Dynamic Spectrum Assignment in Passive Optical Networks Based on Optical Integrated Microring Resonators Using Machine Learning and a Routing, Modulation Level, and Spectrum Assignment Method
The rising demand for bandwidth in optical communication networks has led to the need for more efficient solutions for spectrum allocation. This article presents a solution to enhance the capacity and efficiency of passive optical networks (PON) using optical microring resonators and dynamic spectru...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/24/13294 |
| _version_ | 1797382079656230912 |
|---|---|
| author | Andrés F. Calvo-Salcedo Neil Guerrero González Jose A. Jaramillo-Villegas |
| author_facet | Andrés F. Calvo-Salcedo Neil Guerrero González Jose A. Jaramillo-Villegas |
| author_sort | Andrés F. Calvo-Salcedo |
| collection | DOAJ |
| description | The rising demand for bandwidth in optical communication networks has led to the need for more efficient solutions for spectrum allocation. This article presents a solution to enhance the capacity and efficiency of passive optical networks (PON) using optical microring resonators and dynamic spectrum allocation. The solution relies on wavelength division multiplexing (WDM). It proposes using a support vector machine (SVM) and a Routing, Modulation Level, and Spectrum Assignment (RMLSA) method to manage spectrum allocation based on the bandwidth and distance of multiple requests. The network employs a pulse shaper to physically allocate the spectrum, allowing for the separation of the spectrum generated by the microring resonators into different wavelengths or wavelength ranges (super-channel). Additionally, the SVM and RMLSA algorithms regulate the pulse shaper to execute the allocation. This photonic network achieves improved spectrum utilization and reduces the network blocking probability. Our proposal shows that we successfully addressed 1090 requests with a zero blocking probability, accounting for 81% of the total requests. These request scenarios can simultaneously accommodate up to 200 requests, with a maximum bandwidth of 31 THz. This highlights the efficacy of our approach in efficiently managing requests with substantial processing capacity. |
| first_indexed | 2024-03-08T21:01:18Z |
| format | Article |
| id | doaj.art-192f506de7e2456e8f2f4567e9ea6a75 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-08T21:01:18Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-192f506de7e2456e8f2f4567e9ea6a752023-12-22T13:52:09ZengMDPI AGApplied Sciences2076-34172023-12-0113241329410.3390/app132413294Dynamic Spectrum Assignment in Passive Optical Networks Based on Optical Integrated Microring Resonators Using Machine Learning and a Routing, Modulation Level, and Spectrum Assignment MethodAndrés F. Calvo-Salcedo0Neil Guerrero González1Jose A. Jaramillo-Villegas2Faculty of Engineering, Universidad Tecnológica de Pereira, Pereira 660003, ColombiaFaculty of Engineering, Universidad Nacional de Colombia, Manizales 170002, ColombiaFaculty of Engineering, Universidad Tecnológica de Pereira, Pereira 660003, ColombiaThe rising demand for bandwidth in optical communication networks has led to the need for more efficient solutions for spectrum allocation. This article presents a solution to enhance the capacity and efficiency of passive optical networks (PON) using optical microring resonators and dynamic spectrum allocation. The solution relies on wavelength division multiplexing (WDM). It proposes using a support vector machine (SVM) and a Routing, Modulation Level, and Spectrum Assignment (RMLSA) method to manage spectrum allocation based on the bandwidth and distance of multiple requests. The network employs a pulse shaper to physically allocate the spectrum, allowing for the separation of the spectrum generated by the microring resonators into different wavelengths or wavelength ranges (super-channel). Additionally, the SVM and RMLSA algorithms regulate the pulse shaper to execute the allocation. This photonic network achieves improved spectrum utilization and reduces the network blocking probability. Our proposal shows that we successfully addressed 1090 requests with a zero blocking probability, accounting for 81% of the total requests. These request scenarios can simultaneously accommodate up to 200 requests, with a maximum bandwidth of 31 THz. This highlights the efficacy of our approach in efficiently managing requests with substantial processing capacity.https://www.mdpi.com/2076-3417/13/24/13294optical communicationspassive optical networksmicroring resonatoroptical frequency combspectrum allocation |
| spellingShingle | Andrés F. Calvo-Salcedo Neil Guerrero González Jose A. Jaramillo-Villegas Dynamic Spectrum Assignment in Passive Optical Networks Based on Optical Integrated Microring Resonators Using Machine Learning and a Routing, Modulation Level, and Spectrum Assignment Method Applied Sciences optical communications passive optical networks microring resonator optical frequency comb spectrum allocation |
| title | Dynamic Spectrum Assignment in Passive Optical Networks Based on Optical Integrated Microring Resonators Using Machine Learning and a Routing, Modulation Level, and Spectrum Assignment Method |
| title_full | Dynamic Spectrum Assignment in Passive Optical Networks Based on Optical Integrated Microring Resonators Using Machine Learning and a Routing, Modulation Level, and Spectrum Assignment Method |
| title_fullStr | Dynamic Spectrum Assignment in Passive Optical Networks Based on Optical Integrated Microring Resonators Using Machine Learning and a Routing, Modulation Level, and Spectrum Assignment Method |
| title_full_unstemmed | Dynamic Spectrum Assignment in Passive Optical Networks Based on Optical Integrated Microring Resonators Using Machine Learning and a Routing, Modulation Level, and Spectrum Assignment Method |
| title_short | Dynamic Spectrum Assignment in Passive Optical Networks Based on Optical Integrated Microring Resonators Using Machine Learning and a Routing, Modulation Level, and Spectrum Assignment Method |
| title_sort | dynamic spectrum assignment in passive optical networks based on optical integrated microring resonators using machine learning and a routing modulation level and spectrum assignment method |
| topic | optical communications passive optical networks microring resonator optical frequency comb spectrum allocation |
| url | https://www.mdpi.com/2076-3417/13/24/13294 |
| work_keys_str_mv | AT andresfcalvosalcedo dynamicspectrumassignmentinpassiveopticalnetworksbasedonopticalintegratedmicroringresonatorsusingmachinelearningandaroutingmodulationlevelandspectrumassignmentmethod AT neilguerrerogonzalez dynamicspectrumassignmentinpassiveopticalnetworksbasedonopticalintegratedmicroringresonatorsusingmachinelearningandaroutingmodulationlevelandspectrumassignmentmethod AT joseajaramillovillegas dynamicspectrumassignmentinpassiveopticalnetworksbasedonopticalintegratedmicroringresonatorsusingmachinelearningandaroutingmodulationlevelandspectrumassignmentmethod |