| 1. |
|
|
| 2. |
- Kehoe, Laura, et al.
(author)
-
Make EU trade with Brazil sustainable
- 2019
-
In: Science. - : American Association for the Advancement of Science (AAAS). - 0036-8075 .- 1095-9203. ; 364:6438, s. 341-
-
Journal article (other academic/artistic)
|
|
| 3. |
|
|
| 4. |
- Etezadi, Ehsan, 1993, et al.
(author)
-
Deep reinforcement learning for proactive spectrum defragmentation in elastic optical networks [Invited]
- 2023
-
In: Journal of Optical Communications and Networking. - 1943-0620 .- 1943-0639. ; 15:10, s. E86-E96
-
Journal article (peer-reviewed)abstract
- The immense growth of Internet traffic calls for advanced techniques to enable the dynamic operation of optical networks, efficient use of spectral resources, and automation. In this paper, we investigate the proactive spectrum defragmentation (SD ) problem in elastic optical networks and propose a novel deep reinforcement learning-based framework DeepDefrag to increase spectral usage efficiency. Unlike the conventional, often threshold-based heuristic algorithms that address a subset of the defragmentation related tasks and have limited automation capabilities, DeepDefrag jointly addresses the three main aspects of the SD process: determining when to perform defragmentation, which connections to reconfigure, and which part of the spectrum to reallocate them to. By considering services attributes, spectrum occupancy state expressed by several different fragmentation metrics, as well as reconfiguration cost, DeepDefragmis able to consistently select appropriate reconfiguration actions over the network lifetime and adapt to changing conditions. Extensive simulation results reveal superior performance of the proposed scheme over a scenario with exhaustive defragmentation and a well-known benchmark heuristic from the literature, achieving lower blocking probability at a smaller defragmentation overhead.
|
|
| 5. |
- Etezadi, Ehsan, 1993, et al.
(author)
-
DeepDefrag: A deep reinforcement learning framework for spectrum defragmentation
- 2022
-
In: 2022 IEEE Global Communications Conference, GLOBECOM 2022 - Proceedings. ; , s. 3694-3699
-
Conference paper (peer-reviewed)abstract
- Exponential growth of bandwidth demand, spurred by emerging network services with diverse characteristics and stringent performance requirements, drives the need for dynamic operation of optical networks, efficient use of spectral resources, and automation. One of the main challenges of dynamic, resource-efficient Elastic Optical Networks (EONs) is spectrum fragmentation. Fragmented, stranded spectrum slots lead to poor resource utilization and increase the blocking probability of incoming service requests. Conventional approaches for Spectrum Defragmentation (SD) apply various criteria to decide when, and which portion of the spectrum to defragment. However, these polices often address only a subset of tasks related to defragmentation, are not adaptable, and have limited automation potential. To address these issues, we propose DeepDefrag, a novel framework based on reinforcement learning that addresses the main aspects of the SD process: determining when to perform defragmentation, which connections to reconfigure, and which part of the spectrum to reallocate them to. DeepDefrag outperforms the well-known Older-First First-Fit (OF-FF) defragmentation heuristic, achieving lower blocking probability under smaller defragmentation overhead.
|
|
| 6. |
|
|
| 7. |
- Etezadi, Ehsan, 1993, et al.
(author)
-
Proactive Spectrum Defragmentation Leveraging Spectrum Occupancy State Information
- 2023
-
In: International Conference on Transparent Optical Networks. - 2162-7339. ; 2023-July
-
Conference paper (peer-reviewed)abstract
- One of the main obstacles to efficient resource usage under dynamic traffic in elastic optical networks (EONs) is spectrum fragmentation (SF), leading to blocking of incoming service requests. Proactive spectrum defragmentation (SD) approaches periodically reallocate services to ensure better alignment of available spectrum slots across different links and alleviate blocking. The services for reallocation are commonly selected based on their properties, e.g., age, without detailed consideration of prior or posterior spectrum occupancy states. In this paper, we propose a heuristic algorithm for proactive SD that considers different spectrum fragmentation metrics to select services for reallocation. We analyze the relationship between these metrics and the resulting service blocking probability. Simulation results show that the proposed heuristic outperforms the benchmarking proactive SD algorithms from the literature in reducing blocking probability.
|
|
