• Corpus ID: 246411433

RiskNet: Neural Risk Assessment in Networks of Unreliable Resources

@article{Rusek2022RiskNetNR,
  title={RiskNet: Neural Risk Assessment in Networks of Unreliable Resources},
  author={Krzysztof Rusek and Piotr Borylo and Piotr Jaglarz and Fabien Geyer and Albert Cabellos and Piotr Chołda},
  journal={ArXiv},
  year={2022},
  volume={abs/2201.12263}
}
We propose a graph neural network (GNN)-based method to predict the distribution of penalties induced by outages in communication networks, where connections are protected by resources shared between working and backup paths. The GNN-based algorithm is trained only with random graphs generated with the Barabási–Albert model. Even though, the obtained test results show that we can precisely model the penalties in a wide range of various existing topologies. GNNs eliminate the need to simulate… 

References

SHOWING 1-10 OF 19 REFERENCES

Effective Risk Assessment in Resilient Communication Networks

Business impact analysis in the context of resilient communication networks shows that, in practice, disadvantages do not appear in resilient network design, and $$VaR$$VaR can be used without the need to apply more complex and less informative measures.

DeepComNet: Performance evaluation of network topologies using graph-based deep learning

DeepTMA: Predicting Effective Contention Models for Network Calculus using Graph Neural Networks

A novel framework combining graph-based deep learning and Network Calculus models, called DeepTMA, is derived, which achieves provably valid bounds that are very competitive with TMA.

Analysis of Dependencies between Failures in the UNINETT IP Backbone Network

Analysis of failure logs to identify simultaneous and potentially correlated failures in routers and links of an IP backbone network shows that the actual behavior of failure processes does not support the independence assumption commonly used in theoretical studies.

Risk Management in customs using Deep Neural Network

  • R. RegmiArun K. Timalsina
  • Economics
    2018 IEEE 3rd International Conference on Computing, Communication and Security (ICCCS)
  • 2018
Deep learning has improved accuracy and seizure rate than that of decision Tree (DT) and Support Vector Machine (SVM) and all three methods have achieved a better result than current rule based risk management system.

On/off process modeling of IP network failures

  • P. KuuselaI. Norros
  • Computer Science
    2010 IEEE/IFIP International Conference on Dependable Systems & Networks (DSN)
  • 2010
A reliability model for IP networks is considered, where the routers and links are modeled by independent stationary on/off processes, which allows the derivation of on-off processes describing with high accuracy the IP-availability delivered to customers of each access router.

Learning about risk: Machine learning for risk assessment

Reliability modeling and analysis of communication networks

AIRMS: A risk management tool using machine learning

Deep Sets

The main theorem characterizes the permutation invariant objective functions and provides a family of functions to which any permutation covariant objective function must belong, which enables the design of a deep network architecture that can operate on sets and which can be deployed on a variety of scenarios including both unsupervised and supervised learning tasks.