Limits...
Prediction of Cascading Failures in Spatial Networks.

Shunkun Y, Jiaquan Z, Dan L - PLoS ONE (2016)

Bottom Line: Cascading overload failures are widely found in large-scale parallel systems and remain a major threat to system reliability; therefore, they are of great concern to maintainers and managers of different systems.Fortunately, overload failures that propagate through a network exhibit certain spatial-temporal correlations, which allows the study of a group of nodes that share common spatial and temporal characteristics.We simulated overload failure propagations in a weighted lattice network that start with a center attack and predicted the failure percentages of different groups of nodes that are separated by a given distance.

View Article: PubMed Central - PubMed

Affiliation: School of Reliability and Systems Engineering, Beihang University, Beijing, China.

ABSTRACT
Cascading overload failures are widely found in large-scale parallel systems and remain a major threat to system reliability; therefore, they are of great concern to maintainers and managers of different systems. Accurate cascading failure prediction can provide useful information to help control networks. However, for a large, gradually growing network with increasing complexity, it is often impractical to explore the behavior of a single node from the perspective of failure propagation. Fortunately, overload failures that propagate through a network exhibit certain spatial-temporal correlations, which allows the study of a group of nodes that share common spatial and temporal characteristics. Therefore, in this study, we seek to predict the failure rates of nodes in a given group using machine-learning methods. We simulated overload failure propagations in a weighted lattice network that start with a center attack and predicted the failure percentages of different groups of nodes that are separated by a given distance. The experimental results of a feedforward neural network (FNN), a recurrent neural network (RNN) and support vector regression (SVR) all show that these different models can accurately predict the similar behavior of nodes in a given group during cascading overload propagation.

No MeSH data available.


Related in: MedlinePlus

Average errors and deviations of different sizes of training samples.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4836660&req=5

pone.0153904.g003: Average errors and deviations of different sizes of training samples.

Mentions: To acquire the data used for training and testing, we constructed 100 lattice networks of size 50×50 whose edges were initialized by the Gaussian distribution (1, 0.2). Then, with a tolerance α of [0.2, 0.6, 1.0, 1.4, 1.8, 2.2], where a node will fail if its betweenness is 1 + α times higher than its initial value, we calculated the cascading process of the constructed lattice networks that exhibit different edge weight distributions. Thus, for each α, we have 100 groups of cascading failure data. Because different α values present different laws in the cascading failure process, we first attempt to train and test data for a given α. In this study, we performed certain pre-tests to choose the size of the training samples. With α = 1.0, we trained several RNN models with training samples of different sizes that ranged from 30 to 60. Then, we tested the models using the same five groups of data, which were not included in any training dataset. The average errors of each model and its deviation (Fig 3) showed that the average error of the model not markedly declined as the number of training samples increased. However, the model trained with 45 samples became unstable because its deviation was larger than those of the other models. If the unstable models performed well, the model trained by other sample sizes would also perform well. Therefore, we decided to train the proposed models using 45 samples.


Prediction of Cascading Failures in Spatial Networks.

Shunkun Y, Jiaquan Z, Dan L - PLoS ONE (2016)

Average errors and deviations of different sizes of training samples.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4836660&req=5

pone.0153904.g003: Average errors and deviations of different sizes of training samples.
Mentions: To acquire the data used for training and testing, we constructed 100 lattice networks of size 50×50 whose edges were initialized by the Gaussian distribution (1, 0.2). Then, with a tolerance α of [0.2, 0.6, 1.0, 1.4, 1.8, 2.2], where a node will fail if its betweenness is 1 + α times higher than its initial value, we calculated the cascading process of the constructed lattice networks that exhibit different edge weight distributions. Thus, for each α, we have 100 groups of cascading failure data. Because different α values present different laws in the cascading failure process, we first attempt to train and test data for a given α. In this study, we performed certain pre-tests to choose the size of the training samples. With α = 1.0, we trained several RNN models with training samples of different sizes that ranged from 30 to 60. Then, we tested the models using the same five groups of data, which were not included in any training dataset. The average errors of each model and its deviation (Fig 3) showed that the average error of the model not markedly declined as the number of training samples increased. However, the model trained with 45 samples became unstable because its deviation was larger than those of the other models. If the unstable models performed well, the model trained by other sample sizes would also perform well. Therefore, we decided to train the proposed models using 45 samples.

Bottom Line: Cascading overload failures are widely found in large-scale parallel systems and remain a major threat to system reliability; therefore, they are of great concern to maintainers and managers of different systems.Fortunately, overload failures that propagate through a network exhibit certain spatial-temporal correlations, which allows the study of a group of nodes that share common spatial and temporal characteristics.We simulated overload failure propagations in a weighted lattice network that start with a center attack and predicted the failure percentages of different groups of nodes that are separated by a given distance.

View Article: PubMed Central - PubMed

Affiliation: School of Reliability and Systems Engineering, Beihang University, Beijing, China.

ABSTRACT
Cascading overload failures are widely found in large-scale parallel systems and remain a major threat to system reliability; therefore, they are of great concern to maintainers and managers of different systems. Accurate cascading failure prediction can provide useful information to help control networks. However, for a large, gradually growing network with increasing complexity, it is often impractical to explore the behavior of a single node from the perspective of failure propagation. Fortunately, overload failures that propagate through a network exhibit certain spatial-temporal correlations, which allows the study of a group of nodes that share common spatial and temporal characteristics. Therefore, in this study, we seek to predict the failure rates of nodes in a given group using machine-learning methods. We simulated overload failure propagations in a weighted lattice network that start with a center attack and predicted the failure percentages of different groups of nodes that are separated by a given distance. The experimental results of a feedforward neural network (FNN), a recurrent neural network (RNN) and support vector regression (SVR) all show that these different models can accurately predict the similar behavior of nodes in a given group during cascading overload propagation.

No MeSH data available.


Related in: MedlinePlus