---
_id: '25278'
abstract:
- lang: eng
text: Using Service Function Chaining (SFC) in wireless networks became popular
in many domains like networking and multimedia. It relies on allocating network
resources to incoming SFCs requests, via a Virtual Network Embedding (VNE) algorithm,
so that it optimizes the performance of the SFC. When the load of incoming requests
-- competing for the limited network resources -- increases, it becomes challenging
to decide which requests should be admitted and which one should be rejected.
In this work, we propose a deep Reinforcement learning (RL) solution that can
learn the admission policy for different dependencies, such as the service lifetime
and the priority of incoming requests. We compare the deep RL solution to a first-come-first-serve
baseline that admits a request whenever there are available resources. We show
that deep RL outperforms the baseline and provides higher acceptance rate with
low rejections even when there are enough resources.
author:
- first_name: Haitham
full_name: Afifi, Haitham
id: '65718'
last_name: Afifi
- first_name: Fabian Jakob
full_name: Sauer, Fabian Jakob
last_name: Sauer
- first_name: Holger
full_name: Karl, Holger
id: '126'
last_name: Karl
citation:
ama: 'Afifi H, Sauer FJ, Karl H. Reinforcement Learning for Admission Control in
Wireless Virtual Network Embedding. In: 2021 IEEE International Conference
on Advanced Networks and Telecommunications Systems (ANTS) (ANTS’21). ; 2021.'
apa: Afifi, H., Sauer, F. J., & Karl, H. (2021). Reinforcement Learning for
Admission Control in Wireless Virtual Network Embedding. 2021 IEEE International
Conference on Advanced Networks and Telecommunications Systems (ANTS) (ANTS’21).
bibtex: '@inproceedings{Afifi_Sauer_Karl_2021, place={Hyderabad, India}, title={Reinforcement
Learning for Admission Control in Wireless Virtual Network Embedding}, booktitle={2021
IEEE International Conference on Advanced Networks and Telecommunications Systems
(ANTS) (ANTS’21)}, author={Afifi, Haitham and Sauer, Fabian Jakob and Karl, Holger},
year={2021} }'
chicago: Afifi, Haitham, Fabian Jakob Sauer, and Holger Karl. “Reinforcement Learning
for Admission Control in Wireless Virtual Network Embedding.” In 2021 IEEE
International Conference on Advanced Networks and Telecommunications Systems (ANTS)
(ANTS’21). Hyderabad, India, 2021.
ieee: H. Afifi, F. J. Sauer, and H. Karl, “Reinforcement Learning for Admission
Control in Wireless Virtual Network Embedding,” 2021.
mla: Afifi, Haitham, et al. “Reinforcement Learning for Admission Control in Wireless
Virtual Network Embedding.” 2021 IEEE International Conference on Advanced
Networks and Telecommunications Systems (ANTS) (ANTS’21), 2021.
short: 'H. Afifi, F.J. Sauer, H. Karl, in: 2021 IEEE International Conference on
Advanced Networks and Telecommunications Systems (ANTS) (ANTS’21), Hyderabad,
India, 2021.'
date_created: 2021-10-04T10:42:20Z
date_updated: 2022-01-06T06:56:58Z
ddc:
- '000'
file:
- access_level: closed
content_type: application/pdf
creator: hafifi
date_created: 2021-10-04T10:43:19Z
date_updated: 2021-10-04T10:43:19Z
file_id: '25279'
file_name: Preprint___Reinforcement_Learning_for_Dynamic_Resource_Allocation_in_Wireless_Networks.pdf
file_size: 534737
relation: main_file
success: 1
file_date_updated: 2021-10-04T10:43:19Z
has_accepted_license: '1'
keyword:
- reinforcement learning
- admission control
- wireless sensor networks
language:
- iso: eng
place: Hyderabad, India
project:
- _id: '27'
name: Akustische Sensornetzwerke - Teilprojekt "Verteilte akustische Signalverarbeitung
über funkbasierte Sensornetzwerke
publication: 2021 IEEE International Conference on Advanced Networks and Telecommunications
Systems (ANTS) (ANTS'21)
status: public
title: Reinforcement Learning for Admission Control in Wireless Virtual Network Embedding
type: conference
user_id: '65718'
year: '2021'
...
