Autonomous resource allocation for dense LTE networks: A Multi Armed Bandit formulation

Feki, Afef; Capdevielle, Véronique

doi:10.1109/pimrc.2011.6140047

Cited by 28 publications

(21 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is established in [3] that the proposed first version of the MAB algorithm can converge quickly. In this article, we propose an enhanced CMAB algorithm with sequential decisions among the neighboring cells, in addition to a traffic aware feature.…”

Section: A Proposed Cmab Algorithmmentioning

confidence: 99%

“…In the scope of the new algorithm, some modifications are applied to the reward model proposed in [3]. The detailed definitions and formulas are given below.…”

Section: B Calculation Of the Rewardmentioning

confidence: 99%

“…Thus, autonomous ICI management mechanisms are primordial for an efficient coexistence of all the cells, in the same frequency band. In [3], a reinforcement learning approach has proven its efficiency in steering each cell, in autonomous manner, towards the most appropriate spectral resources, so that interference levels are minimized among all the neighboring cells. This approach inspired from the Multi Armed bandit (MAB) problem resolution was proposed and evaluated in a first version with static users and fixed traffic load conditions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Self-Organized Resource Allocation for LTE Pico Cells: A Reinforcement Learning Approach

Feki¹,

Capdevielle²,

Sorsy

2012

2012 IEEE 75th Vehicular Technology Conference (VTC Spring)

Self Cite

View full text Add to dashboard Cite

This article proposes a smart resource sharing algorithm to manage interference in LTE networks. Relying on reinforcement learning theory, the proposed Cyclic Multi Armed Bandit (CMAB) algorithm steers each cell in the choice of the most suitable frequency band portions, in autonomous manner. Thanks to the traffic aware feature, the algorithm adapts as well to the real needs of the cell. Adding to that, a refinement of the decision function is proposed to speed up the convergence time. The proposed approach is tested in LTE compliant simulator and the results shows its efficiency compared to conventional static reuse schemes.

show abstract

Section: A Proposed Cmab Algorithmmentioning

confidence: 99%

“…In the scope of the new algorithm, some modifications are applied to the reward model proposed in [3]. The detailed definitions and formulas are given below.…”

Section: B Calculation Of the Rewardmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Self-Organized Resource Allocation for LTE Pico Cells: A Reinforcement Learning Approach

Feki¹,

Capdevielle²,

Sorsy

2012

2012 IEEE 75th Vehicular Technology Conference (VTC Spring)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Using this new cost function the Q-table is filled in state s i for each action a, which corresponds to P k,F r (8). This initialization is done only for states, that have not been visited before.…”

Section: Decentralized Q-learning With Improved Initializationmentioning

confidence: 99%

“…A resource sharing method inspired from the RL solutions targeted to resolve the MAB problem is proposed in [8].…”

Section: B Multi-armed Bandit (Mab) Learningmentioning

confidence: 99%

On Interference Management Techniques in LTE Heterogeneous Networks

Simsek

Czylwik

Bennis

2012

2012 21st International Conference on Computer Communications and Networks (ICCCN)

View full text Add to dashboard Cite

Autonomous interference management solutions for inter-cell interference coordination (ICIC) are of utmost importance. In this paper, the coexistence between macro and small cells is studied whereby different ICIC techniques pertaining to different deployment and information assumptions are evaluated. Inspired from Evolutionary Game Theory (EGT), decentralized strategies are devised, in which small cell Base Stations (BSs) exchange information through a central controller, and adapt their strategies based on instantaneous and average payoffs of the small cell population. In contrast, when distributed operation is aimed at, using tools from Reinforcement Learning (RL) small cells learn by interacting with their environment through trialsand-errors, and autonomously optimize their strategies based on a mere feedback. In particular, we compare the performance of decentralized Q-learning, Fuzzy Q-learning, improved Qlearning and expertness-based Q-learning procedures. Finally, the overall performance of the network in terms of average peruser data throughput and convergence are carried out in an LTE-A system level simulator.Index Terms-LTE heterogeneous networks, small cells, interference management, reinforcement learning, game theory.

show abstract

Resource allocation trends for ultra dense networks in 5G and beyond networks: A classification and comprehensive survey

Sharma

Kumar

2021

Physical Communication

View full text Add to dashboard Cite

Autonomous resource allocation for dense LTE networks: A Multi Armed Bandit formulation

Cited by 28 publications

References 6 publications

Self-Organized Resource Allocation for LTE Pico Cells: A Reinforcement Learning Approach

Self-Organized Resource Allocation for LTE Pico Cells: A Reinforcement Learning Approach

On Interference Management Techniques in LTE Heterogeneous Networks

Resource allocation trends for ultra dense networks in 5G and beyond networks: A classification and comprehensive survey

Contact Info

Product

Resources

About