WDM Optical Network Reconfiguration Using Automated Regression-Based Parameter Value Selection
Oh la la
Your session has expired but don’t worry, your message
has been saved.Please log in and we’ll bring you back
to this page. You’ll just need to click “Send”.
Your evaluation is of great value to our authors and readers. Many thanks for your time.
When you're done, click "publish"
Only blue fields are mandatory.
Your mailing list is currently empty.
It will build up as you send messages
and links to your peers.
besides you has access to this list.
Enter the e-mail addresses of your recipients in the box below. Note: Peer Evaluation will NOT store these email addresses log in
Your message has been sent.
Full text for this article was not available? Send a request to the author(s)
: WDM Optical Network Reconfiguration Using Automated Regression-Based Parameter Value Selection
Abstract : A key feature of optical networks based on wavelength division multiplexing (WDM) technology is the ability to optimize the configuration of optical resources, i.e. wavelengths, with respect to a particular traffic demand. In the broadcast architecture, this involves the assignment of wavelengths to logical links, while in the switched architecture it additionally involves the routing of bandwidth-guaranteed circuits known as lightpaths. This paper is concerned with the problem of automatically updating the configuration of an optical network in response to changes in traffic demand, which entails making a reconfiguration policy decision, selecting a new configuration, and migrating from the current to the new configuration. A technique is proposed that automatically selects values for parameters inherent in reconfiguration algorithms and reconfiguration policies, with the goal of maximizing the long-term performance gain due to reconfiguration. The effectiveness of the technique is evaluated in the context of a threshold-based reconfiguration policy. In the best case, the technique is shown to perform only 4% worse than a carefully chosen combination of static parameter values. However, a simple random assignment of parameter values is shown to perform equally well.
: Computer Science
Leave a comment
This contribution has not been reviewed yet. review?