Direction prediction assisted handover using the multilayer perception neural network to reduce the handover time delays in LTE networks
TL;DR: An advanced technique using the historical information to reduce the handover time delay as much as possible depending on the packet loss, the time required for the base station to reply and the region domain as muchAs the time domain is proposed.
Abstract: Nowadays, the rapid increase in the development of the wireless communication, the Evolved Universal Terrestrial Radio Access (E-UTRA) of the Long Term Evolution (LTE) is more improved and modern technology compared with the WiMAX technology. The researchers discussed the accurate and fast handover in the LTE in the recent years. Moreover, the researchers of the evolved Node B(eNB) proposed the history of the UE visited base stations and the use of their information just to consider the target in the case of handover. While the identification of the cell and their times were kept inside the cell of the base station. In this paper, an advanced technique using the historical information to reduce the handover time delay as much as possible depending on the packet loss, the time required for the base station to reply and the region domain as much as the time domain. In conclusion, the angle of the situated target base station is computed and the distance to that base station is taken into consideration for cutting down more and more real-time of the handover procedure in the LTE system. The simulation results showed that the proposed model is more efficacious in decreasing the handover time delay by skipping unwanted base station according to their angles.
Citations
More filters
02 Dec 2020
TL;DR: In this article, an ANN-FL protocol that addressed both security and QoS in 5G and B5G networks was developed. But, the proposed protocol was not robust against attacks such as de-synchronization and tracing attacks and yielded a 27.1% increase in handover success rate, 27.3% reduction in handoff failure rate, and a 24.1 percent reduction in ping pong handovers.
Abstract: Technical network challenges in 5G relates to handover authentication, user privacy protection and resource management. Due to interoperability requirements among the heterogeneous networks (Hetnets), the security requirements for 5G are high compared to 2G, 3G and 4G. The current 5G handover protocols are based on either fuzzy logic (FL), artificial neural networks (ANN), blockchain, software defined network (SDN), or Multi-layer Feed Forward Network (MFNN). These protocols have either long latencies or focus on either security or quality of services parameters such as user satisfaction. The usage of these inefficient authentication schemes during 5G handovers lead to performance degradation in heterogeneous cells and increases the delay. In addition, 5G networks experience frequent handover failures and increased handover delays. Consequently, the provision of strong security, privacy and low latency handovers is required for the successful deployment of 5G networks such as 5G wireless local area networks (5G-WLAN) heterogeneous networks. These new requirements, coupled with demands for higher scalability, reliability, security, data rates, quality of service (QoS), and support for internet of everything (IoE) have seen the shift from 5G to beyond 5G (B5G). However, 5G and B5G are incapable of providing the complete requirements of IoE such as enhanced security and QoS. This paper sought to develop an ANN-FL protocol that addressed both security and QoS in 5G and B5G networks. The simulation results showed that the developed protocol was robust against attacks such de-synchronization and tracing attacks and yielded a 27.1% increase in handover success rate, a 27.3% reduction in handover failure rate, and a 24.1% reduction in ping pong handovers.
13 citations
TL;DR: It is established through simulation results that the proposed approach yields significantly improved handover performance mitigating mobility problem in ultra-dense cellular networks to notable extent.
Abstract: Since the advent of 1G through 5G networks, telecommunication industry has gone through phenomenal transformation in the way we communicate, we work, and we socialize. In dense or ultra-dense mobile communication networks, the users are very frequently handed over to other cells making seamless mobility a challenging and complex problem. Therefore, robust connectivity in such networks becomes a very critical issue. In this paper, we present a data-driven handover optimization approach aiming to mitigate the mobility problems including handover delay, early handover, wrong selection of target cell and frequent handover. The proposal is based on collecting the information from the network and developing a model to determine the relationship between the features drawn from the collected dataset and key performance indicator (KPI) expressed as the weighted average of mobility problem ratios. Handover design parameters- time to trigger and handover margin are optimized to improve KPI. The KPI estimation drawn on time to trigger and hysteresis margin design parameters is estimated through neural network multilayer perception method. It is established through simulation results that the proposed approach yields significantly improved handover performance mitigating mobility problem in ultra-dense cellular networks to notable extent.
