Mobile traffic forecasting for maximizing 5G network slicing resource utilization

Mobile traffic forecasting for maximizing 5G network slicing resource utilization. Sciancalepore, V., Samdanis, K., Costa-Perez, X., Bega, D., Gramaglia, M., & Banchs, A. In IEEE INFOCOM 2017 - IEEE Conference on Computer Communications, pages 1–9, Atlanta, GA, USA, May, 2017. IEEE.

Paper doi abstract bibtex

The emerging network slicing paradigm for 5G provides new business opportunities by enabling multi-tenancy support. At the same time, new technical challenges are introduced, as novel resource allocation algorithms are required to accommodate different business models. In particular, infrastructure providers need to implement radically new admission control policies to decide on network slices requests depending on their Service Level Agreements (SLA). When implementing such admission control policies, infrastructure providers may apply forecasting techniques in order to adjust the allocated slice resources so as to optimize the network utilization while meeting network slices’ SLAs. This paper focuses on the design of three key network slicing building blocks responsible for (i) trafﬁc analysis and prediction per network slice, (ii) admission control decisions for network slice requests, and (iii) adaptive correction of the forecasted load based on measured deviations. Our results show very substantial potential gains in terms of system utilization as well as a trade-off between conservative forecasting conﬁgurations versus more aggressive ones (higher gains, SLA risk).

@inproceedings{sciancalepore_mobile_2017,
	address = {Atlanta, GA, USA},
	title = {Mobile traffic forecasting for maximizing {5G} network slicing resource utilization},
	isbn = {978-1-5090-5336-0},
	url = {http://ieeexplore.ieee.org/document/8057230/},
	doi = {10.1109/INFOCOM.2017.8057230},
	abstract = {The emerging network slicing paradigm for 5G provides new business opportunities by enabling multi-tenancy support. At the same time, new technical challenges are introduced, as novel resource allocation algorithms are required to accommodate different business models. In particular, infrastructure providers need to implement radically new admission control policies to decide on network slices requests depending on their Service Level Agreements (SLA). When implementing such admission control policies, infrastructure providers may apply forecasting techniques in order to adjust the allocated slice resources so as to optimize the network utilization while meeting network slices’ SLAs. This paper focuses on the design of three key network slicing building blocks responsible for (i) trafﬁc analysis and prediction per network slice, (ii) admission control decisions for network slice requests, and (iii) adaptive correction of the forecasted load based on measured deviations. Our results show very substantial potential gains in terms of system utilization as well as a trade-off between conservative forecasting conﬁgurations versus more aggressive ones (higher gains, SLA risk).},
	language = {en},
	urldate = {2024-08-17},
	booktitle = {{IEEE} {INFOCOM} 2017 - {IEEE} {Conference} on {Computer} {Communications}},
	publisher = {IEEE},
	author = {Sciancalepore, Vincenzo and Samdanis, Konstantinos and Costa-Perez, Xavier and Bega, Dario and Gramaglia, Marco and Banchs, Albert},
	month = may,
	year = {2017},
	pages = {1--9},
}

