QoE-Driven Edge Caching in Vehicle Networks Based on Deep Reinforcement Learning

Song, Chunhe; Xu, Wenxiang; Wu, Tingting; Yu, Shimao; Zeng, Peng; Zhang, Ning

doi:10.1109/tvt.2021.3077072

Cited by 64 publications

(27 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…User and Context related IFs can be gender, age, social, characteristics, education, user location, background, usage history, living environments, job, personal interest and others. These factors can be measured by using User Engagement metrics such as records of user profile and background, number of downloads, average visit time, screen views per visits, retention rate, user event tracking (e.g., search history), and others [49], [50], [51], [52], [53], [54], [6], [55], [51]. All of these measurements can be utilized by Machine Learning approaches to tailor quality of experience at User level, which is dependent on marketing strategies.…”

Section: A Qoe Cause Factorsmentioning

confidence: 99%

“…As a result, many prior works proposed QoE-related things by using objective QoE metrics. QoE metrics can be estimated from various factors : network delay and quality, [50], [61], [62], [63], [77], [78], [64], [54], [6], latency [79], energy consumption [80], [81] processing and completion time [82], resource states [83], [81], contentrelated metrics (e.g., voice, video, image) [84], [85], [86], [87], and user-related metrics [49], [81] User and Context related IFs : gender, age, social, characteristics, education, user location (e.g., home, workplaces), live style, background, usage history, living environment, workplace, job, personal interest, memory experiences user engagement metrics : user background and profiles, number of downloads, average visit time, screen views per visits, retention rate, number of active users, user event tracking (e.g., search history), user satisfaction metrics (e.g., app rating, touch heatmap, in-app feedback), user perception metrics (app crashes, speed, latency) [49], [50], [51], [52], [53], [54], [6], [55], [51] marketing strategies and tuning designs for users e.g., machine learning approaches for tailor-made experience for each user Application (Contentrelated)…”

Section: B Qoe Measurement and Indicatormentioning

confidence: 99%

“…User-relate metrics can be user tendency, profile, users' device status, class-based metrics and others. Mushtaq et al [50] and Song et al [49] included user profiles into their QoE model. User engagement and perception metrics are applied in [51], [52], [53], [54], [6], [55], [131].…”

Section: B Qoe Metricsmentioning

confidence: 99%

“…Thus, access time to services or contents are significantly reduced by optimizing caching policies. Recent caching policies were designed to reduce latency and decrease traffic in Edge Computing [146], [134], [147], [133] , Mobile Edge Computing (MEC) [85], [148], [149], [135], [87], [86] , Fog Radio Access Networks (RANs) [150], [151], [152] and other Access Networks [153], [49], [55] Since Data caching helps the system reducing latency between IoT devices and Edge/Fog, or Edge/Fog and Cloud, minimizing content retrieval time and maximizing Caching Hit Rate (CHR) will result in significant improvement of QoS/QoE due to much lower access time. However, many works proposed new caching policies with only QoS consideration.…”

Section: Qos/qoe and Data Cachingmentioning

confidence: 99%

See 3 more Smart Citations

QoE-Driven IoT Architecture: A Comprehensive Review on System and Resource Management

et al. 2022

View full text Add to dashboard Cite

Internet of Things (IoT) services have grown substantially in recent years. Consequently, IoT service providers (SPs) are emerging in the market and competing to offer their services. Many IoT applications utilize these services in an integrated manner with different Quality-of-Service (QoS) requirements. Thus, the provisioning of end-to-end QoS is getting more indispensable for IoT platforms. However, provisioning the system by using only QoS metrics without considering user experiences is not sufficient. Recently, Quality of Experience (QoE) model has become a promising approach to quantify actual user experiences of services. A holistic design approach that considers constraints of various QoS/QoE metrics together is needed to satisfy requirements of these applications and services. Besides, IoT services may operate in environments with limited resources. Therefore, effective management of services and system resources is essential for QoS/QoE support. This paper provides a comprehensive survey for the state-of-the-art studies on IoT services with QoS/QoE perspective. Our contributions are threefold: (1) QoEdriven architecture is demonstrated by classifying vital components according to QoE-related functions in prior studies, (2) QoE metrics and QoE optimization objectives are classified by corresponding system and resource control problems in the architecture, and (3) QoE-aware resource management e.g., QoE-aware offloading, placement and data caching policies with recent Machine Learning approaches are extensively reviewed. INDEX TERMSInternet of Things, Quality of Service, Quality of Experience, IoT services, IoT applications, QoS for IoT services, QoS metrics, QoE metrics, IoT architecture Recently, emerging IoT architectures with multi-layers, e.g., Mobile Edge Computing (MEC), Fog Computing and Cloud Computing, have been proposed to improve user experiences.

