{ "access": { "embargo": { "active": false, "reason": null }, "files": "public", "record": "public", "status": "open" }, "created": "2021-06-16T14:02:31.638987+00:00", "custom_fields": { "meeting:meeting": { "acronym": "INFOCOM", "dates": "10-13 May 2021", "title": "IEEE International Conference on Computer Communications" } }, "deletion_status": { "is_deleted": false, "status": "P" }, "files": { "count": 1, "enabled": true, "entries": { "Bayesian Online Learning for Energy.pdf": { "checksum": "md5:d44eb429e7811d4dad887ec6d035867d", "ext": "pdf", "id": "b569f441-9f2b-4249-8e96-ad304a1c0dd2", "key": "Bayesian Online Learning for Energy.pdf", "metadata": null, "mimetype": "application/pdf", "size": 1263297 } }, "order": [], "total_bytes": 1263297 }, "id": "4966637", "is_draft": false, "is_published": true, "links": { "access": "https://zenodo.org/api/records/4966637/access", "access_links": "https://zenodo.org/api/records/4966637/access/links", "access_request": "https://zenodo.org/api/records/4966637/access/request", "access_users": "https://zenodo.org/api/records/4966637/access/users", "archive": "https://zenodo.org/api/records/4966637/files-archive", "archive_media": "https://zenodo.org/api/records/4966637/media-files-archive", "communities": "https://zenodo.org/api/records/4966637/communities", "communities-suggestions": "https://zenodo.org/api/records/4966637/communities-suggestions", "doi": "https://doi.org/10.5281/zenodo.4966637", "draft": "https://zenodo.org/api/records/4966637/draft", "files": "https://zenodo.org/api/records/4966637/files", "latest": "https://zenodo.org/api/records/4966637/versions/latest", "latest_html": "https://zenodo.org/records/4966637/latest", "media_files": "https://zenodo.org/api/records/4966637/media-files", "parent": "https://zenodo.org/api/records/4966636", "parent_doi": "https://zenodo.org/doi/10.5281/zenodo.4966636", "parent_html": "https://zenodo.org/records/4966636", "requests": "https://zenodo.org/api/records/4966637/requests", "reserve_doi": "https://zenodo.org/api/records/4966637/draft/pids/doi", "self": "https://zenodo.org/api/records/4966637", "self_doi": "https://zenodo.org/doi/10.5281/zenodo.4966637", "self_html": "https://zenodo.org/records/4966637", "self_iiif_manifest": "https://zenodo.org/api/iiif/record:4966637/manifest", "self_iiif_sequence": "https://zenodo.org/api/iiif/record:4966637/sequence/default", "versions": "https://zenodo.org/api/records/4966637/versions" }, "media_files": { "count": 0, "enabled": false, "entries": {}, "order": [], "total_bytes": 0 }, "metadata": { "creators": [ { "affiliations": [ { "name": "School of Computer Science and Statistics, Trinity College Dublin, Ireland" } ], "person_or_org": { "family_name": "Ayala-Romero", "given_name": "Jose", "name": "Ayala-Romero, Jose", "type": "personal" } }, { "affiliations": [ { "name": "NEC Laboratories Europe, Germany" } ], "person_or_org": { "family_name": "Garcia-Saavedra", "given_name": "Andres", "name": "Garcia-Saavedra, Andres", "type": "personal" } }, { "affiliations": [ { "name": "NEC Laboratories Europe, Germany" } ], "person_or_org": { "family_name": "Costa-Perez", "given_name": "Xavier", "name": "Costa-Perez, Xavier", "type": "personal" } }, { "affiliations": [ { "name": "Delft University of Technology, Netherlands" } ], "person_or_org": { "family_name": "Iosifidis", "given_name": "George", "name": "Iosifidis, George", "type": "personal" } } ], "description": "
Radio Access Network Virtualization (vRAN) will spearhead the quest towards supple radio stacks that adapt to heterogeneous infrastructure: from energy-constrained platforms deploying cells-on-wheels (e.g., drones) or battery-powered cells to green edge clouds. We perform an in-depth experimental analysis of the energy consumption of virtualized Base Stations (vBSs) and render two conclusions: (i) characterizing performance and power consumption is intricate as it depends on human behavior such as network load or user mobility; and (ii) there are many control policies and some of them have non-linear and monotonic relations with power and throughput. Driven by our experimental insights, we argue that machine learning holds the key for vBS control. We formulate two problems and two algorithms: (i) BP-vRAN, which uses Bayesian online learning to balance performance and energy consumption, and (ii) SBPvRAN, which augments our Bayesian optimization approach with safe controls that maximize performance while respecting hard power constraints. We show that our approaches are data-efficient and have provably performance, which is paramount for carriergrade vRANs. We demonstrate the convergence and flexibility of our approach and assess its performance using an experimental prototype.