Downloads: 0

{"_id":"aEDrvMh9Z7f9LSHcd","bibbaseid":"sciancalepore-samdanis-costaperez-bega-gramaglia-banchs-mobiletrafficforecastingformaximizing5gnetworkslicingresourceutilization-2017","author_short":["Sciancalepore, V.","Samdanis, K.","Costa-Perez, X.","Bega, D.","Gramaglia, M.","Banchs, A."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Atlanta, GA, USA","title":"Mobile traffic forecasting for maximizing 5G network slicing resource utilization","isbn":"978-1-5090-5336-0","url":"http://ieeexplore.ieee.org/document/8057230/","doi":"10.1109/INFOCOM.2017.8057230","abstract":"The emerging network slicing paradigm for 5G provides new business opportunities by enabling multi-tenancy support. At the same time, new technical challenges are introduced, as novel resource allocation algorithms are required to accommodate different business models. In particular, infrastructure providers need to implement radically new admission control policies to decide on network slices requests depending on their Service Level Agreements (SLA). When implementing such admission control policies, infrastructure providers may apply forecasting techniques in order to adjust the allocated slice resources so as to optimize the network utilization while meeting network slices’ SLAs. This paper focuses on the design of three key network slicing building blocks responsible for (i) trafﬁc analysis and prediction per network slice, (ii) admission control decisions for network slice requests, and (iii) adaptive correction of the forecasted load based on measured deviations. Our results show very substantial potential gains in terms of system utilization as well as a trade-off between conservative forecasting conﬁgurations versus more aggressive ones (higher gains, SLA risk).","language":"en","urldate":"2024-08-17","booktitle":"IEEE INFOCOM 2017 - IEEE Conference on Computer Communications","publisher":"IEEE","author":[{"propositions":[],"lastnames":["Sciancalepore"],"firstnames":["Vincenzo"],"suffixes":[]},{"propositions":[],"lastnames":["Samdanis"],"firstnames":["Konstantinos"],"suffixes":[]},{"propositions":[],"lastnames":["Costa-Perez"],"firstnames":["Xavier"],"suffixes":[]},{"propositions":[],"lastnames":["Bega"],"firstnames":["Dario"],"suffixes":[]},{"propositions":[],"lastnames":["Gramaglia"],"firstnames":["Marco"],"suffixes":[]},{"propositions":[],"lastnames":["Banchs"],"firstnames":["Albert"],"suffixes":[]}],"month":"May","year":"2017","pages":"1–9","bibtex":"@inproceedings{sciancalepore_mobile_2017,\n\taddress = {Atlanta, GA, USA},\n\ttitle = {Mobile traffic forecasting for maximizing {5G} network slicing resource utilization},\n\tisbn = {978-1-5090-5336-0},\n\turl = {http://ieeexplore.ieee.org/document/8057230/},\n\tdoi = {10.1109/INFOCOM.2017.8057230},\n\tabstract = {The emerging network slicing paradigm for 5G provides new business opportunities by enabling multi-tenancy support. At the same time, new technical challenges are introduced, as novel resource allocation algorithms are required to accommodate different business models. In particular, infrastructure providers need to implement radically new admission control policies to decide on network slices requests depending on their Service Level Agreements (SLA). When implementing such admission control policies, infrastructure providers may apply forecasting techniques in order to adjust the allocated slice resources so as to optimize the network utilization while meeting network slices’ SLAs. This paper focuses on the design of three key network slicing building blocks responsible for (i) trafﬁc analysis and prediction per network slice, (ii) admission control decisions for network slice requests, and (iii) adaptive correction of the forecasted load based on measured deviations. Our results show very substantial potential gains in terms of system utilization as well as a trade-off between conservative forecasting conﬁgurations versus more aggressive ones (higher gains, SLA risk).},\n\tlanguage = {en},\n\turldate = {2024-08-17},\n\tbooktitle = {{IEEE} {INFOCOM} 2017 - {IEEE} {Conference} on {Computer} {Communications}},\n\tpublisher = {IEEE},\n\tauthor = {Sciancalepore, Vincenzo and Samdanis, Konstantinos and Costa-Perez, Xavier and Bega, Dario and Gramaglia, Marco and Banchs, Albert},\n\tmonth = may,\n\tyear = {2017},\n\tpages = {1--9},\n}\n\n\n\n","author_short":["Sciancalepore, V.","Samdanis, K.","Costa-Perez, X.","Bega, D.","Gramaglia, M.","Banchs, A."],"key":"sciancalepore_mobile_2017","id":"sciancalepore_mobile_2017","bibbaseid":"sciancalepore-samdanis-costaperez-bega-gramaglia-banchs-mobiletrafficforecastingformaximizing5gnetworkslicingresourceutilization-2017","role":"author","urls":{"Paper":"http://ieeexplore.ieee.org/document/8057230/"},"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/wmarshedi","dataSources":["k2G6TcS6hwL7cLxSu","6oX56jrCWfxNpSJQs"],"keywords":[],"search_terms":["mobile","traffic","forecasting","maximizing","network","slicing","resource","utilization","sciancalepore","samdanis","costa-perez","bega","gramaglia","banchs"],"title":"Mobile traffic forecasting for maximizing 5G network slicing resource utilization","year":2017}