as a macro-cell. One of the theoretical contributions of this paper is to use the invariance in the difference co-array to cover the derive the entire set of the channel fading coefficients. Furthermore, this paper proves the validity of using the average sum-rate capacity to calculate the capacity of the networks in both Rayleigh fading and non-fading channels. We also use simulations to confirm the correctness of the proposed theories from another perspective. As a result, the proposed approach remarkably improves the capacity of the network with the same amount of base stations.

Femtocell network is regarded as the potential and effective technique to improve the capacity and coverage of traditional cellular networks. One of the challenges is how to access the network and manage the interference among different users. Compared with other access strategies, hybrid access strategy allows femtocell base stations (FBSs) to provide preferential access to femtocell users (FUEs) while other users can access nearby FBS with specific restrictions. In this paper, a robust downlink power control scheme is studied in two-tier femtocell networks, where femtocells share the same frequency with macrocell. A hierarchical game framework that takes the different users' requirements into consideration is constructed. In addition, as the link gains are actually uncertain in dynamic environment, probabilistic constraints are used to describe the uncertainty. Then two sub-problems are obtained to maximise the sum rate of macrocell and femtocells, respectively and guarantee the quality of service (QoS) of different users. To tackle the nonlinear and nonconvex optimization problem, successive convex approximation is introduced. And the practical iterative power allocation algorithm is provided. Finally, numerical results show that the proposed scheme is effective in aspect of energy saving and QoS guarantee under dynamic environment.