On yield, fault distributions, and clustering of particles
IBM Journal of Research and Development
Broadcasting with random faults
Discrete Applied Mathematics
Modeling Defect Spatial Distribution
IEEE Transactions on Computers
Highly-resilient, energy-efficient multipath routing in wireless sensor networks
ACM SIGMOBILE Mobile Computing and Communications Review
Using Network Fault Predictions to Enable IP Traffic Management
Journal of Network and Systems Management
A Clustered Failure Model for the Memory Array Reconfiguration Problem
IEEE Transactions on Computers
Sparse networks supporting efficient reliable broadcasting
Nordic Journal of Computing
Predicting Defect-Tolerant Yield in the Embedded Core Context
IEEE Transactions on Computers
Efficient Exact Spare Allocation via Boolean Satisfiability
DFT '05 Proceedings of the 20th IEEE International Symposium on Defect and Fault Tolerance in VLSI Systems
Deterministic Models of Communication Faults
MFCS '08 Proceedings of the 33rd international symposium on Mathematical Foundations of Computer Science
Communication in Random Geometric Radio Networks with Positively Correlated Random Faults
ADHOC-NOW '08 Proceedings of the 7th international conference on Ad-hoc, Mobile and Wireless Networks
| Hi-index | 0.00 |
The aim of this paper is to study communication in networks where nodes fail in a random dependent way. In order to capture fault dependencies, we introduce the neighborhood fault model, where damaging events, called spots, occur randomly and independently with probability p at nodes of a network, and cause faults in the given node and all of its neighbors. Faults at distance at most 2 become dependent in this model and are positively correlated. We investigate the impact of spot probability on feasibility and time of communication in the fault-free part of the network. We show a network which supports fast communication with high probability, if p = 1/c log n. We also show that communication is not feasible with high probability in most classes of networks, for constant spot probabilities. For smaller spot probabilities, high probability communication is supported even by bounded degree networks. It is shown that the torus supports communication with high probability when p decreases faster than 1/n1/2, and does not when p ? 1/O(n1/2). Furthermore, a network built of tori is designed, with the same faulttolerance properties and additionally supporting fast communication. We show, however, that networks of degree bounded by a constant d do not support communication with high probability, if p ? 1/O(n1/d). While communication in networks with independent faults was widely studied, this is the first analytic paper which investigates network communication for random dependent faults.