The goal of energy cost-aware routing and wavelength assignment (RWA) is to minimize the total electricity expenditure in an optical network. While effective, simply aiming to reduce the electricity consumed does not necessarily mitigate the environmental impact. A new approach is required to simultaneously reduce both the electricity cost and emissions produced as a by-product of RWA. We present a method for doing so through the use of mixed-integer linear programming (MILP), which can find the optimal solution that minimizes the electricity cost of RWA for a static set of requests while keeping emissions under a specified cap. This objective is quantitatively compared to alternative goals, including directly minimizing the emissions produced, reducing the length of established paths, and balancing reductions in both emissions and electricity cost simultaneously. As MILP computation is costly and the results are required in near real time to react to changing prices, we present a solution that employs a well-known supervised machine learning algorithm, logistic regression, that predicts the cost saving paths in real time. Using a dataset of 808,024 records (70% for training and 30% for testing) output from the MILP, we find that this logistic regression model predicts the most cost-efficient path with 92.5% accuracy.
© 2018 Optical Society of AmericaFull Article | PDF Article
23 October 2018: A typographical correction was made to the author affiliations.
23 October 2018: A typographical correction was made to the abstract.
23 October 2018: Typographical corrections were made to paragraph 4 of page D81
23 October 2018: A correction was made to Ref. 39.
More Like This
Arash Deylamsalehi, Yan Cui, Pegah Afsharlar, and Vinod M. Vokkarane
J. Opt. Commun. Netw. 9(4) 257-274 (2017)
Xiaoliang Chen, Zuqing Zhu, Jiannan Guo, Sheng Kang, Roberto Proietti, Alberto Castro, and S. J. B. Yoo
J. Opt. Commun. Netw. 10(2) A232-A240 (2018)
Roberto Proietti, Xiaoliang Chen, Kaiqi Zhang, Gengchen Liu, M. Shamsabardeh, Alberto Castro, Luis Velasco, Zuqing Zhu, and S. J. Ben Yoo
J. Opt. Commun. Netw. 11(1) A1-A10 (2019)