Intelligent Handover Management in 5G Mobile Networks based on Recurrent Neural Networks

Maksymyuk, Taras; Han, Longzhe; Larionov, Stanislav; Shubyn, Bohdan; Luntovskyy, Andriy; Klymash, Mykhailo

doi:10.1109/aiact.2019.8847734

Cited by 29 publications

(28 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Для проведення експерименту згенеровано навчальну вибірку, яка імітує кількість запитів до інформаційного ресурсу для кожної комірки в залежності від часу доби. Для обробки такого типу даних створено модель рекурентної нейронної мережі на основі архітектури GRU, яка має доведену ефективність для розв'язку задач регресії [15].…”

Section: прогнозування популярності контенту на основі рекурентних нейронних мережunclassified

Method of intelligent content management in mobile networks

Maksymyuk¹,

Shubyn²,

Андрущак³

et al. 2020

TIT

View full text Add to dashboard Cite

With the advent of 5G, the market has been expecting the immersive user experience with rich multimedia content. Meeting such requirements within the physical constraints of limited spectrum and infrastructure availability is a challenging task, which prevents operators to scale their services properly. Currently, mobile operators are forced to invest large amount of money in their infrastructure, in order to maximize the capacity by network densification and higher frequency reuse factors. The dark side of such trend is that infrastructure becomes more expensive, spectrum price is getting higher and total cost of ownership for operator increases drastically. Nowadays, with the rise of artificial intelligence, cloud and edge computing the network becomes more flexible that opens many opportunities to enhance the performance and user experience. In this paper, we propose a new approach for content management in mobile network by using predictive caching of rich multimedia content in edge servers. Proposed approach is based on the content popularity prediction by using recurrent neural networks, that allows to deliver corresponding content in the close proximity to the target end users by the time it will be needed. Simulation results show that the proposed model is more than 90% accurate for both daily and weekly timeframes. Furthermore, we develop a method of personalized content caching in user devices based on their subscriptions and preferences, to make sure that user will have the best experience. Proposed approach for content management allows to improve the overall network performance by proactive content caching during the time of low network load. Moreover, the proactive caching allows to download the content in the best quality, regardless of the network congestions and bottlenecks.

show abstract

Section: прогнозування популярності контенту на основі рекурентних нейронних мережunclassified

Method of intelligent content management in mobile networks

Maksymyuk¹,

Shubyn²,

Андрущак³

et al. 2020

TIT

View full text Add to dashboard Cite

show abstract

“…Some of these include deep and reinforcement learning (RL) handoffs (HOs). The challenge is that most of the previous HO works [3][4][5][6] selected target cells on the basis of initial maximum network performance values. However, the challenge is that the optimum initial value does not always guarantee reliability of the connection after HO.…”

Section: Introductionmentioning

confidence: 99%

“…However, the challenge is that the optimum initial value does not always guarantee reliability of the connection after HO. For instance, the selection of mmWave target links based on the highest SINR values [4][5][6][7] does not always reveal the reliability of the link after a HO or caching [7] event. In most cases, HOs end up getting executed too early, too late, wrongly, or wastefully.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Handover for 5G mmWave Mobile Networks Using Jump Markov Linear System and Deep Reinforcement Learning

Chiputa

Zhang

Ali

et al. 2022

Sensors

View full text Add to dashboard Cite

The Fifth Generation (5G) mobile networks use millimeter waves (mmWaves) to offer gigabit data rates. However, unlike microwaves, mmWave links are prone to user and topographic dynamics. They easily get blocked and end up forming irregular cell patterns for 5G. This in turn causes too early, too late, or wrong handoffs (HOs). To mitigate HO challenges, sustain connectivity, and avert unnecessary HO, we propose an HO scheme based on a jump Markov linear system (JMLS) and deep reinforcement learning (DRL). JMLS is widely known to account for abrupt changes in system dynamics. DRL likewise emerges as an artificial intelligence technique for learning highly dimensional and time-varying behaviors. We combine the two techniques to account for time-varying, abrupt, and irregular changes in mmWave link behavior by predicting likely deterioration patterns of target links. The prediction is optimized by meta training techniques that also reduce training sample size. Thus, the JMLS–DRL platform formulates intelligent and versatile HO policies for 5G. When compared to a signal and interference noise ratio (SINR) and DRL-based HO scheme, our HO scheme becomes more reliable in selecting reliable target links. In particular, our proposed scheme is able to reduce wasteful HO to less than 5% within 200 training episodes compared to the DRL-based HO scheme that needs more than 200 training episodes to get to less than 5%. It supports longer dew time between HOs and high sum rates by ably averting unnecessary HOs with almost half the HOs compared to a DRL-based HO scheme.

show abstract

“…Some of these include Deep and Reinforcement Learning (RL) Handoffs (HOs). The challenge is that most of the previous HO works [5,7] select target cells based on initial maximum network performance values. However, the challenge is the optimum initial value do not always guarantee reliability of the connection after HO.…”

Section: Introductionmentioning

confidence: 99%

“…However, the challenge is the optimum initial value do not always guarantee reliability of the connection after HO. For instance, the selection of mmWave target links based on highest SINR values [4][5][6][7], does not always reveal the reliability of the link after a HO event. In most cases, HOs end up getting executed too early, too late, wrongly, or wastefully.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Handover for 5G Mobile Networks using Jump Markov Linear System and Deep Reinforcement Learning

Chiputa¹,

Zhang²,

Ali³

et al. 2021

Preprint

View full text Add to dashboard Cite

The fifth Generation (5G) mobile networks use millimeter Waves (mmWaves) to offer giga bit data rates. However, unlike microwaves, mmWave links are prone to user and topographic dynamics. They easily get blocked and end up forming irregular cell patterns for 5G. This in turn cause too early, too late, or wrong handoffs (HOs). To mitigate HO challenges, sustain connectivity and avert unnecessary HO, we propose a HO scheme based on Jump Markov Linear System (JMLS) and Deep Reinforcement Learning (DRL). JMLS is widely known to account for abrupt changes in system dynamics. DRL likewise emerges as an artificial intelligence technique for learning highly dimensional and time-varying behaviors. We combine the two techniques to account for time-varying, abrupt, and irregular changes in mmWave link behaviour by predicting likely deterioration patterns of target links. The prediction is optimized by meta training techniques that also reduces training sample size. Thus, the JMLS-DRL platform formulates intelligent and versatile HO policies for 5G. Results show our proposed prediction scheme about target link behavior post HO to be highly reliable. The scheme also averts unnecessary HOs thus ably supports longer dew time.

show abstract

Intelligent Handover Management in 5G Mobile Networks based on Recurrent Neural Networks

Cited by 29 publications

References 6 publications

Method of intelligent content management in mobile networks

Method of intelligent content management in mobile networks

Enhancing Handover for 5G mmWave Mobile Networks Using Jump Markov Linear System and Deep Reinforcement Learning

Enhancing Handover for 5G Mobile Networks using Jump Markov Linear System and Deep Reinforcement Learning

Contact Info

Product

Resources

About