show abstract

Section: A Qoe Cause Factorsmentioning

confidence: 99%

Section: B Qoe Measurement and Indicatormentioning

confidence: 99%

Section: B Qoe Metricsmentioning

confidence: 99%

Section: Qos/qoe and Data Cachingmentioning

confidence: 99%

See 2 more Smart Citations

QoE-Driven IoT Architecture: A Comprehensive Review on System and Resource Management

et al. 2022

View full text Add to dashboard Cite

show abstract

“…For travel research, route planning is crucial. Map navigation mobile applications represented by Baidu Maps and Gaode Map, as well as travel mobile applications represented by Drop Taxi provide users with relevant services, such as travel planning, displaying congested road sections, avoiding obstacle sections, and real-time navigation [ 4 ]. Nevertheless, the safety and comfort of the route are still difficult to be guaranteed.…”

Section: Introductionmentioning

confidence: 99%

Design of Travel Route Identification and Scheduling System Based on Artificial Intelligence-Aided Image Segmentation

Hou

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

This study designs a travel recognition and scheduling system using artificial intelligence and image segmentation techniques. To address the problem of low division quality of current point division algorithms, this study proposes a streaming graph division model based on a sliding window (GraphWin), which dynamically adjusts the amount of information (vertex degree information and adjacency information) referenced at each division according to the current division quality and division time by introducing a sliding window mechanism, to achieve the highest possible division while allowing loss of certain division efficiency. The goal is to improve the division quality as much as possible while allowing a certain loss of division efficiency. To meet the user’s need to travel through multiple destinations with the shortest route, this thesis proposes a deep reinforcement learning actor-critic (AC)-based multiobjective point path planning algorithm. The algorithm builds a strategy network and an evaluation network based on actor-critic’s multiobjective point path planning, updates the strategy network and evaluation network parameters using AC optimization training, reduces the reliance of the algorithm model on a large amount of high-quality label data, and speeds up the convergence speed of the deep reinforcement learning algorithm by pretraining, finally completing the multiobjective point access sequential path planning task. Finally, the personalized travel recommendation system is designed and implemented, and the system performance analysis is conducted to clarify the system requirements in terms of functional and nonfunctional aspects: the system architecture, system functional modules, and database tables are designed to conduct use case testing of the main functional modules of the system, and the usability of the attraction recommendation algorithm is verified through the concrete implementation of the functional modules such as attraction recommendation in the system.

show abstract

Hierarchical Reinforcement Learning-Based Mobility-Aware Content Caching and Delivery Policy for Vehicle Networks

Zhang

Lai

Yang

2023

Algorithms and Architectures for Parallel Processing

View full text Add to dashboard Cite

QoE-Driven Edge Caching in Vehicle Networks Based on Deep Reinforcement Learning

Cited by 64 publications

References 32 publications

QoE-Driven IoT Architecture: A Comprehensive Review on System and Resource Management

QoE-Driven IoT Architecture: A Comprehensive Review on System and Resource Management

Design of Travel Route Identification and Scheduling System Based on Artificial Intelligence-Aided Image Segmentation

Hierarchical Reinforcement Learning-Based Mobility-Aware Content Caching and Delivery Policy for Vehicle Networks

Contact Info

Product

Resources

About