Intelligent Handover Triggering Mechanism in 5G Ultra-Dense Networks Via Clustering-Based Reinforcement Learning

Liu, Qianyu; Kwong, Chiew Foong; Sun, Wei; Li, Lincan; Zhang, Sibo

doi:10.1007/s11036-020-01718-w

Cited by 26 publications

(22 citation statements)

References 25 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors in Reference 51 presented a FL based VHO management process in which fuzzylite dataset was used to accomplish the necessary quality assessments and to simplify the design of practical systems. The authors in Reference 52 proposed a smart HO initiating scheme for access point using Q‐learning and subtractive clustering concepts in 5G ultra‐dense network. Fuzzy logic based systems are complex in nature, and also the results produced by these systems may not be accurate always and are totally depends on expertize and hypothesis.…”

Section: Related Workmentioning

confidence: 99%

An efficient multicriteria‐based vertical handover decision‐making algorithm for heterogeneous networks

Satapathy

Mahapatro

2021

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Heterogeneous networks are designed to offload or route some of data traffics of mobile networks through other co‐located wireless access networks. This technique apparently increases the capacity of mobile network. In such networks, a vertical handover process plays an important role in providing seamless and uninterrupted connectivity as well as the required level of quality‐of‐service along with a wide coverage for all mobile nodes. Traditional vertical handover algorithms that are based on single criterion (eg, received signal strength) are not performing well in terms of excess handover rates, ping‐pong effects, handover delays, handover cost, etc. This research presents an efficient multicriteria‐based vertical handover decision‐making algorithm for heterogeneous networks. This algorithm uses a two‐step execution procedure, the first step evaluates whether the handover is needed or not before initiating a handover process, if needed, then a set of feasible solutions are generated for the vertical handover problem formulated as a multi‐objective optimization problem with two objective functions such as quality factor of networks and handover processing cost. In the second step, an optimal solution (ie, an appropriate access network) for handover is obtained using a hybrid approach of fuzzy analytic hierarchy process (FAHP) and technique for order preference by similarity to ideal solution (TOPSIS). Our simulation study shows that the proposed algorithm performs well as compared to some other existing algorithms (ie, single‐criterion based, multicriteria with AHP, multicriteria with TOPSIS, and multicriteria with both AHP and TOPSIS) in terms of performance metrics such as handover rate, delay, cost, and energy consumption.

show abstract

Section: Related Workmentioning

confidence: 99%

An efficient multicriteria‐based vertical handover decision‐making algorithm for heterogeneous networks

Satapathy

Mahapatro

2021

Trans Emerging Tel Tech

View full text Add to dashboard Cite

show abstract

“…Based on Q-learning frameworks and subtractive clustering approaches, article [26] offers an intelligent handover triggering system for UE. Subtractive clustering is used to transform the input measurements to state vectors, which can increase the training process's efficiency and efficacy.…”

Section: Related Workmentioning

confidence: 99%

A Fuzzy Based Handover Decision Scheme for Mobile Devices Using Predictive Model

Gupta

Goel²,

Garg³

et al. 2021

Electronics

View full text Add to dashboard Cite

Handover usually deals with the mobility of the end users in a mobile network to assure about the ongoing session of a user. It is observed that frequent handover results in call dropping due to latency. In order to overcome this issue, a fuzzy based handover decision scheme for mobile devices using a predictive model is proposed. First, an MFNN (Multi-layer Feed Forward Network) is used to determine the next cell of the user along with best hand off time. To obtain the best access network, multiple-attribute Access Network Selection Function (ANSF) is used. The fuzzy rule is applied by considering the parameter data rate, reliability, signal strength, battery power and mobility as input and the output obtained is the optimal network. The proposed scheme selects the best access network and enhances the quality of services.

show abstract

“…Apart from that, several artificial intelligence (AI) techniques have been proposed in the literature to improve the handover performance in UDNs [26]- [28]. In [26], the handover method based on multi-agent reinforcement learning was presented to reduce the frequent handovers while increasing the overall throughput.…”

Section: Introductionmentioning

confidence: 99%

“…The deep Q learning technique based on the channel and load balancing characteristics of the UE has been exploited to optimize the handover procedure in UDNs [27]. With the purpose of enhancing mobility robustness while maintaining the quality of service (QoS) requirements, the Q learning method was studied in [28] to obtain an optimal handover triggering policy. It is worth noting that the previous research efforts only consider the handover analysis in the traditional handover scheme, i.e., BS-to-BS handover scheme.…”

Section: Introductionmentioning

confidence: 99%

User-Centric Cooperative Transmissions-enabled Handover for Ultra-Dense Networks

Kibinda¹,

Ge²

2022

Preprint

View full text Add to dashboard Cite

The user-centric cooperative transmission provides a compelling way to alleviate frequent handovers caused by an ever-increasing number of randomly deployed base stations (BSs) in ultra-dense networks (UDNs). This paper proposes a new user-centric cooperative transmissions-based handover scheme, i.e., the group-cell handover (GCHO) scheme, with the aim of reducing the handover rate in UDNs. In the proposed scheme, the boundary of the cooperating cluster depends on the distance among the user equipment (UE) and cooperating BSs. The new scheme captures the dynamicity and irregularity of the cooperating cluster topology resulting from randomly distributed BSs. Based on stochastic-geometry tools where BSs locations are modeled as the Poison point process (PPP), we derive an analytical expression of the handover rate for the UE with an arbitrary movement trajectory. Furthermore, a GCHO skipping (GCHO-S) scheme is proposed to minimize the handover cost, i.e., the percentage of time wasted in handover signaling in user-centric cooperative transmissions scenarios. The numerical results show that the GCHO scheme decreases the handover rate by 42.3% and 72.7% compared with the traditional single BS association and fixed-region cooperative network topology handover approaches, respectively. Moreover, under the same group-cell size and constant velocity, the GCHO-S scheme diminishes the handover cost by 50% against the GCHO scheme.

show abstract

Intelligent Handover Triggering Mechanism in 5G Ultra-Dense Networks Via Clustering-Based Reinforcement Learning

Cited by 26 publications

References 25 publications

An efficient multicriteria‐based vertical handover decision‐making algorithm for heterogeneous networks

An efficient multicriteria‐based vertical handover decision‐making algorithm for heterogeneous networks

A Fuzzy Based Handover Decision Scheme for Mobile Devices Using Predictive Model

User-Centric Cooperative Transmissions-enabled Handover for Ultra-Dense Networks

Contact Info

Product

Resources

About