November 29, 2021 Preprint Open Access

Jose A. Ayala-Romero; Andres Garcia-Saavedra; Xavier Costa-Perez; George Iosifidis

JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/704b4bf0-6144-4a4a-81c9-0b98015ba846/conext21-final106.pdf"
      }, 
      "checksum": "md5:a6d51d30ccd1187a9a743a6354a65083", 
      "bucket": "704b4bf0-6144-4a4a-81c9-0b98015ba846", 
      "key": "conext21-final106.pdf", 
      "type": "pdf", 
      "size": 2657316
    }
  ], 
  "owners": [
    198853
  ], 
  "doi": "10.5281/zenodo.5734886", 
  "stats": {
    "version_unique_downloads": 135.0, 
    "unique_views": 184.0, 
    "views": 202.0, 
    "version_views": 247.0, 
    "unique_downloads": 121.0, 
    "version_unique_views": 213.0, 
    "volume": 337479132.0, 
    "version_downloads": 149.0, 
    "downloads": 127.0, 
    "version_volume": 337585084.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.5734886", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.5734868", 
    "bucket": "https://zenodo.org/api/files/704b4bf0-6144-4a4a-81c9-0b98015ba846", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.5734868.svg", 
    "html": "https://zenodo.org/record/5734886", 
    "latest_html": "https://zenodo.org/record/5734886", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.5734886.svg", 
    "latest": "https://zenodo.org/api/records/5734886"
  }, 
  "conceptdoi": "10.5281/zenodo.5734868", 
  "created": "2021-11-29T13:01:50.218730+00:00", 
  "updated": "2021-11-29T13:48:44.132548+00:00", 
  "conceptrecid": "5734868", 
  "revision": 2, 
  "id": 5734886, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.5734886", 
    "description": "<p>Supporting Edge AI services is one of the most exciting features of future mobile networks. These services involve the collection and processing of voluminous data streams, right at the network edge, so as to offer real-time and accurate inferences to users. However, their widespread deployment is hampered by the energy cost they induce to the network. To overcome this obstacle, we propose a Bayesian learning framework for jointly configuring the service and the Radio Access Network (RAN), aiming to minimize the total energy consumption while respecting desirable accuracy and latency thresholds. Using a fully-fledged prototype with a software-defined base station (BS) and a GPU-enabled edge server, we profile a state-of-the-art video analytics AI service and identify new performance trade-offs. Accordingly, we tailor the optimization framework to account for the network context, the user needs, and the service metrics. The efficacy of our proposal is verified in a series of experiments and comparisons with neural network-based benchmarks.</p>", 
    "language": "eng", 
    "title": "EdgeBOL: Automating Energy-savings for Mobile Edge AI", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "relations": {
      "version": [
        {
          "count": 2, 
          "index": 1, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "5734868"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "5734886"
          }
        }
      ]
    }, 
    "communities": [
      {
        "id": "h2020daemon"
      }
    ], 
    "grants": [
      {
        "code": "101017109", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::101017109"
        }, 
        "title": "Network intelligence for aDAptive and sElf-Learning MObile Networks", 
        "acronym": "DAEMON", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }
    ], 
    "keywords": [
      "Mobile networks", 
      "O-RAN", 
      "energy efficiency", 
      "QoS"
    ], 
    "publication_date": "2021-11-29", 
    "creators": [
      {
        "affiliation": "Huawei Ireland Research Center", 
        "name": "Jose A. Ayala-Romero"
      }, 
      {
        "orcid": "0000-0003-2005-2222", 
        "affiliation": "NEC Laboratories Europe GmbH", 
        "name": "Andres Garcia-Saavedra"
      }, 
      {
        "affiliation": "NEC Laboratories Europe GmbH, i2cat, ICREA", 
        "name": "Xavier Costa-Perez"
      }, 
      {
        "affiliation": "Delft University of Technology", 
        "name": "George Iosifidis"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "subtype": "preprint", 
      "type": "publication", 
      "title": "Preprint"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.1145/3485983.3494849", 
        "relation": "isPublishedIn"
      }, 
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.5734868", 
        "relation": "isVersionOf"
      }
    ]
  }
}