Energy-Efficient Lightpath Establishment in Backbone Optical Networks Based on Ant Colony Optimization

Abstract

Energy-aware lightpath routing and establishment in optical backbone networks can reduce energy consumption while preserving performance levels. A heuristic method based on Ant Colony Optimization (suitable for both network planning and operation) is proposed that reduces network's energy footprint by exploiting the basic principles of Swarm Intelligence for finding the most energy-efficient routes from source to the destination node per traffic request and at the same time, for reducing computational complexity to a polynomial level. The reduction of energy consumption is achieved in comparison to other related heuristics under representative backbone network topologies and their actual traffic demand. IP over WDM optical networks are considered for evaluating the performance along with the next generation elastic networks.

Artificial intelligence (AI) methods in optical networks: A comprehensive survey

“…Ant colony optimization [9]: RWA solution with great robustness and adaptability to varying network and traffic conditions. [81]: reduces network's energy footprint by finding the most energy-efficient routes. [82]: introduces a heuristic on the way ants choose a request from demand space in order to find the shortest path.…”

“…Simulation results indicate that taking advantage of similar past experiences or cases stored in a knowledge base (KB) can reduce computational time by 25% over classical RWA algorithms, while maintaining or even improving performance. In addition, Kyriakopoulos et al [81] propose a heuristic method based on ACO to reduce network energy footprint by exploiting the basic principles of swarm intelligence for finding the most energy-efficient routes from source to the destination node per traffic request. A different ACO-based proposal [82], which introduces a heuristic on the way ants choose a request from demand space (those that can be served with shorter route first), outperforms both regular ACO and shortestpath and most-used algorithms.…”

Towards energy efficiency in virtual topology design of elastic optical networks

“…The ACO‐Split Bypass method is developed for IP‐over‐WDM networks but is also extended to support IP‐over‐EON. It has the ability to save energy in typical backbone topologies, but due to the ACO core it is based upon, in very large topologies as well.…”

“…Also, it concentrates on a simple implementation with the optical grooming being extensively exploited. The previous work relates to the energy‐efficient VT design of mid‐to‐large backbone topologies mainly in conventional WDM (Wavelength Division Multiplexing) architectures. The computational complexity is confronted by the use of Ant Colony Optimization (ACO) principles.…”

Evolution towards Smart Optical Networking: Where Artificial Intelligence (AI) meets the World of Photonics

“…Genetic Algorithms (GA) are one of the popular algorithms in optical networking among many evolutionary algorithms discovered and designed for optimizing complex systems, which has been used extensively and in a myriad network design problems. Swarm based systems have also been used to solve network optimization problems: [8] proposed a heuristic method based on ant colony optimization to reduce network energy footprint, whereas [9] presented a comparative study among three multi-objective evolutionary algorithms (MOEAs) based on swarm intelligence to solve the RWA problem in optical networks. We expect that the increasing bandwidth requirements will demand network optimization as a core network feature, while the introduction of flex-grid optics, sliceable variable bandwidth transponders and other emerging optical technologies will further increase the computational complexity of the optimization problem.…”