---
_id: '5679'
abstract:
- lang: eng
text: Cloud computing promises the flexible delivery of computing services in a
pay-as-you-go manner. It allows customers to easily scale their infrastructure
and save on the overall cost of operation. However Cloud service offerings can
only thrive if customers are satisfied with service performance. Allow-ing instantaneous
access and flexible scaling while maintaining the service levels and offering
competitive prices poses a significant challenge to Cloud Computing providers.
Furthermore services will remain available in the long run only if this business
generates a stable revenue stream. To address these challenges we introduce novel
policy-based service admission control mod-els that aim at maximizing the revenue
of Cloud providers while taking in-formational uncertainty regarding resource
requirements into account. Our evaluation shows that policy-based approaches statistically
significantly out-perform first come first serve approaches, which are still state
of the art. Furthermore the results give insights in how and to what extent uncertainty
has a negative impact on revenue.
author:
- first_name: Tim
full_name: Püschel, Tim
last_name: Püschel
- first_name: Guido
full_name: Schryen, Guido
id: '72850'
last_name: Schryen
- first_name: Diana
full_name: Hristova, Diana
last_name: Hristova
- first_name: Dirk
full_name: Neumann, Dirk
last_name: Neumann
citation:
ama: 'Püschel T, Schryen G, Hristova D, Neumann D. Revenue Management for Cloud
Computing Providers: Decision Models for Service Admission Control under Non-probabilistic
Uncertainty. European Journal of Operational Research. 2015;244(2):637-647.'
apa: 'Püschel, T., Schryen, G., Hristova, D., & Neumann, D. (2015). Revenue
Management for Cloud Computing Providers: Decision Models for Service Admission
Control under Non-probabilistic Uncertainty. European Journal of Operational
Research, 244(2), 637–647.'
bibtex: '@article{Püschel_Schryen_Hristova_Neumann_2015, title={Revenue Management
for Cloud Computing Providers: Decision Models for Service Admission Control under
Non-probabilistic Uncertainty}, volume={244}, number={2}, journal={European Journal
of Operational Research}, publisher={Elsevier}, author={Püschel, Tim and Schryen,
Guido and Hristova, Diana and Neumann, Dirk}, year={2015}, pages={637–647} }'
chicago: 'Püschel, Tim, Guido Schryen, Diana Hristova, and Dirk Neumann. “Revenue
Management for Cloud Computing Providers: Decision Models for Service Admission
Control under Non-Probabilistic Uncertainty.” European Journal of Operational
Research 244, no. 2 (2015): 637–47.'
ieee: 'T. Püschel, G. Schryen, D. Hristova, and D. Neumann, “Revenue Management
for Cloud Computing Providers: Decision Models for Service Admission Control under
Non-probabilistic Uncertainty,” European Journal of Operational Research,
vol. 244, no. 2, pp. 637–647, 2015.'
mla: 'Püschel, Tim, et al. “Revenue Management for Cloud Computing Providers: Decision
Models for Service Admission Control under Non-Probabilistic Uncertainty.” European
Journal of Operational Research, vol. 244, no. 2, Elsevier, 2015, pp. 637–47.'
short: T. Püschel, G. Schryen, D. Hristova, D. Neumann, European Journal of Operational
Research 244 (2015) 637–647.
date_created: 2018-11-14T15:40:13Z
date_updated: 2022-01-06T07:02:30Z
ddc:
- '000'
department:
- _id: '277'
extern: '1'
file:
- access_level: open_access
content_type: application/pdf
creator: hsiemes
date_created: 2018-12-07T11:44:10Z
date_updated: 2018-12-13T15:09:12Z
file_id: '6036'
file_name: ELSEVIER_JOURNAL_VERSION.pdf
file_size: 1270024
relation: main_file
file_date_updated: 2018-12-13T15:09:12Z
has_accepted_license: '1'
intvolume: ' 244'
issue: '2'
keyword:
- admission control
- informational uncertainty
- revenue management
- cloud computing
language:
- iso: eng
oa: '1'
page: 637-647
publication: European Journal of Operational Research
publisher: Elsevier
status: public
title: 'Revenue Management for Cloud Computing Providers: Decision Models for Service
Admission Control under Non-probabilistic Uncertainty'
type: journal_article
user_id: '61579'
volume: 244
year: '2015'
...