Modeling and Control of Priority Queueing in Software Defined Networks via Machine Learning
Software Defined Networking (SDN) is a new architectural paradigm that enables programmable control of a network to make it more flexible and easier to manage. SDN architectures decouple control and forwarding functionalities, and enable switches and routers to be remotely configurable/programmable...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9868133/ |
| _version_ | 1811268405559296000 |
|---|---|
| author | Enrico Reticcioli Giovanni Domenico Di Girolamo Francesco Smarra Angelo Torzi Fabio Graziosi Alessandro D'innocenzo |
| author_facet | Enrico Reticcioli Giovanni Domenico Di Girolamo Francesco Smarra Angelo Torzi Fabio Graziosi Alessandro D'innocenzo |
| author_sort | Enrico Reticcioli |
| collection | DOAJ |
| description | Software Defined Networking (SDN) is a new architectural paradigm that enables programmable control of a network to make it more flexible and easier to manage. SDN architectures decouple control and forwarding functionalities, and enable switches and routers to be remotely configurable/programmable in run-time by a controller. Modeling and optimization of such modern heterogeneous network infrastructures are key factors to achieve better performance, e.g. in terms of traffic flow improvement while reducing bandwidth allocation. Identifying an accurate model of a network device in SDNs (e.g., a switch or a router) is crucial in order to apply advanced techniques such as Model Predictive Control (MPC). However, such a problem is very challenging due to non-linearities and unavailability of internal variables measurements in real devices. To this aim, a promising direction is given by an appropriate integration of System Identification and Machine Learning techniques to obtain predictive models using historical data collected from the network thanks to the SDN paradigm. In this paper we apply a novel data-driven methodology to learn accurate models of the dynamical input-output behavior of a network’s switch device by appropriately combining AutoRegressive eXogenous (ARX) model identification with Regression Trees (RTs) and Random Forests (RFs). The advantage of such model is that it can be directly used to apply MPC (which just requires Quadratic Programming to be solved) to optimally control the queues’ bandwidth of the switch ports within the SDN paradigm. We validate our approach on an experimental emulation setup using the Mininet network emulator environment and a real dataset obtained from measurements of an Italian Internet Service Provider (Sonicatel S.r.l.). To this aim, we first develop a model of a real network switch, then implement MPC using the RYU controller, and finally demonstrate the benefits of the proposed dynamic queueing control methodology in terms of packet losses reduction and bandwidth saving, i.e. in terms of improvement of the Quality of Service. |
| first_indexed | 2024-04-12T21:21:14Z |
| format | Article |
| id | doaj.art-32327c028c4c48d2a620eaf471491932 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T21:21:14Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-32327c028c4c48d2a620eaf4714919322022-12-22T03:16:17ZengIEEEIEEE Access2169-35362022-01-0110914819149610.1109/ACCESS.2022.32018239868133Modeling and Control of Priority Queueing in Software Defined Networks via Machine LearningEnrico Reticcioli0https://orcid.org/0000-0002-2487-8139Giovanni Domenico Di Girolamo1Francesco Smarra2https://orcid.org/0000-0002-2715-9447Angelo Torzi3Fabio Graziosi4https://orcid.org/0000-0001-7808-0707Alessandro D'innocenzo5https://orcid.org/0000-0002-5239-0894Department of Information Engineering, Computer Science and Mathematics, Università degli Studi dell'Aquila, L’Aquila, ItalyDepartment of Information Engineering, Computer Science and Mathematics, Università degli Studi dell'Aquila, L’Aquila, ItalyDepartment of Information Engineering, Computer Science and Mathematics, Università degli Studi dell'Aquila, L’Aquila, ItalySonicatel s.r.l., Pescara, ItalyDepartment of Information Engineering, Computer Science and Mathematics, Università degli Studi dell'Aquila, L’Aquila, ItalyDepartment of Information Engineering, Computer Science and Mathematics, Università degli Studi dell'Aquila, L’Aquila, ItalySoftware Defined Networking (SDN) is a new architectural paradigm that enables programmable control of a network to make it more flexible and easier to manage. SDN architectures decouple control and forwarding functionalities, and enable switches and routers to be remotely configurable/programmable in run-time by a controller. Modeling and optimization of such modern heterogeneous network infrastructures are key factors to achieve better performance, e.g. in terms of traffic flow improvement while reducing bandwidth allocation. Identifying an accurate model of a network device in SDNs (e.g., a switch or a router) is crucial in order to apply advanced techniques such as Model Predictive Control (MPC). However, such a problem is very challenging due to non-linearities and unavailability of internal variables measurements in real devices. To this aim, a promising direction is given by an appropriate integration of System Identification and Machine Learning techniques to obtain predictive models using historical data collected from the network thanks to the SDN paradigm. In this paper we apply a novel data-driven methodology to learn accurate models of the dynamical input-output behavior of a network’s switch device by appropriately combining AutoRegressive eXogenous (ARX) model identification with Regression Trees (RTs) and Random Forests (RFs). The advantage of such model is that it can be directly used to apply MPC (which just requires Quadratic Programming to be solved) to optimally control the queues’ bandwidth of the switch ports within the SDN paradigm. We validate our approach on an experimental emulation setup using the Mininet network emulator environment and a real dataset obtained from measurements of an Italian Internet Service Provider (Sonicatel S.r.l.). To this aim, we first develop a model of a real network switch, then implement MPC using the RYU controller, and finally demonstrate the benefits of the proposed dynamic queueing control methodology in terms of packet losses reduction and bandwidth saving, i.e. in terms of improvement of the Quality of Service.https://ieeexplore.ieee.org/document/9868133/Software defined networkingmachine learningsystem identificationnetwork optimization |
| spellingShingle | Enrico Reticcioli Giovanni Domenico Di Girolamo Francesco Smarra Angelo Torzi Fabio Graziosi Alessandro D'innocenzo Modeling and Control of Priority Queueing in Software Defined Networks via Machine Learning IEEE Access Software defined networking machine learning system identification network optimization |
| title | Modeling and Control of Priority Queueing in Software Defined Networks via Machine Learning |
| title_full | Modeling and Control of Priority Queueing in Software Defined Networks via Machine Learning |
| title_fullStr | Modeling and Control of Priority Queueing in Software Defined Networks via Machine Learning |
| title_full_unstemmed | Modeling and Control of Priority Queueing in Software Defined Networks via Machine Learning |
| title_short | Modeling and Control of Priority Queueing in Software Defined Networks via Machine Learning |
| title_sort | modeling and control of priority queueing in software defined networks via machine learning |
| topic | Software defined networking machine learning system identification network optimization |
| url | https://ieeexplore.ieee.org/document/9868133/ |
| work_keys_str_mv | AT enricoreticcioli modelingandcontrolofpriorityqueueinginsoftwaredefinednetworksviamachinelearning AT giovannidomenicodigirolamo modelingandcontrolofpriorityqueueinginsoftwaredefinednetworksviamachinelearning AT francescosmarra modelingandcontrolofpriorityqueueinginsoftwaredefinednetworksviamachinelearning AT angelotorzi modelingandcontrolofpriorityqueueinginsoftwaredefinednetworksviamachinelearning AT fabiograziosi modelingandcontrolofpriorityqueueinginsoftwaredefinednetworksviamachinelearning AT alessandrodinnocenzo modelingandcontrolofpriorityqueueinginsoftwaredefinednetworksviamachinelearning |