Estimation of all-terminal network reliability using an artificial neural network

Computers and Operations Research

Volumn 29, Issue 7, 2002, Pages 849-868

  Srivaree Ratana, Chat ^a   Konak, Abdullah ^a   Smith, Alice E ^a  

^a AUBURN UNIVERSITY   (United States)

Author keywords

Network design; Network reliability; Neural network; Simulated annealing

Indexed keywords

COMPUTER SIMULATION; MONTE CARLO METHODS; NEURAL NETWORKS; OPERATIONS RESEARCH; RELIABILITY;

OPTIMAL NETWORK DESIGN;

COMPUTER AIDED NETWORK ANALYSIS;

ARTIFICIAL NEURAL NETWORK;

EID: 0036604737     PISSN: 03050548     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0305-0548(00)00088-5     Document Type: Article

References (27)

1. Topological optimization of a communication network subject to a reliability constraint
2. Topological layout of links for optimising the overall reliability in a computer communication system
3. Network topology for maximizing the terminal reliability in a computer communication network
4. Heuristic optimization of network design considering all-terminal reliability
5. Economic design of reliable networks
6. Efficient optimization of all-terminal reliable networks using an evolutionary approach
7. Local search genetic algorithm for optimal design of reliable networks
8. Topological optimization of communication networks subject to reliability constraints
9. Backtracking algorithms for network reliability analysis
10. Reliability evaluation in computer-communication networks
11. Cutset manipulations for communication network reliability estimation
12. A cutset approach to reliability evaluation in communication networks
13. The complexity of counting cuts and of computing the probability that a graph is connected
14. A Monte Carlo sampling plan for estimating network reliability
15. A new Monte Carlo method for estimating network reliability
16. Neural networks: A review from a statistical perspective
17. Neural networks and the bias/variance dilemma
18. On the approximate realization of continuous mappings by neural networks
19. Multilayer feedforward networks are universal approximators
20. Connectionist nonparametric regression: Multilayer feedforward networks can learn arbitrary mappings
21. Solving the redundancy allocation problem using a combined neural network/genetic algorithm approach
22. A general upperbound for all-terminal network reliability and its uses
23. Design of reliable networks
24. Bias and variance of validation methods for function approximation neural networks under conditions of sparse data