We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
A Modified Wavenet-Based Link Status Predictor for Computer Networks.
- Authors
Abdul-Jabbar, Jassim M.; Hazim, Omar A.
- Abstract
In this paper, a modified wavelet neural network (WNN) (or wavenet)-based predictor is introduced to predict link status (congestion with load indication) of each link in the computer network. On the contrary of previous wavenet-based predictors, the proposed modified wavenet-based link state predictor (MWBLSP) generates two indicating outputs for congestion and load status of each link based on the premeasured power burden (square values) of utilization on each link in the previous time intervals. Fortunately, WNNs possess all learning and generalization capabilities of traditional neural networks. In addition, the ability of such WNNs are efficiently enhanced by the local characteristics of wavelet functions to deal with sudden changes and burst network load. The use of power burden utilization at the predictor input supports some non-linear distributions of the predicted values in a more efficient manner. The proposed MWBLSP predictor can be used in the context of active congestion control and link load balancing techniques to improve the performance of all links in the network with best utilization of network resources.
- Subjects
COMPUTER networks; ARTIFICIAL neural networks; LOGICAL prediction; NONLINEAR analysis; DISTRIBUTION (Probability theory); GENERALIZATION
- Publication
Iraqi Journal for Electrical & Electronic Engineering, 2013, Vol 9, Issue 1, p49
- ISSN
1814-5892
- Publication type
Article