Machine learning based Call Admission Control approaches: A comparative study

Bashar, Abul; Parr, Gerard; McClean, Sally; Scotney, Bryan; Nauck, Detlef

doi:10.1109/cnsm.2010.5691261

Cited by 13 publications

(3 citation statements)

References 9 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Typically, machine learning techniques, such as Q-learning [5], help implement the adaptation methods of self-configuration and self-management in the autonomic computing paradigm. Recent work further reinforces the efficacy of leveraging machine learning for network management task optimization [6][7][8][9].…”

Section: Introductionmentioning

confidence: 67%

Self‐adapting protocol tuning for multi‐hop wireless networks using Q‐learning

Marconett

Lee

et al. 2012

Int J Network Mgmt

View full text Add to dashboard Cite

SUMMARYToday's network control systems have very limited ability to adapt to changing network conditions. The addition of reinforcement learning-based network management agents can improve quality of service by reconfiguring the network layer protocol parameters in response to observed network performance conditions. This paper presents a closed-loop approach to tuning the layer three protocol based upon current and previous network state observations, specifically the Hello Interval and Active Route Timeout parameters of the AODV routing protocol (AODV-Q). Simulation results demonstrate that the self-configuration method proposed here demonstrably improves the performance of the original Ad-Hoc On-Demand Distance Vector (AODV) protocol, reducing protocol overhead by 43% and end-to-end delay 29% while increasing the packet delivery ratio by up to 11%.

show abstract

Section: Introductionmentioning

confidence: 67%

Self‐adapting protocol tuning for multi‐hop wireless networks using Q‐learning

Marconett

Lee

et al. 2012

Int J Network Mgmt

View full text Add to dashboard Cite

show abstract

“…There exist many heuristic algorithms for this problem, and also ML has been applied, e.g., leveraging Supervised Learning (SL) methods [9]- [13] for estimation of performance metrics or Reinforcement Learning (RL) for admission policy optimization [14]- [16]. Bashar et al [12] give a concrete example for an SL approach. They compare the performance of Neural Networks and Bayesian Networks to estimate Quality of Service metrics, such as delay or packet loss, that are used as input to the CAC algorithm.…”

Section: A Call Admission Controlmentioning

confidence: 99%

Ismael: Using Machine Learning to Predict Acceptance of Virtual Clusters in Data Centers

Zerwas

Kalmbach

Schmid

et al. 2019

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

Existing virtual network admission control algorithms targeting high utilization of data center infrastructure are computationally expensive or provide poor performance. In particular, existing algorithms have in common that they are oblivious to the past, i.e., requests are handled in a fireand-forget manner, not taking into account information from previously solved instances. This can be inefficient and misses out on a basic optimization opportunity: as for any network optimization algorithm that faces repeating problem instances, it may be beneficial to learn from network states and the outcome of acceptance decisions of the past. In this paper, we propose ISMAEL, a Machine Learning framework for predicting the acceptance of Virtual Clusters, one of the most common virtual network abstractions in data centers. ISMAEL can be configured with, and learn from, different existing algorithms by combining fixed-size feature representations for graphs with a Convolutional Neural Network or a Fully Connected Deep Neural Network. We report on extensive simulations, which demonstrate that it is possible to mimic existing, computationally-intensive admission control algorithms with an accuracy of up to 94 %, while significantly reducing runtime.

show abstract

“…This study used the Machine Learning application, since they can model the behavior of the system through the learning process, based on observing performance data over a period. Once properly trained, they can automatically estimate and predict future system behavior and subsequently make admission decisions with high accuracy and speed [21].…”

Section: Artificial Intelligencementioning

confidence: 99%