13 citations
TL;DR: An ensemble classifier comprising of K-Nearest Neighbours (KNN), Naive Bayes (NB), Decision Tree (DT) and Support Vector Machine (SVM) is built, trained and tested and shows that the proposed classifier has the best performance in terms of precision, recall, F-measure and classification accuracy.
Abstract: Machine learning algorithms have been deployed in numerous optimization, prediction and classification problems. This has endeared them for application in fields such as computer networks and medical diagnosis. Although these machine learning algorithms achieve convincing results in these fields, they face numerous challenges when deployed on imbalanced dataset. Consequently, these algorithms are often biased towards majority class, hence unable to generalize the learning process. In addition, they are unable to effectively deal with high-dimensional datasets. Moreover, the utilization of conventional feature selection techniques from a dataset based on attribute significance render them ineffective for majority of the diagnosis applications. In this paper, feature selection is executed using the more effective Neighbour Components Analysis (NCA). During the classification process, an ensemble classifier comprising of K-Nearest Neighbours (KNN), Naive Bayes (NB), Decision Tree (DT) and Support Vector Machine (SVM) is built, trained and tested. Finally, cross validation is carried out to evaluate the developed ensemble model. The results shows that the proposed classifier has the best performance in terms of precision, recall, F-measure and classification accuracy.
6 citations
07 Jun 2020
TL;DR: It is argued that simple methods can sometimes outperform more sophisticated ones and be used to identify favorable edge nodes to host the mobile applications, to best provide continuous and QoS-aware service for mobile users.
Abstract: As the research community inclines toward adopting increasingly complex techniques for future networks, and simple methods are often ignored, being labeled as trivial. In this paper, we argue that simple methods can sometimes outperform more sophisticated ones. We demonstrate that by evaluating two prediction mechanisms to forecast mobile user's handovers exploiting user-network association patterns. We perform a series of experiments on real-world data, evaluating the performance characteristics of such methods over more sophisticated and complex prediction techniques. Furthermore, we discuss how to easily bootstrap these mechanisms into the 5G network architecture. We suggest the use of these methods associated with Multi-access Edge Computing (MEC) scenarios, as a mean to identify favorable edge nodes to host the mobile applications, to best provide continuous and QoS-aware service for mobile users.
5 citations
Cites methods from "Direction prediction assisted hando..."
...Machine learning algorithms were also utilized for handover prediction as in [13], where a Long Short Time Memory (LSTM) neural network was employed, and [14] which used multi-layer perception neural network for direction prediction assisted handover....
[...]
01 Nov 2019
TL;DR: In this paper, the authors examined several works carried out on a handover criteria (hysteresis margin) needed for designing an effective handover framework, which is based on the received signal strength between both target and serving eNodeBs, and its proper determination amongst other advantages mitigated the rate of unnecessary and repeated handover (ping-pong effect).
Abstract: The technology, Long Term Evolution (LTE) developed by 3rd Generation Partnership Project
is considered an improved standard in mobile communications when compared to previously attained
network standards. LTE with prospects of decreased latency levels and support of downlink and uplink
transmission at data rates exceeding 100Mbps and 50Mbps, an effective handover framework needs to be
put in place to improve quality of service rendered to the network users and decrease wastage of network
resources. This study examines several works carried out on a handover criteria (hysteresis margin) needed
for designing an effective handover framework. This margin is based on the received signal strength
between both target and serving eNodeBs, and its proper determination amongst other advantages mitigates
the rate of unnecessary and repeated handover (ping-pong effect). The model presented in this research
integrates the artificial neural network (ANN) mechanism into the determination of hysteresis margin in
the LTE handover process which is to minimize handover delay and ping-pong taking into consideration
the speed of the user equipment (UE).
3 citations
References
More filters
TL;DR: The main technologies for LTE-Advanced are explained, together with possible improvements, their associated challenges, and some approaches that have been considered to tackle those challenges.
