An Overview on Application of Machine Learning Techniques in Optical Networks
read more
Citations
A Very Brief Introduction to Machine Learning With Applications to Communication Systems
A Survey of Multi-Access Edge Computing in 5G and Beyond: Fundamentals, Technology Integration, and State-of-the-Art
An Optical Communication's Perspective on Machine Learning and Its Applications
Machine learning for network automation: overview, architecture, and applications [Invited Tutorial]
References
Reinforcement Learning: An Introduction
Dropout: a simple way to prevent neural networks from overfitting
Data Mining: Concepts and Techniques
Pattern Recognition and Machine Learning
Related Papers (5)
Machine learning for network automation: overview, architecture, and applications [Invited Tutorial]
Frequently Asked Questions (16)
Q2. What are the contributions mentioned in the paper "An overview on application of machine learning techniques in optical networks" ?
This information can be retrieved from network traffic traces, network alarms, signal quality indicators, users ’ behavioral data, etc. In this paper the authors provide an overview of the application of ML to optical communications and networking. The authors classify and survey relevant literature dealing with the topic, and they also provide an introductory tutorial on ML for researchers and practitioners interested in this field. Although a good number of research papers have recently appeared, the application of ML to optical networks is still in its infancy: to stimulate further work in this area, the authors conclude the paper proposing new possible research directions. Among these mathematical tools, Machine Learning ( ML ) is regarded as one of the most promising methodological approaches to perform network-data analysis and enable automated network self-configuration and fault management.
Q3. What future works have the authors mentioned in the paper "An overview on application of machine learning techniques in optical networks" ?
The authors thus envisage that, after learning from a batch of available past samples, other types of algorithms, in the field of semisupervised and/or unsupervised ML, could be implemented to gradually take in novel input data as they are made available by the network control plane. Under a different perspective, re-training of supervised mechanisms must be investigated to extend their applicability to, e. g., different network infrastructures ( the training on a given topology might not be valid for a different topology ) or to the same network infrastructure at a different point in time ( the training performed in a certain week/month/year might not be valid anymore after some time ). Although, to the best of their knowledge, no specific activity is currently undergoing with dedicated focus on optical networks, it is worth mentioning, e. g., ITU-T focus group on ML [ 122 ], whose activities are concentrated on various aspects of future networking, such as architectures, interfaces, protocols, algorithms and data formats. Finally, an interesting, though speculative, area of future research is the application of ML to all-optical devices and networks.
Q4. What are the successful applications of unsupervised learning methods?
Social network analysis, genes clustering and market research are among the most successful applications of unsupervised learning methods.
Q5. What can be used to extract common traffic patterns in different portions of the network?
unsupervised learning algorithms can be also used to extract common traffic patterns in different portions of the network.
Q6. What is the way to use a limited dataset?
Another option that is very useful in case of a limited dataset is to use cross-validation so that as much of the available data as possible is exploited for training.
Q7. What is the importance of performance monitoring?
With increasing capacity requirements for optical communication systems, performance monitoring is vital to ensure robust and reliable networks.
Q8. What can be used to reduce the amount of monitors to deploy in the system?
To reduce the amount of monitors to deploy in the system, especially at intermediate points of the lightpaths, supervised learning algorithms can be used to learn the mapping between the optical fiber channel parameters and the properties of the detected signal at the receiver, which can be retrieved, e.g., by observing statistics of power eye diagrams, signal amplitude, OSNR, etc.
Q9. What is the advantage of manually providing features to the algorithm?
The advantage of manually providing the features to the algorithm is that the NN can be relatively simple, e.g., consisting of one hidden layer and up to 10 hidden units and does not require large amount of data to be trained.
Q10. What is the common method of calculating the cost of a path?
path computation is performed by using cost-based routing algorithms, such as Dijkstra, Bellman-Ford, Yen algorithms, which rely on the definition of a pre-defined cost metric (e.g., based on the distance between source and destination, the end-to-end delay, the energy consumption, or even a combination of several metrics) to discriminate between alternative paths.
Q11. How many instances of the Bayesian classifier were misclassified?
The effectiveness of the Bayesian classifier is assessed in an experimental testbed: results show that only 0.8% of the tested instances were misclassified.
Q12. What is the main advantage of semi-supervised learning?
According to the classification proposed in [28], semi-supervised learning techniques can be organized in four classes: i) methods based on generative models4; ii) methods based on the assumption that the decision boundary should lie in a low-density region; iii) graph-based methods; iv) two-step methods (first an unsupervised learning step to change the data representation or construct a new kernel; then a supervised learning step based on the new representation or kernel).
Q13. What are the secondary features of the FEELING algorithm?
In context of the FEELING algorithm, some secondary features are also defined in [98] which are linear combinations of the primary features.
Q14. What is the first reference to compare the performance of unsupervised clustering algorithms?
The first reference compares the performance of 6 unsupervised clustering algorithms to discriminate among 5 different formats (i.e. BPSK, QPSK, 8-PSK, 8-QAM, 16-QAM) in terms of True Positive Rate and running time depending on the OSNR at the receiver.
Q15. What is the class of the signal that is suffering from a filter-related failure?
the SVM classifies the signal suffering from filter-related failures into two classes based on whether the failure is due to tight filtering or due to filter shift.
Q16. What is the trade-off between database size and computational time?
The trade-off between database size, computational time and effectiveness of the classification performance is extensively studied: in [40], the technique is shown to outperform state-of-the-art ML algorithms such as Naive Bayes, J48 tree and Random Forests (RFs).