Greenly offloading traffic in stochastic heterogeneous cellular networks

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

1 Citation (Scopus)

Abstract

This paper puts forwards an on-line reinforcement learning framework for the problem of traf?c of?oading in a stochastic Markovian heterogeneous cellular network (HCN), where the time-varying traf?c demand of mobile terminals (MTs) can be of?oaded from macrocells to small-cells. Our aim is to minimize the average energy consumption of the HCN while maintaining the Quality-of-Service (QoS) experienced by MTs. For each cell (i.e., a macrocell or a small-cell), the energy consumption is determined by its system load which is coupled with the system loads served in other cells due to the sharing over a common frequency band. We model the energy-aware traf?c of?oading in such HCNs as a constrained Markov decision process (C-MDP). The statistics of the C-MDP depends on a selected traf?c of?oading strategy and thus, the actions performed by a network controller have a long-term impact on the network state evolution. Based on the traf?c demand observations and the traf?c of?oading operations, the controller gradually optimizes the strategy with no prior knowledge of the process statistics. Numerical experiments are conducted to show the effectiveness of the proposed learning framework in balancing the tradeoff between energy saving and QoS satisfaction
Original languageEnglish
Title of host publicationProceedings
Subtitle of host publication1st International Workshop on Cognitive Cellular Systems, CCS 2014
PublisherInstitute of Electrical and Electronic Engineers IEEE
Number of pages5
ISBN (Electronic)978-1-4799-4139-1
DOIs
Publication statusPublished - 2014
MoE publication typeA4 Article in a conference publication
EventIEEE International Workshop on Cognitive Cellular Systems CCS 2014 - Rhine River, Germany
Duration: 2 Sep 20144 Sep 2014

Conference

ConferenceIEEE International Workshop on Cognitive Cellular Systems CCS 2014
Abbreviated titleCCS 2014
CountryGermany
CityRhine River
Period2/09/144/09/14

Fingerprint

Quality of service
Energy utilization
Statistics
Controllers
Reinforcement learning
Frequency bands
Energy conservation
Experiments

Keywords

  • energy consumption
  • macrocell networks
  • scattering
  • quality of service
  • telecommunication traffic
  • interference
  • switches

Cite this

Chen, X., Chen, T., Wu, S., & Lasanen, M. (2014). Greenly offloading traffic in stochastic heterogeneous cellular networks. In Proceedings: 1st International Workshop on Cognitive Cellular Systems, CCS 2014 Institute of Electrical and Electronic Engineers IEEE. https://doi.org/10.1109/CCS.2014.6933789
Chen, Xianfu ; Chen, Tao ; Wu, S ; Lasanen, Mika. / Greenly offloading traffic in stochastic heterogeneous cellular networks. Proceedings: 1st International Workshop on Cognitive Cellular Systems, CCS 2014. Institute of Electrical and Electronic Engineers IEEE, 2014.
@inproceedings{620db63f44494d9f9820ec1d35a5057b,
title = "Greenly offloading traffic in stochastic heterogeneous cellular networks",
abstract = "This paper puts forwards an on-line reinforcement learning framework for the problem of traf?c of?oading in a stochastic Markovian heterogeneous cellular network (HCN), where the time-varying traf?c demand of mobile terminals (MTs) can be of?oaded from macrocells to small-cells. Our aim is to minimize the average energy consumption of the HCN while maintaining the Quality-of-Service (QoS) experienced by MTs. For each cell (i.e., a macrocell or a small-cell), the energy consumption is determined by its system load which is coupled with the system loads served in other cells due to the sharing over a common frequency band. We model the energy-aware traf?c of?oading in such HCNs as a constrained Markov decision process (C-MDP). The statistics of the C-MDP depends on a selected traf?c of?oading strategy and thus, the actions performed by a network controller have a long-term impact on the network state evolution. Based on the traf?c demand observations and the traf?c of?oading operations, the controller gradually optimizes the strategy with no prior knowledge of the process statistics. Numerical experiments are conducted to show the effectiveness of the proposed learning framework in balancing the tradeoff between energy saving and QoS satisfaction",
keywords = "energy consumption, macrocell networks, scattering, quality of service, telecommunication traffic, interference, switches",
author = "Xianfu Chen and Tao Chen and S Wu and Mika Lasanen",
note = "Project code: 82164",
year = "2014",
doi = "10.1109/CCS.2014.6933789",
language = "English",
booktitle = "Proceedings",
publisher = "Institute of Electrical and Electronic Engineers IEEE",
address = "United States",

