An Efficient Movement-Based Handover Prediction Scheme for Hierarchical Mobile IPv6 in VANETs

Aljeri, Noura; Boukerche, Azzedine

doi:10.1145/3243046.3243053

Cited by 9 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SNR prediction was added to a conventional HO algorithm to proactively trigger HOs in a mmWave vehicular network. By matching the vehicle's predicted future location with known BS locations, the algorithm proposed in [29] could proactively trigger optimal HOs while reducing the complexity of HO decision making. A recurrent neural network (RNN) based auto-encoder and a multi-layer perception neural network were developed in [30] for HO optimization based on the quality of experience after HO by combining various information gathered throughout the LTE protocol stack for a regression task to assist in optimal HO decision making and provided generalization ability across different scenario setups.…”

Section: Related Workmentioning

confidence: 99%

Intelligent Handover Algorithm for Vehicle-to-Network Communications With Double-Deep Q-Learning

Tan

Bremner

Kernec

et al. 2022

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

For vehicle-to-network communications, handover (HO) management enables vehicles to maintain the connection with the network while transiting through coverage areas of different base stations (BSs). However, the high mobility of vehicles means shorter connection periods with each BS that leads to frequent HOs, hence raises the necessity for optimal HO decision making for high quality infotainment services. Machine learning is capable of capturing underlying pattern via data driven methods to find optimal solutions to complex problems, and much learning-based HO optimization research has been conducted focusing on specific network setups. However, attention still needs to be paid to the actual deployment aspect and standardized datasets or simulation environments for evaluation. This paper proposes a deep reinforcement learning-based HO algorithm using the input parameters that are configurable in the existing measurement report of cellular networks. The performance of the proposed algorithm is evaluated using the well-known network simulator ns-3 with its official LTE module. A realistic network setup in the city center of Glasgow (UK) is configured with vehicle trajectories generated by the routes mobility model using Google Maps Directions API. Evaluation results reveal that the proposed algorithm significantly outperforms the A3 RSRP baseline with an average of 25.72% packet loss reduction per HO, suggesting significant improvement in quality of service of phone call and video streaming, etc. The proposed algorithm also has a small implementation cost compared to some state-of-the-art and should be deployed by a software update to a local BS controller.

show abstract

Section: Related Workmentioning

confidence: 99%

Intelligent Handover Algorithm for Vehicle-to-Network Communications With Double-Deep Q-Learning

Tan

Bremner

Kernec

et al. 2022

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

show abstract

“…HMM can also be combined with other algorithms for next-cell prediction. The work of [45] proposes a vehicle network movement prediction approach based on the combination of HMM with Kalman filtering. The authors take the mobility information of vehicles as the observable states and the connected AP as the hidden states.…”

Section: A) Evaluationmentioning

confidence: 99%

A Survey on Next-Cell Prediction in Cellular Networks: Schemes and Applications

2020

View full text Add to dashboard Cite

Mobility prediction is a powerful tool for network operators to optimize network performance. From cell level, if network operators know the cells to which the users will be connected in advance, wireless resources can be pre-allocated to improve network performance and better user experience can be provided in location-based services. Many next-cell prediction models and methods have been suggested and implemented. This paper is devoted to next-cell prediction (cell level mobility prediction) in cellular networks, and provides a thorough survey of the prediction schemes and applications. Particularly, a two-level classification methodology was proposed and applied. We first divided the prediction schemes into three categories based on the mobility data used for prediction, i.e. Current Movement State based Approaches (CMSA), Historical Movement Pattern based Approaches (HMPA), and HybriD Approaches (HDA). Prediction schemes in each category were further classified based on the used prediction methods. The typical application scenarios were introduced as well, including handover management, resource allocation, etc. Finally, current challenges and potential trends in the near future were further discussed.

show abstract

“…Some of the identified challenges can benefit from existing mechanisms. For instance, handover prediction methods [105]- [107] can avail proactive service migration in choosing the target edge node to host the migrated service. Additionally, service downtime can be minimized by adopting novel migration mechanisms such as thread-based or paralleled live migrations [108], [109], which efficiently migrate memory intensive VMs by creating multiple threads parallel to the VM threads in the hypervisors at both source and destination hosts, coupled with compression techniques.…”

Section: Future Work Directionsmentioning

confidence: 99%

QoS-Aware Service Continuity in the Virtualized Edge

2019

View full text Add to dashboard Cite

5G systems are envisioned to support numerous delay-sensitive applications such as the tactile Internet, mobile gaming, and augmented reality. Such applications impose new demands on service providers in terms of the quality of service (QoS) provided to the end-users. Achieving these demands in mobile 5G-enabled networks represent a technical and administrative challenge. One of the solutions proposed is to provide cloud computing capabilities at the edge of the network. In such vision, services are cloudified and encapsulated within the virtual machines or containers placed in cloud hosts at the network access layer. To enable ultrashort processing times and immediate service response, fast instantiation, and migration of service instances between edge nodes are mandatory to cope with the consequences of user's mobility. This paper surveys the techniques proposed for service migration at the edge of the network. We focus on QoS-aware service instantiation and migration approaches, comparing the mechanisms followed and emphasizing their advantages and disadvantages. Then, we highlight the open research challenges still left unhandled.

show abstract

An Efficient Movement-Based Handover Prediction Scheme for Hierarchical Mobile IPv6 in VANETs

Cited by 9 publications

References 21 publications

Intelligent Handover Algorithm for Vehicle-to-Network Communications With Double-Deep Q-Learning

Intelligent Handover Algorithm for Vehicle-to-Network Communications With Double-Deep Q-Learning

A Survey on Next-Cell Prediction in Cellular Networks: Schemes and Applications

QoS-Aware Service Continuity in the Virtualized Edge

Contact Info

Product

Resources

About