Fuzzy-Q-learning-based autonomic management of macro-diversity algorithm in UMTS networks

Nasri, Ridha; Altman, Zwi; Dubreil, H.

doi:10.1007/bf03219884

Cited by 10 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This procedure is known as fuzzification. This degree of membership information is then used by Fuzzy Logic Controller (FLC) [12], [25] to calculate output action for each of the triggered rules. The process of defuzzification maps these actions into a crisp (continuous) value.…”

Section: Ql For Self-optimization In Ltementioning

confidence: 99%

Self-Organizing Networks: A Packet Scheduling Approach for Coverage/Capacity Optimization in 4G Networks Using Reinforcement Learning

Tiwana

Nawaz

Ikram

et al. 2014

ElAEE

View full text Add to dashboard Cite

The next generation mobile networks LTE and LTE-A are all-IP based networks. In such IP based networks, the issue of Quality of Service (QoS) is becoming more and more critical with the increase in network size and heterogeneity. In this paper, a Reinforcement Learning (RL) based framework for QoS enhancement is proposed. The framework achieves the coverage/capacity optimization by adjusting the scheduling strategy. The proposed selfoptimization algorithm uses coverage/capacity compromise in Packet Scheduling (PS) to maximize the capacity of an eNB subject to the condition that minimum coverage constraint is not violated. Each eNB has an associated agent that dynamically changes the scheduling parameter value of an eNB. The agent uses the RL technique of Fuzzy Q-Learning (FQL) to learn the optimal scheduling parameter. The learning framework is designed to operate in an environment with varying traffic, user positions, and propagation conditions. A comprehensive analysis on the obtained simulation results is presented, which shows that the proposed approach can significantly improve the network coverage as well as capacity in terms of throughput.

show abstract

Section: Ql For Self-optimization In Ltementioning

confidence: 99%

Self-Organizing Networks: A Packet Scheduling Approach for Coverage/Capacity Optimization in 4G Networks Using Reinforcement Learning

Tiwana

Nawaz

Ikram

et al. 2014

ElAEE

View full text Add to dashboard Cite

show abstract

“…As for the most used keywords per year, as Figure 9 reveals, starting with the year 2006, the most used keyword was "UMTS", which refers to the third generation (3G) of mobile networks, specifically to the universal mobile telecommunications system, which was one of the technologies most used by mobile devices after the year 2000 approximately [80]. At that time, studies were carried out through fuzzy learning for the better management of the mobile network [81]. Then, in 2012, the most commonly used keyword was "SPIM", which as SPAM detection on instant messaging, and the studies carried out focused on how to improve and characterize this type of message to mitigate the overload of the server [82].…”

Section: Resultsmentioning

confidence: 99%

Research Trends in the Use of Machine Learning Applied in Mobile Networks: A Bibliometric Approach and Research Agenda

García-Pineda,

Valencia-Arias,

Patiño-Vanegas

et al. 2023

Informatics

View full text Add to dashboard Cite

This article aims to examine the research trends in the development of mobile networks from machine learning. The methodological approach starts from an analysis of 260 academic documents selected from the Scopus and Web of Science databases and is based on the parameters of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. Quantity, quality and structure indicators are calculated in order to contextualize the documents’ thematic evolution. The results reveal that, in relation to the publications by country, the United States and China, who are competing for fifth generation (5G) network coverage and are responsible for manufacturing devices for mobile networks, stand out. Most of the research on the subject focuses on the optimization of resources and traffic to guarantee the best management and availability of a network due to the high demand for resources and greater amount of traffic generated by the many Internet of Things (IoT) devices that are being developed for the market. It is concluded that thematic trends focus on generating algorithms for recognizing and learning the data in the network and on trained models that draw from the available data to improve the experience of connecting to mobile networks.

show abstract

“…The solution corresponding to the planning HM 0 value (denoted hereafter as the planning solution) is plotted using a yellow circle. The first Pareto front in red triangles corresponds to the static optimization with the polynomial parameterization surface function (9). The results for the Pareto front using the exponential parameterization surface (10) are shown with blue squares in the Figure . The parameter b in ( 10) is fixed to the planning value of 6 dB and the parameters a 1 and a 2 are optimized by the PSO.…”

Section: Resultsmentioning

confidence: 99%

“…The advantage of such a solution is that it benefits from both computation resources available at the management-plane, and from high reactivity when implemented in the control-plane. It is noted that a two phase approach for self-optimization load balancing has been considered in the framework of Fuzzy Q-Learning (FQL) [8][9]. This approach can be viewed as a fully control-plane approach, where both learning and control (exploration and exploitation in the learning nomenclature) are performed on-line.…”

Section: Introductionmentioning

confidence: 99%

Particle swarm optimization for Mobility Load Balancing SON in LTE networks

Altman

Sallem

Nasri

et al. 2014

2014 IEEE Wireless Communications and Networking Conference Workshops (WCNCW)

Self Cite

View full text Add to dashboard Cite

Abstract-This paper presents a self-optimizing solution for Mobility Load Balancing (MLB). The MLB-SON is performed in two phases. In the first, a MLB controller is designed using Multi-Objective Particle Swarm Optimization (MO-PSO) which incorporates a priori expert knowledge to considerably reduce the search space and optimization time. The dynamicity of the optimization phase is addressed. In the second phase, the controller is pushed into the base stations to implement the MLB SON. The method is applied to dynamically adapt Handover Margin parameters of a large scale LTE network in order to balance traffic of the network eNodeBs. Numerical results illustrate the benefits of the proposed solution.

show abstract

Fuzzy-Q-learning-based autonomic management of macro-diversity algorithm in UMTS networks

Cited by 10 publications

References 13 publications

Self-Organizing Networks: A Packet Scheduling Approach for Coverage/Capacity Optimization in 4G Networks Using Reinforcement Learning

Self-Organizing Networks: A Packet Scheduling Approach for Coverage/Capacity Optimization in 4G Networks Using Reinforcement Learning

Research Trends in the Use of Machine Learning Applied in Mobile Networks: A Bibliometric Approach and Research Agenda

Particle swarm optimization for Mobility Load Balancing SON in LTE networks

Contact Info

Product

Resources

About