Analysis of Limitations of Mobility Load Balancing in a Live LTE System

Ruiz-Avilés, J. M.; Toril, M.; Luna-Ramírez, Salvador; Buenestado, V.; Regueira, Miguel

doi:10.1109/lwc.2015.2430345

Cited by 19 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where the expectation in (7) operates over the state s(1) and action a(1). We also see that (7) as a recursive form of the action-value is an unbiased estimation of Q π (s, a). Q π (s, a) together with ( 7) is known as the Bellman equation.…”

Section: A Preliminary On Reinforcement Learningmentioning

confidence: 99%

“…For simplicity, we only elaborate the case of two dimensional rewards, where the reward vector with more than two dimensions can be easily obtained. According to the definition of the action-value function in (7), we can rephrase (14) as…”

Section: Pareto Deterministic Policy Gradientmentioning

confidence: 99%

“…These analytical methods are often unextendable to online fashions due to the bottlenecks of modeling the network dynamics and developing feasible solvers [6]. From the experiments in [7], it demonstrates that directly using the results from a static optimization approach to a dynamic scenario can lead to 85% to 97% hand-over failures and connection outages. Also, the negative impacts of model mismatch (applying long-term measurements based strategies to dynamic situations) are discussed in [8].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Pareto Deterministic Policy Gradients and Its Application in 5G Massive MIMO Networks

Zhou,

Xin,

Chen

et al. 2020

Preprint

View full text Add to dashboard Cite

In this paper, we consider jointly optimizing cell load balance and network throughput via a reinforcement learning (RL) approach, where inter-cell handover (i.e., user association assignment) and massive MIMO antenna tilting are configured as the RL policy to learn. Our rationale behind using RL is to circumvent the challenges of analytically modeling user mobility and network dynamics.To accomplish this joint optimization, we integrate vector rewards into the RL value network and conduct RL action via a separate policy network. We name this method as Pareto deterministic policy gradients (PDPG). It is an actor-critic, model-free and deterministic policy algorithm which can handle the coupling objectives with the following two merits: 1) It solves the optimization via leveraging the degree of freedom of vector reward as opposed to choosing handcrafted scalar-reward; 2) Crossvalidation over multiple policies can be significantly reduced. Accordingly, the RL enabled network behaves in a self-organized way: It learns out the underlying user mobility through measurement history to proactively operate handover and antenna tilt without environment assumptions. Our numerical evaluation demonstrates that the introduced RL method outperforms scalar-reward based approaches.Meanwhile, to be self-contained, an ideal static optimization based brute-force search solver is included as a benchmark. The comparison shows that the RL approach performs as well as this ideal strategy, though the former one is constrained with limited environment observations and lower action frequency, whereas the latter ones have full access to the user mobility. The convergence of our introduced approach is also tested under different user mobility environment based on our measurement data from a real scenario.

show abstract

Section: A Preliminary On Reinforcement Learningmentioning

confidence: 99%

Section: Pareto Deterministic Policy Gradientmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Pareto Deterministic Policy Gradients and Its Application in 5G Massive MIMO Networks

Zhou,

Xin,

Chen

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The resulting increased network efficiency using MLB postpones the deployment of additional network capacity, in turn reducing costs. This is usually done through range-expansion [16], achieved by either cell coverage parameter adjustments or mobility parameter adjustments. However, in 4G LTE networks, MLB is known to lead to network performance degradation due to the frequency reuse-1 in this technology [17].…”

Section: Self-optimisation Functionsmentioning

confidence: 99%

Network Architecture and Essential Features for 5G: The SESAME Project Approach

Goratti¹,

Costa²,

Pérez-Romano³

et al. 2016

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

“…This technique is used in Global System for Mobile communications (GSM) [3], Universal Mobile Telecommunications System (UMTS) [4], and Long Term Evolution (LTE) [5]. However, the use of MLB in LTE presents important limitations (see, e.g., [6]).…”

Section: Introductionmentioning

confidence: 99%

A Quality of Experience Management Framework for Mobile Users

Algar

Diego

Fernández-Isabel

et al. 2019

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Voice transmission is no longer the main usage of mobile phones. Data transmissions, in particular Internet access, are very common actions that we might perform with these devices. However, the spectacular growth of the mobile data demand in 5G mobile communication systems leads to a reduction of the resources assigned to each device. Therefore, to avoid situations in which the Quality of Experience (QoE) would be negatively affected, an automated system for degradation detection of video streaming is proposed. This approach is named QoE Management for Mobile Users (QoEMU). QoEMU is composed of several modules to perform a real-time analysis of the network traffic, select a mitigation action according to the information of the traffic and to some predefined policies, and apply these actions. In order to perform such tasks, the best Key Performance Indicators (KPIs) for a given set of video traces are selected. A QoE Model is trained to define a global QoE for the set of traces. When an alert regarding degradation in the quality appears, a proper mitigation plan is activated to mitigate this situation. The performance of QoEMU has been evaluated over a degradation situation experiments with different video users.

show abstract

Analysis of Limitations of Mobility Load Balancing in a Live LTE System

Cited by 19 publications

References 6 publications

Pareto Deterministic Policy Gradients and Its Application in 5G Massive MIMO Networks

Pareto Deterministic Policy Gradients and Its Application in 5G Massive MIMO Networks

Network Architecture and Essential Features for 5G: The SESAME Project Approach

A Quality of Experience Management Framework for Mobile Users

Contact Info

Product

Resources

About