Abstract: This paper provides an in-depth view on the technologies being considered for Long Term Evolution-Advanced (LTE-Advanced). First, the evolution from third generation (3G) to fourth generation (4G) is described in terms of performance requirements and main characteristics. The new network architecture developed by the Third Generation Partnership Project (3GPP), which supports the integration of current and future radio access technologies, is highlighted. Then, the main technologies for LTE-Advanced are explained, together with possible improvements, their associated challenges, and some approaches that have been considered to tackle those challenges.
490 citations
TL;DR: A new handover algorithm known as LTE Hard Handover Algorithm with Average Received Signal Reference Power (RSRP) Constraint (LHHAARC) is proposed in order to minimize number of handovers and the system delay as well as maximize the system throughput.
Abstract: Hard handover mechanism is adopted to be used in 3GPP Long Term Evolution (3GPP LTE) in order to reduce the complexity of the LTE network architecture. This mechanism comes with degradation in system throughput as well as a higher system delay. This paper proposes a new handover algorithm known as LTE Hard Handover Algorithm with Average Received Signal Reference Power (RSRP) Constraint (LHHAARC) in order to minimize number of handovers and the system delay as well as maximize the system throughput. An optimized system performance of the LHHAARC is evaluated and compared with three well-known handover algorithms via computer simulation. The simulation results show that the LHHAARC outperforms three well-known handover algorithms by having less number of average handovers per UE per second, shorter total system delay whilst maintaining a higher total system throughput.
52 citations
07 Jul 2014
TL;DR: An advance UE history information is proposed, reducing the handover failure rate and ping-pong handover rate by using the history information like Region-Domain, Time-Domain and Time To Trigger.
Abstract: In response to the rapidly developing of wireless communication technology, the deployed of eNB is denser and more complex. The research of how to handover accurately and fast in LTE-A are discussed much in recent years .In 3GPP Release 8, the UE History Information recorded by eNB was first proposed, it's proposed to provide eNB to judge the target eNB when handover. The history information includes the Cell ID and Time UE stayed in cell. We proposed an advance UE history information, reducing the handover failure rate and ping-pong handover rate by using the history information like Region-Domain, Time-Domain and Time To Trigger.
20 citations
TL;DR: A new handover approach enhancing the existing handover schemes is proposed mainly based on the two notions of handover management: lazy hand over for avoiding ping-pong effect and early handover for handling real-time services.
Abstract: Handover is one of the key operations in the mobility management of long-term evolution (LTE)-based systems. Hard handover decided by handover margin and time to trigger (TTT) has been adopted in third Generation Partnership Project (3GPP) LTE with the purpose of reducing the complexity of network architecture. Various handover algorithms, however, have been proposed for 3GPP LTE to maximize the system goodput and minimize packet delay. In this paper, a new handover approach enhancing the existing handover schemes is proposed. It is mainly based on the two notions of handover management: lazy handover for avoiding ping-pong effect and early handover for handling real-time services. Lazy handover is supported by disallowing handover before the TTT window expires, while early handover is supported even before the window expires if the rate change in signal power is very large. The performance of the proposed scheme is evaluated and compared with two well-known handover algorithms based on goodput per cell, average packet delay, number of handovers per second, and signal-to-interference-plus-noise ratio. The simulation with LTE-Sim reveals that the proposed scheme significantly enhances the goodput while reducing packet delay and unnecessary handover.
14 citations
TL;DR: Soft frequency reuse (SFR) and multiple preparations (MP), so‐called SFRAMP, are proposed to provide a seamless and fast handover with high throughput by keeping the ICI low and results show that the outage probability and delay are reduced.
Abstract: will increase the signalling exchanges between the serving eNB and the target eNB, resulting in increased ICI. This is overcome by means of our proposed Soft Frequency Reuse (SFR). Simulation results using LTE-Sim show that the outage probability and delay are reduced by 24.4% and 11.9% respectively, over the HHO method, which is quite significant.
11 citations