Self‐Organising Networks (SON)

Kordybach, Krzysztof; Hämäläinen, Seppo; Sartori, Cinzia; Viering, Ingo

doi:10.1002/9781119961789.ch3

Cited by 7 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Important examples of such algorithms are those controlling the Remote Electrical Tilt (RET) of the antennas at Base Stations (BSs). Coverage Capacity Optimization (CCO) is actually one of the key use-cases specified by Self-Organizing Networks (SONs), the network automation technology introduced by the 3 rd Generation Partnership Project (3GPP) [27]. The goal in CCO is to maximize the network capacity while ensuring that a targeted service area remains covered.…”

Section: Introductionmentioning

confidence: 99%

Learning Optimal Antenna Tilt Control Policies: A Contextual Linear Bandit Approach

Vannella¹,

Proutière²,

Jedra³

et al. 2022

Preprint

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Learning Optimal Antenna Tilt Control Policies: A Contextual Linear Bandit Approach

Vannella¹,

Proutière²,

Jedra³

et al. 2022

Preprint

View full text Add to dashboard Cite

“…Classical load balancing systems seek to solve load imbalance problems by collecting data from the network and user equipment (UE). Once key performance indicators (KPIs) and counters are analyzed, they are included in the network optimization process based on Self-Organized Network (SON) paradigm to improve performance while reducing operational expenditure (OPEX) and capital expenditure (CAPEX) [4]. However, the automatic adaptation of applications, systems, and devices to users' context changes provides useful external network information that is not yet included in this classical SON mechanisms [5,6].…”

Section: Introductionmentioning

confidence: 99%

Social-Aware Load Balancing System for Crowds in Cellular Networks

et al. 2021

View full text Add to dashboard Cite

Over time, load balancing systems in cellular networks have been key to avoiding overload problems in the network and to maintaining a correct resource allocation and performance. However, the classical approaches were not designed for the dynamism generated by user behavior. The big crowds of users at certain social venues are one of the main concerns of mobile operators due to the load imbalance generated. Additionally, the mobility of users who attend social events (e.g., sports events, concerts, etc.) greatly impacts network performance due to its high correlation with network traffic. The availability to inform about events, particularly regarding venue location (e.g., stadiums, concert halls, convention centers) is exponentially growing thanks to its proliferation in social networks through geolocation databases and other functionalities. Therefore, the present work proposes a novel load balancing system integrating a fuzzy logic controller algorithm with social-awareness, which considers the relative position between cell sites and the social event venue in order to configure the network parameters. This approach is evaluated for different configurations of load balancing methods simulated on an urban macro scenario, mitigating the impact of the number of users per cell without degrading the signal quality. In this way, results show that social event data information plus soft or aggressive transmission power changes in cells can help to maintain the balance in the number of users per cell during mass events.

show abstract

“…The RET problem consists in remotely controlling the vertical tilt angle of multiple antennas to optimize ad-hoc Key Performance Indicators (KPIs) such as coverage, capacity, interference, etc, that determine the network Quality of Service (QoS). RET automation can be framed in the context of Self-Optimizing Networks (SON), the network automation technology introduced by the 3 rd Generation Partnership Project (3GPP), and is an effective technique for handling interference and improving coverage and capacity in mobile networks [1].…”

Section: Introductionmentioning

confidence: 99%

Off-policy Learning for Remote Electrical Tilt Optimization

Vannella¹,

Jeong²,

Proutière³

2020

Preprint

View full text Add to dashboard Cite

We address the problem of Remote Electrical Tilt (RET) optimization using off-policy Contextual Multi-Armed-Bandit (CMAB) techniques. The goal in RET optimization is to control the orientation of the vertical tilt angle of the antenna to optimize Key Performance Indicators (KPIs) representing the Quality of Service (QoS) perceived by the users in cellular networks. Learning an improved tilt update policy is hard. On the one hand, coming up with a new policy in an online manner in a real network requires exploring tilt updates that have never been used before, and is operationally too risky. On the other hand, devising this policy via simulations suffers from the simulation-toreality gap. In this paper, we circumvent these issues by learning an improved policy in an offline manner using existing data collected on real networks. We formulate the problem of devising such a policy using the off-policy CMAB framework. We propose CMAB learning algorithms to extract optimal tilt update policies from the data. We train and evaluate these policies on realworld 4G Long Term Evolution (LTE) cellular network data. Our policies show consistent improvements over the rule-based logging policy used to collect the data.

show abstract

Self‐Organising Networks (SON)

Cited by 7 publications

References 4 publications

Learning Optimal Antenna Tilt Control Policies: A Contextual Linear Bandit Approach

Learning Optimal Antenna Tilt Control Policies: A Contextual Linear Bandit Approach

Social-Aware Load Balancing System for Crowds in Cellular Networks

Off-policy Learning for Remote Electrical Tilt Optimization

Contact Info

Product

Resources

About