Dynamic reallocation of SLA parameters in passive optical network based on clustering analysis

Frigui, Nejm Eddine; Lemlouma, Tayeb; Gosselin, Stéphane; Radier, Benoît; Meur, Renaud Le; Bonnin, Jean-Marie

doi:10.1109/icin.2018.8401589

Cited by 5 publications

(15 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the trend of using machine learning in the last few years, thoughts are directed towards approaches that have the character of being able to be managed and capable of learning over time. In this context, we have proposed in [1] a new model (Fig.1) for the optimization of PON upstream resources which stems from a very simple idea: analyzing the past customers' behavior based on their historical data to estimate and reallocate their upstream bitrates in the future. Indeed, in daily life, traffic patterns of different users may change several times per day.…”

Section: Related Workmentioning

confidence: 99%

“…In a recent work [1], we have proposed an architecture for optimizing the upstream bandwidth allocation in PON based on the dynamic adjustment of Service Level Agreement (SLA) parameters. The latter represent the input parameters of the DBA algorithm that can be managed by the operator.…”

Section: Introductionmentioning

confidence: 99%

“…In this case, the reallocation of the SLA parameters can be very useful and advantageous in the context of optimizing PON upstream resources for a specific day period. The evaluation phase that we have conducted in [1] was limited to the analysis of the clustering module in order to select which algorithm gives a better distribution of users. In this work, we continue the evaluation of the model that we have proposed in [1] by analysing the assignment index module and its impact on the user classification phase.…”

Section: Introductionmentioning

confidence: 99%

“…The evaluation phase that we have conducted in [1] was limited to the analysis of the clustering module in order to select which algorithm gives a better distribution of users. In this work, we continue the evaluation of the model that we have proposed in [1] by analysing the assignment index module and its impact on the user classification phase. Then, we extend the proposed architecture by adding a forecasting module as a part of a second user classification step that we suggest to be an improvement of the first classification method.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Optimization of the upstream bandwidth allocation in passive optical networks using internet users' behavior forecast

Frigui

Lemlouma

Gosselin

et al. 2018

2018 International Conference on Optical Network Design and Modeling (ONDM)

Self Cite

View full text Add to dashboard Cite

The application of classification techniques based on machine learning approaches to analyze the behavior of network users has interested many researchers in the last years. In a recent work, we have proposed an architecture for optimizing the upstream bandwidth allocation in Passive Optical Network (PON) based on the traffic pattern of each user. Clustering analysis was used in association with an assignment index calculation in order to specify for PON users their upstream data transmission tendency. A dynamic adjustment of Service Level Agreement (SLA) parameters is then performed to maximize the overall customers' satisfaction with the network. In this work, we extend the proposed architecture by adding a prediction module as a complementary to the first classification phase. Grey Model GM(1,1) is used in this context to learn more about the traffic trend of users and improve their assignment. An experimental study is conducted to show the impact of the forecaster and how it can overcome the limits of the initial model.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimization of the upstream bandwidth allocation in passive optical networks using internet users' behavior forecast

Frigui

Lemlouma

Gosselin

et al. 2018

2018 International Conference on Optical Network Design and Modeling (ONDM)

Self Cite

View full text Add to dashboard Cite

show abstract

“…N. E. Frigui et al introduce a bandwidth allocation scheme that uses customer traffic use pattern which they find by doing clustering analysis[32]. They used K-means and DBSCAN clustering methods to have the pattern of usage.…”

mentioning

confidence: 99%

Supporting Diverse Customers and Prioritized Traffic in Next-Generation Passive Optical Networks

Hoque

Ramamurthy

2020

Optical Network Design and Modeling

View full text Add to dashboard Cite

Adviser: Byrav RamamurthyThe already high demand for more bandwidth usage has been growing rapidly.Access network traffic is usually bursty in nature and the present traffic trend is mostly video-dominant. This motivates the need for higher transmission rates in the system. At the same time, the deployment costs and maintenance expenditures have to be reasonable. Therefore, Passive Optical Networks (PON) are considered promising next-generation access technologies. As the existing PON standards are not suitable to support future-PON services and applications, the FSAN (Full Service Access Network) group and the ITU-T (Telecommunication Standardization Sector of the International Telecommunication Union) have worked on developing the NG-PON2 (Next Generation PON 2) standard.Resource allocation is a fundamental task in any PON and it is necessary to have an efficient scheme that reduces delay, maximizes bandwidth usage, and minimizes the resource wastage. A variety of DBA (Dynamic Bandwidth Allocation) and DWBA (Dynamic Wavelength and Bandwidth Allocation) algorithms have been proposed which are based on different PONs (e.g. EPON, GPON, XG-PON, 10G-EPON, etc.). But to our knowledge, no DWBA scheme for NG-PON2 system, with diverse customers and prioritized traffic, has been proposed yet. In this work, this problem is addressed and five different dynamic wavelength and bandwidth allocation (DWBA) schemes are proposed. First, mixed integer linear programming (MILP) models are developed to minimize the total delay of the high priority data. Due to the MILP's high computational complexity, heuristic algorithms are developed based on the MILP model insights. The five heuristics algorithms are: No Block-Split Heuristic (NBH), Equal Block-Split Heuristic (EBH), Priority Based No Block-Split Heuristic (P-NBH), Priority Based Equal Block-Split Heuristic (P-EBH), and Priority Based Decider Block-Split Heuristic (P-DBH). Six priority classes of requests areintroduced with the goal of minimizing the total delay for the high priority data and to lessen the bandwidth wastage of the system. Finally, experiments for the performance evaluation of the five DWBA schemes are conducted. The results show that P-NBH, P-EBH, P-DBH schemes show a 47.63% less delay and 30% of less bandwidth wastage on average for the highest priority data transmission than the schemes without priority support (NBH and EBH). Among these five schemes, NBH method has the highest delay, whereas EBH and P-EBH waste more bandwidth than the other schemes. P-DBH is the most efficient among the five because this scheme offers the lowest delay for high priority data and the minimum bandwidth wastage for lower priority ones. iv ACKNOWLEDGMENTS I would first like to express my gratitude to my supervisor, Dr. Byrav Ramamurthy, for his advice and selfless time. I greatly appreciate the freedom that he has given me to find my own path throughout the thesis.Besides my supervisor, I am also grateful to my thesis committee: Dr. Lisong Xu and Dr. Massimilano Pierobon for their...

show abstract

Dynamic wavelength and bandwidth allocation for supporting diverse customers and prioritized traffic in NG-PON2 networks

Hoque

Ramamurthy

2020

Photon Netw Commun

View full text Add to dashboard Cite

Dynamic reallocation of SLA parameters in passive optical network based on clustering analysis

Cited by 5 publications

References 16 publications

Optimization of the upstream bandwidth allocation in passive optical networks using internet users' behavior forecast

Optimization of the upstream bandwidth allocation in passive optical networks using internet users' behavior forecast

Supporting Diverse Customers and Prioritized Traffic in Next-Generation Passive Optical Networks

Dynamic wavelength and bandwidth allocation for supporting diverse customers and prioritized traffic in NG-PON2 networks

Contact Info

Product

Resources

About