}

Chen, X, Chen, T, Wu, S & Lasanen, M 2014, Greenly offloading traffic in stochastic heterogeneous cellular networks. in Proceedings: 1st International Workshop on Cognitive Cellular Systems, CCS 2014. Institute of Electrical and Electronic Engineers IEEE, IEEE International Workshop on Cognitive Cellular Systems CCS 2014, Rhine River, Germany, 2/09/14. https://doi.org/10.1109/CCS.2014.6933789

Greenly offloading traffic in stochastic heterogeneous cellular networks. / Chen, Xianfu; Chen, Tao; Wu, S; Lasanen, Mika.

Proceedings: 1st International Workshop on Cognitive Cellular Systems, CCS 2014. Institute of Electrical and Electronic Engineers IEEE, 2014.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Greenly offloading traffic in stochastic heterogeneous cellular networks

AU - Chen, Xianfu

AU - Chen, Tao

AU - Wu, S

AU - Lasanen, Mika

N1 - Project code: 82164

PY - 2014

Y1 - 2014

N2 - This paper puts forwards an on-line reinforcement learning framework for the problem of traf?c of?oading in a stochastic Markovian heterogeneous cellular network (HCN), where the time-varying traf?c demand of mobile terminals (MTs) can be of?oaded from macrocells to small-cells. Our aim is to minimize the average energy consumption of the HCN while maintaining the Quality-of-Service (QoS) experienced by MTs. For each cell (i.e., a macrocell or a small-cell), the energy consumption is determined by its system load which is coupled with the system loads served in other cells due to the sharing over a common frequency band. We model the energy-aware traf?c of?oading in such HCNs as a constrained Markov decision process (C-MDP). The statistics of the C-MDP depends on a selected traf?c of?oading strategy and thus, the actions performed by a network controller have a long-term impact on the network state evolution. Based on the traf?c demand observations and the traf?c of?oading operations, the controller gradually optimizes the strategy with no prior knowledge of the process statistics. Numerical experiments are conducted to show the effectiveness of the proposed learning framework in balancing the tradeoff between energy saving and QoS satisfaction

AB - This paper puts forwards an on-line reinforcement learning framework for the problem of traf?c of?oading in a stochastic Markovian heterogeneous cellular network (HCN), where the time-varying traf?c demand of mobile terminals (MTs) can be of?oaded from macrocells to small-cells. Our aim is to minimize the average energy consumption of the HCN while maintaining the Quality-of-Service (QoS) experienced by MTs. For each cell (i.e., a macrocell or a small-cell), the energy consumption is determined by its system load which is coupled with the system loads served in other cells due to the sharing over a common frequency band. We model the energy-aware traf?c of?oading in such HCNs as a constrained Markov decision process (C-MDP). The statistics of the C-MDP depends on a selected traf?c of?oading strategy and thus, the actions performed by a network controller have a long-term impact on the network state evolution. Based on the traf?c demand observations and the traf?c of?oading operations, the controller gradually optimizes the strategy with no prior knowledge of the process statistics. Numerical experiments are conducted to show the effectiveness of the proposed learning framework in balancing the tradeoff between energy saving and QoS satisfaction

KW - energy consumption

KW - macrocell networks

KW - scattering

KW - quality of service

KW - telecommunication traffic

KW - interference

KW - switches

U2 - 10.1109/CCS.2014.6933789

DO - 10.1109/CCS.2014.6933789

M3 - Conference article in proceedings

BT - Proceedings

PB - Institute of Electrical and Electronic Engineers IEEE

ER -

Chen X, Chen T, Wu S, Lasanen M. Greenly offloading traffic in stochastic heterogeneous cellular networks. In Proceedings: 1st International Workshop on Cognitive Cellular Systems, CCS 2014. Institute of Electrical and Electronic Engineers IEEE. 2014 https://doi.org/10.1109/CCS.2014.6933789