", "funding": [ { "award": { "acronym": "DAEMON", "id": "00k4n6c32::101017109", "identifiers": [ { "identifier": "https://cordis.europa.eu/projects/101017109", "scheme": "url" } ], "number": "101017109", "program": "H2020", "title": { "en": "Network intelligence for aDAptive and sElf-Learning MObile Networks" } }, "funder": { "id": "00k4n6c32", "name": "European Commission" } } ], "publication_date": "2021-06-16", "publisher": "Zenodo", "resource_type": { "id": "publication-conferencepaper", "title": { "de": "Konferenzbeitrag", "en": "Conference paper" } }, "rights": [ { "description": { "en": "The Creative Commons Attribution license allows re-distribution and re-use of a licensed work on the condition that the creator is appropriately credited." }, "icon": "cc-by-icon", "id": "cc-by-4.0", "props": { "scheme": "spdx", "url": "https://creativecommons.org/licenses/by/4.0/legalcode" }, "title": { "en": "Creative Commons Attribution 4.0 International" } } ], "title": "Bayesian Online Learning for Energy-Aware Resource Orchestration in Virtualized RANs" }, "parent": { "access": { "owned_by": { "user": 235888 } }, "communities": { "default": "b7e9e83a-df78-4547-ac49-3b19cce36f58", "entries": [ { "access": { "member_policy": "open", "members_visibility": "public", "record_policy": "open", "review_policy": "open", "visibility": "public" }, "children": { "allow": false }, "created": "2021-02-25T16:18:59.538314+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "id": "b7e9e83a-df78-4547-ac49-3b19cce36f58", "links": {}, "metadata": { "curation_policy": "Uploads must have been fully or partially funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No. 101017109.
\r\n", "page": "The DAEMON H2020 european project develops and implements innovative and pragmatic approaches to Network Intelligence (NI) design that enable high performance, sustainable and extremely reliable zero-touch network system. DAEMON designs an end-to-end NI-native architecture for Beyond 5G (B5G) that fully coordinates NI-assisted functionalities. More info in our website:
\r\n\r\n\r\n\r\nThe success of Beyond 5G (B5G) systems will largely depend on the quality of the Network Intelligence (NI) that will fully automate network management. Artificial Intelligence (AI) models are commonly regarded as the cornerstone for NI design; indeed, AI models have proven extremely successful at solving hard problems that require inferring complex relationships from entangled and massive (e.g., traffic) data. However, AI is not the best solution for every NI task; and, when it is, the dominating trend of plugging ‘vanilla’ AI into network controllers and orchestrators is not a sensible choice.
\r\n\r\nDeparting from the current hype around AI, DAEMON will set forth a pragmatic approach to NI design. The project will carry out a systematic analysis of which NI tasks are appropriately solved with AI models, providing a solid set of guidelines for the use of machine learning in network functions. For those problems where AI is a suitable tool, DAEMON will design tailored AI models that respond to the specific needs of network functions, taking advantage of the most recent advances in machine learning. Building on these models, DAEMON will design an end-to-end NI-native architecture for B5G that fully coordinates NI-assisted functionalities.
\r\n\r\nThe advances to NI devised by DAEMON will be applied in practical network settings to:
\r\n\r\nTo achieve this, DAEMON will design practical algorithms for eight concrete NI-assisted functionalities, carefully selected to achieve the objectives above. The performance of the DAEMON algorithms will be evaluated in real-world conditions via four experimental sites, and at scale with data-driven approaches based on two nationwide traffic measurement datasets, against nine ambitious yet feasible KPI targets.
\r\n\r\nThe H2020 DAEMON consortium is formed by:
\r\n\r\n