System Reliability of a Modern Distributed Network with Node Failure and Budget Consideration Using Analytical Algorithm and Deep Learning Model

Abstract

Cloud and edge computing are necessary elements in the modern distributed network. To reflect the capacity variances of the system, stochastic capacities and costs of components (arcs and nodes) are considered such that stochastic capacity distributed networks (SCDNs) can be formed in the paper. To learn the capability of the SCDN for system monitoring and management, system reliability can be utilized which is defined as the probability of satisfying demands (data) under a budget for an SCDN. An exact-system reliability algorithm for system reliability is derived in advance for prudent management and decision-making. For immediate control and management, a deep neural network (DNN) architecture is proposed to create a prediction model for system reliability. Enough data points about SCDN information are generated and transformed into an appropriate format for training the prediction model. Note that the labels (system reliability) for all the data points would be calculated using the exact-system reliability algorithm. Necessary hyperparameters for determining the DNN of system reliability of the SCDN are also suggested. The model can be used for the future management of the distributed network.