Load Balancing in Heterogeneous Networks Based on Distributed Learning in Near-Potential Games

Ali, Mohd. Shabbir; Coucheney, Pierre; Coupechoux, Marceau

doi:10.1109/twc.2016.2551744

Cited by 23 publications

(12 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding the dynamic nature of the network conditions (eg, traffic intensity, number of users, user positions), most previous works 7,8,14‐17,20,21,29‐34 assume static or stationary conditions. While some works consider nonstationary scenarios, 9,18,19,22,28 their approaches are based on optimization or heuristic algorithms over mathematical models of the network , like in References 6‐8,10,20,21,32,34‐37. For mathematical tractability, even the most complete mathematical network models comprise simplifications and assumptions that may limit their application to real operating networks.…”

Section: Related Work and Contributionmentioning

confidence: 99%

See 1 more Smart Citation

Online reinforcement learning for adaptive interference coordination

Alcaraz

Ayala‐Romero

Vales‐Alonso

et al. 2020

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Heterogeneous networks (HetNets), in which small cells overlay macro cells, are a cost-effective approach to increase the capacity of cellular networks. However, HetNets have raised new issues related to cell association and interference management. In particular, the optimal configuration of interference coordination (IC) parameters is a challenging task because it depends on multiple stochastic processes such as the locations of the users, the traffic demands, or the strength of the received signals. This work proposes a self-optimization algorithm capable of finding the optimal configuration in an operating network. We address the problem using a reinforcement learning (RL) approach, in which the actions are the IC configurations, whose performances are initially unknown. The main difficulty is that, due to the variable network conditions, the performance of each action may change over time. Our proposal is based on two main elements: the sequential exploration of subsets of actions (exploration regions), and an optimal stopping (OS) strategy for deciding when to end current exploration and start a new one. For our algorithm, referred to as local exploration with optimal stopping (LEOS), we provide theoretical bounds on its long-term regret per sample and its convergence time. We compare LEOS to state-of-the-art learning algorithms based on multiarmed bandits and policy gradient RL. Considering different changing rates in the network conditions, our numerical results show that LEOS outperforms the first alternative by 22%, and the second one by 48% in terms of average regret per sample.

show abstract

Section: Related Work and Contributionmentioning

confidence: 99%

“…Earlier works on eICIC 6‐10 relied, in general, on mathematical modeling. This approach is appropriate, for example, to estimate the network capacity, but not to optimize the configuration of a real operating network, because of the limitations of the mathematical models.…”

Section: Introductionmentioning

confidence: 99%

Online reinforcement learning for adaptive interference coordination

Alcaraz

Ayala‐Romero

Vales‐Alonso

et al. 2020

Trans Emerging Tel Tech

View full text Add to dashboard Cite

show abstract

“…Therefore, BSs can adaptively optimize CRE based on the network's conditions. 24 Since, in this paper, our focus is on the UE-centric approach, we assume that the BSs have bias 1. Therefore, the received SINR from MBS m at the receiver of UE k is given by…”

Section: System Modelmentioning

confidence: 99%

“…In the work of Ye et al, 23 to implement UE-BS association, a logarithmic utility maximization problem is developed, in which a fractional association assumption is used to convert the problem into a convex optimization problem. In the work of Ali et al, 24 a network-centric approach using cell range expansion (CRE) for UEA is proposed, in which BSs take decisions on selecting CRE, and then, UEs follow the association rule.…”

Section: Introductionmentioning

confidence: 99%

A distributed learning–based user association for heterogeneous networks

Arani

Omidi

Mehbodniya

et al. 2017

Trans Emerging Tel Tech

View full text Add to dashboard Cite

The coexistence of various base stations (BSs) in heterogeneous networks (HetNets) has emerged as a promising approach to meet the ever increasing network capacity. In these networks, one of the important issues is the problem of associating user equipments (UEs) to BSs. In this paper, we investigate the UE association (UEA) problem in heterogeneous networks and propose a load-aware UEA mechanism based on the BSs' estimated load and signal-to-interference-and-noise ratio. The proposed mechanism can capture the trade-off between UE's quality-of-service requirement and delay. We model this strategic UE-BS association as a noncooperative game. To solve the game, we develop a fully distributed algorithm inspired by machine learning techniques, whereby the proposed UEA scheme corresponds to a Markov chain.In the proposed scheme, each UE senses its environment and decides which BS to select based on the satisfaction technique. Therefore, it achieves a high level of satisfaction for UEs. Furthermore, use of historical information helps UEs select BSs with better long-term performance. Simulation results show that the proposed mechanism reduces fractional transfer time and the number of unsatisfied UEs, respectively, up to about 46% and 52.3% and improves BS throughput up to about 15.4% compared to a benchmark algorithm that is based on the received signal strength and the BS's estimated load.

show abstract

“…It is an exact potential game. BLLA induces a regular Markov process over the action space X of G [17], [26], [29]. Let denote P τ as the transition matrix of the regular Markov process.…”

Section: A Proof Of Convergence Of Blla With Fixed τmentioning

confidence: 99%

Optimal distributed channel assignment in D2D networks using learning in noisy potential games

Ali¹,

Coucheney²,

Coupechoux³

2017

2017 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)

Self Cite

View full text Add to dashboard Cite

Abstract-We present a novel solution for Channel Assignment Problem (CAP) in Device-to-Device (D2D) wireless networks that takes into account the throughput estimation noise. CAP is known to be NP-hard in the literature and there is no practical optimal learning algorithm that takes into account the estimation noise. In this paper, we first formulate the CAP as a stochastic optimization problem to maximize the expected sum data rate. To capture the estimation noise, CAP is modeled as a noisy potential game, a novel notion we introduce in this paper. Then, we propose a distributed Binary Log-linear Learning Algorithm (BLLA) that converges to the optimal channel assignments. Convergence of BLLA is proved for bounded and unbounded noise. Proofs for fixed and decreasing temperature parameter of BLLA are provided. A sufficient number of estimation samples is given that guarantees the convergence to the optimal state. We assess the performance of BLLA by extensive simulations, which show that the sum data rate increases with the number of channels and users. Contrary to the better response algorithm, the proposed algorithm achieves the optimal channel assignments distributively even in presence of estimation noise.

show abstract

Load Balancing in Heterogeneous Networks Based on Distributed Learning in Near-Potential Games

Cited by 23 publications

References 44 publications

Online reinforcement learning for adaptive interference coordination

Online reinforcement learning for adaptive interference coordination

A distributed learning–based user association for heterogeneous networks

Optimal distributed channel assignment in D2D networks using learning in noisy potential games

Contact Info

Product

Resources

About