New generation networks performance analysis and optimization

Yuriy, Zaychenko; Aydin, Gasanov; Hamidov, Galib

doi:10.1109/icaict.2016.7991771

Cited by 5 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the fast fifth-generation (5G) wireless communications [1]- [14], the cellular network performance, which is often evaluated by key performance indicator (KPI) and key quality indicator (KQI) [15], has been getting more and more attention [16], [17]. On the one hand, KQI is derived from a number of sources, including the performance metrics of the service or underlying support services as KPI, and hence it The associate editor coordinating the review of this manuscript and approving it for publication was Yue Cao .…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Based Quantitative Association Rule Mining Method for Evaluating Cellular Network Performance

et al. 2019

View full text Add to dashboard Cite

Cellular network performance is often evaluated by key performance indicator (KPI) and key quality indicator (KQI). The association between KQI and KPI is the most critical step to optimize the performance of cellular network. Traditional association methods between KPI and KQI are based on the end-to-end evaluation. However, these methods require professional engineers to evaluate cellular network performance, and the man-manned evaluation is often inaccurate and labor-consuming, which cannot find out the caused factor of deterioration networks. In order to solve the problem, we propose a machine learning based quantitative association rule mining (QARM) method called SWP-RF, which consists of slidingwindow partitioning (SWP) and random forest (RF), to associate KPI with KQI. Specifically, we first use SWP to discretize continuous attributes into boolean values, which is adopted to mine its association rules. The warning intervals and the warning points is obtained by SWP. Next, we use RF feature importance to measure the association between KPI and KQI. The priority of the association strength between all KPIs and each KQI can be obtained by RF. Finally, we select the warning points and the association strength priority as optimal output solution. Experiments are conducted over the actual data from telecom operators and the results confirm the feasibility and accuracy of the proposed method. INDEX TERMS Quantitative association rule mining (QARM), machine learning, continuous attributes, sliding-window partioning (SWP), random forest (RF).

show abstract

Section: Introductionmentioning

confidence: 99%

Machine Learning Based Quantitative Association Rule Mining Method for Evaluating Cellular Network Performance

et al. 2019

View full text Add to dashboard Cite

show abstract

“…For the implementation of adaptive approach of mutation probability change we use so-called Rechenberg adaptation rule [2 ].…”

Section: Adaptive Approachmentioning

confidence: 99%

New Generation Networks Structural Synthesis With Application of Modified Genetic Algorithm

Zaychenko

2017

Information and Telecommunication Sciences

View full text Add to dashboard Cite

Background. The problem of new generation computer network structural synthesis is considered under constraints on Quality of Service (QoS) -average packets transfer delay (PTD) and packets loss ratio (PLR). Besides network structure it is necessary to determine simultaneously channels capacities and find flow distribution for all classes of service (customers). This problem refers to so-called NP-difficult combinatorial optimization problems for which there are no exact algorithms of polynomial computational complexity. Therefore in the paper modified genetic algorithm (GA) is suggested for its solution.Objective. The aim of the paper is to investigate different modifications (variants) of genetic algorithms: deterministic, adaptive and self-adjusted and estimate their efficiency for the solution of the considered problem.Methods. Based on analysis of literature on GA classes of algorithms were detected differed by variants of strategic parameters adaptation -probabilities of crossover and mutations. Different combinations of adaptation methods were implemented and analyzed -deterministic, adaptive and self-adjusting.Results. The following variants of GA were investigated in the research:• the combination of unconditional crossover and dynamic deterministic mutation; • the combination of unconditional crossover and dynamic adaptive mutation; • the combination of unconditional crossover and dynamic self-adjusting mutation; • the combination dynamic deterministic crossover and dynamic mutation; • the combination dynamic adaptive crossover an unconditional mutation.Conclusions. In result of investigations it was established that the most efficient for the computer networks structural synthesis is the genetic algorithm with combination of dynamic adaptive crossover an unconditional mutation. This algorithm was implemented in software kit and applied for real problem of NG network structural design and its efficiency was estimated.

show abstract

New Advanced Approach for Data Flows Prioritization at an Output of a User Terminal

Bridova,

Brida,

Papan

et al. 2022

IEEE Access

View full text Add to dashboard Cite

New generation networks performance analysis and optimization

Cited by 5 publications

References 0 publications

Machine Learning Based Quantitative Association Rule Mining Method for Evaluating Cellular Network Performance

Machine Learning Based Quantitative Association Rule Mining Method for Evaluating Cellular Network Performance

New Generation Networks Structural Synthesis With Application of Modified Genetic Algorithm

New Advanced Approach for Data Flows Prioritization at an Output of a User Terminal

Contact Info

Product

Resources

About