Machine Learning Based Optimal Modulation Format Prediction for Physical Layer Network Planning

Rafique, Danish

doi:10.1109/icton.2018.8473593

Cited by 5 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this use case we instead aim to predict the optimum modulation format based on features such as symbol rate, channel load, number of spans, etc. In particular, we consider various multi-layer perceptron (MLP) architectures and show the performance in terms of classification accuracy and training time [40]. Figure 18 shows the setup considered in this work.…”

Section: Physical Layer Capacity Optimizationmentioning

confidence: 99%

Machine Learning for Network Automation: Overview, Architecture, and Applications [Invited Tutorial]

Rafique

Velasco

2018

J. Opt. Commun. Netw.

Self Cite

258

137

View full text Add to dashboard Cite

Networks are complex interacting systems involving cloud operations, core and metro transport, and mobile connectivity all the way to video streaming and similar user applications. With localized and highly engineered operational tools, it is typical of these networks to take days to weeks for any changes, upgrades, or service deployments to take effect. Machine learning, a sub-domain of artificial intelligence, is highly suitable for complex system representation. In this tutorial paper, we review several machine learning concepts tailored to the optical networking industry and discuss algorithm choices, data and model management strategies, and integration into existing network control and management tools. We then describe four networking case studies in detail, covering predictive maintenance, virtual network topology management, capacity optimization, and optical spectral analysis.

show abstract

Section: Physical Layer Capacity Optimizationmentioning

confidence: 99%

Machine Learning for Network Automation: Overview, Architecture, and Applications [Invited Tutorial]

Rafique

Velasco

2018

J. Opt. Commun. Netw.

Self Cite

258

137

View full text Add to dashboard Cite

show abstract

“…No escopo de inteligência artificial em projetos de links ópticos, o trabalho de Danish Rafique propõe prever o formato de modulação ideal para um enlace ao se utilizar de redes neurais (Rafique, 2018). No presente trabalho pretende-se uma otimização mais abrangente, predizendo com o uso de IA a quantidade de EDFAs e potência de bombeamentos desses amplificadores, como também sua localização e comprimento necessário para a fibra DCF, a fim de corrigir as distorções com o menor uso de equipamentos de regeneração.…”

Section: Aplicações De Inteligência Artificial Em Comunicações óPticasunclassified

Projeto De Links De Fibras Ópticas Usando Técnicas De Inteligência Artificial

Lima¹,

Marques²,

Omar³

et al. 2019

Atas Da Conferência Ibero-Americana WWW/Internet 2019

View full text Add to dashboard Cite

A comunicação digital em nossa sociedade é fortemente baseada em redes interconectadas usando fibras ópticas. Este cenário exige redes melhores com alto desempenho e baixo custo tanto na operação como no projeto da rede. Efeitos lineares e não lineares afetam o desempenho da comunicação em links ópticos e devem ser levados em consideração no projeto do enlace. O presente trabalho propõe a utilização de algoritmos de inteligência artificial (IA) para prever distorções de atenuação, dispersão e efeitos não-lineares em projetos de links ópticos, garantindo sua otimização autônoma. Propomos o uso de IA para o projeto de um enlace de fibra óptica dados a distância, taxa de operação e taxa de erro de bits (BER) requerida. Comparamos a performance de 4 algoritmos de IA (redes Bayesianas, redes neurais perceptron (MLP), KNN, e Deep Learning) e obtivemos acurácias de até 99% e previsão de enlaces otimizados em recursos de amplificação e compensação de dispersão dentro dos parâmetros estabelecidos com a abordagem Deep Learning e KNN.

show abstract

Machine learning-based methods for MCS prediction in 5G networks

Tsipi,

Karavolos,

Papaioannou

et al. 2024

Telecommun Syst

View full text Add to dashboard Cite

In the ever-evolving landscape of wireless communication systems, including fifth-generation (5G) networks and beyond (B5G), accurate Modulation and Coding Scheme (MCS) prediction is crucial for optimizing data transmission efficiency and quality of service. Traditional MCS selection methods rely on predefined rules and heuristics, offering transparency and control but lacking adaptability in changing wireless conditions. The emergence of Machine Learning (ML) has brought transformative capabilities, particularly in MCS prediction. ML leverages data-driven models, promising improved accuracy and adaptability in dynamic wireless environments. This paper marks a novel endeavor in this domain, as it explores and evaluates a range of machine learning (ML) techniques for predicting MCS in orthogonal frequency-division multiplexing (OFDM) systems, representing the first such investigation in this field. Additionally, it introduces a specialized Deep Neural Network (DNN) architecture with two hidden layers for MCS prediction, guided by performance metrics such as accuracy, precision, recall, and F1-score. The examined ML methods include Artificial Neural Networks (ANN), Support Vector Machine (SVM), Random Forest (RF), and Bagging with k-NN (B-kNN). These methods undergo thorough training and evaluation using a dataset generated from simulations of non-standalone 5G networks. The study incorporates physical layer measurements and employs a ray-tracing path loss prediction model for comprehensive environmental characterization. Also, advanced data mining techniques preprocess raw data, addressing model underfitting and overfitting challenges. Finally, performance evaluation results reveal that the ANN with two hidden layers achieves the highest accuracy at 98.71%, while RF and B-kNN methods attain the lowest accuracy, below 88.65%. SVM and ANN models, with one and four hidden layers, respectively, demonstrate comparable MCS prediction accuracy, ranging from 97.02 to 97.30%.

show abstract

Machine Learning Based Optimal Modulation Format Prediction for Physical Layer Network Planning

Cited by 5 publications

References 13 publications

Machine Learning for Network Automation: Overview, Architecture, and Applications [Invited Tutorial]

Machine Learning for Network Automation: Overview, Architecture, and Applications [Invited Tutorial]

Projeto De Links De Fibras Ópticas Usando Técnicas De Inteligência Artificial

Machine learning-based methods for MCS prediction in 5G networks

Contact Info

Product

Resources

About