QoE-Driven IoT Architecture: A Comprehensive Review on System and Resource Management DOI Creative Commons
Boonyarith Saovapakhiran,

Wibhada Naruephiphat,

Chalermpol Charnsripinyo

et al.

IEEE Access, Journal Year: 2022, Volume and Issue: 10, P. 84579 - 84621

Published: Jan. 1, 2022

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

Language: Английский

COME-UP: Computation Offloading in Mobile Edge Computing with LSTM Based User Direction Prediction DOI Creative Commons

Sardar Khaliq uz Zaman,

Ali Imran Jehangiri, Tahir Maqsood

et al.

Applied Sciences, Journal Year: 2022, Volume and Issue: 12(7), P. 3312 - 3312

Published: March 24, 2022

In mobile edge computing (MEC), devices limited to computation and memory resources offload compute-intensive tasks nearby servers. User movement causes frequent handovers in 5G urban networks. The resultant delays task execution due unknown user position base station lead increased energy consumption resource wastage. current MEC offloading solutions separate from mobility. For offloading, techniques that predict the user’s future location do not consider direction. We propose a framework termed COME-UP Computation Offloading with Long-short term (LSTM) based direction prediction. nature of mobility data is nonlinear leads time series prediction problem. LSTM considers previous features, such as location, velocity, direction, input feed-forward mechanism train learning model next location. proposed architecture also uses fitness function calculate priority weights for selecting an optimum server on latency, energy, load. simulation results show latency are lower than baseline techniques, while utilization enhanced.

Language: Английский

Citations

36
MCOTM: Mobility-aware computation offloading and task migration for edge computing in industrial IoT DOI
Wei Qin, Haiming Chen, Lei Wang

et al.

Future Generation Computer Systems, Journal Year: 2023, Volume and Issue: 151, P. 232 - 241

Published: Oct. 10, 2023

Language: Английский

Citations

22
Energy efficient offloading scheme for MEC-based augmented reality system DOI
Abdelhamied A. Ateya, Ammar Muthanna, Andrey Koucheryavy

et al.

Cluster Computing, Journal Year: 2023, Volume and Issue: 26(1), P. 789 - 806

Published: Jan. 9, 2023

Language: Английский

Citations

17
Machine learning-based computation offloading in edge and fog: a systematic review DOI

Sanaz Taheri-abed,

Amir Masoud Eftekhari Moghadam, Mohammad Hossein Rezvani

et al.

Cluster Computing, Journal Year: 2023, Volume and Issue: 26(5), P. 3113 - 3144

Published: July 21, 2023

Language: Английский

Citations

17
An overview of mobility awareness with mobile edge computing over 6G network: Challenges and future research directions DOI Creative Commons
Soule Issa Loutfi, Ibraheem Shayea, Ufuk Türeli

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: 23, P. 102601 - 102601

Published: July 22, 2024

The evolution of science has given rise to many technologies that have changed the world. upcoming Six-Generation (6G) mobile network indicates a fundamental transformation in wireless technologies, enhancing connectivity and data transmission rates. In this circumstance, Mobile Edge Computing (MEC) is paradigm technology emerges as key major supporter mobility awareness. computing offers improved efficiency for service migration from edge node user. However, management MEC complex challenge seamless handovers between nodes must be efficiently executed ensure uninterrupted devices, demanding intricate coordination low-latency decision-making. To best author's knowledge, there been no comprehensive work on most recent developments awareness using 6G. paper aims present general overview intersection over 6G networks. concept networks comprehensively introduced. This will highlight integration bringing more efficient edge, reducing latency, user experience. Meanwhile, survey discusses augmented reality with applications. applications emphasizes need results providing communication during serving base station target station. study contributes understanding trends enable operation communication. Furthermore, we delve into challenges future research directions networks, underlining complexities potentials integrating computing.

Language: Английский

Citations

8
Deep Neural Networks meet computation offloading in mobile edge networks: Applications, taxonomy, and open issues DOI
Ehzaz Mustafa, Junaid Shuja, Faisal Rehman

et al.

Journal of Network and Computer Applications, Journal Year: 2024, Volume and Issue: 226, P. 103886 - 103886

Published: April 24, 2024

Language: Английский

Citations

7
Modified Artificial Bee Colony Based Feature Optimized Federated Learning for Heart Disease Diagnosis in Healthcare DOI Creative Commons
Muhammad Mateen Yaqoob, Muhammad Nazir, Abdullah Yousafzai

et al.

Applied Sciences, Journal Year: 2022, Volume and Issue: 12(23), P. 12080 - 12080

Published: Nov. 25, 2022

Heart disease is one of the lethal diseases causing millions fatalities every year. The Internet Medical Things (IoMT) based healthcare effectively enables a reduction in death rate by early diagnosis and detection disease. biomedical data collected using IoMT contains personalized information about patient this has serious privacy concerns. To overcome issues, several protection laws are proposed internationally. These created huge problem for techniques used traditional machine learning. We propose framework on federated matched averaging with modified Artificial Bee Colony (M-ABC) optimization algorithm to issues improve method prediction heart paper. technique improves accuracy, classification error, communication efficiency as compared state-of-the-art learning algorithms real-world dataset.

Language: Английский

Citations

27
DQN-enabled content caching and quantum ant colony-based computation offloading in MEC DOI
Chunlin Li, Yong Zhang, Youlong Luo

et al.

Applied Soft Computing, Journal Year: 2022, Volume and Issue: 133, P. 109900 - 109900

Published: Dec. 2, 2022

Language: Английский

Citations

24
Application and Research of IoT Architecture for End-Net-Cloud Edge Computing DOI Open Access
Yongqiang Zhang,

Hongchang Yu,

Wanzhen Zhou

et al.

Electronics, Journal Year: 2022, Volume and Issue: 12(1), P. 1 - 1

Published: Dec. 20, 2022

At the edge of network close to source data, computing deploys computing, storage and other capabilities provide intelligent services in proximity offers low bandwidth consumption, latency high security. It satisfies requirements transmission bandwidth, real-time security for Internet Things (IoT) application scenarios. Based on IoT architecture, an (EC-IoT) reference architecture is proposed, which contained three layers: The end edge, cloud edge. Furthermore, key technologies artificial intelligence (AI) technology EC-IoT analyzed. Platforms different locations are classified by comparing platforms. On basis industrial (IIoT) solution, Vehicles (IoV) a gateway-based smart home proposed. Finally, trends challenges examined, will have very promising applications.

Language: Английский

Citations

23
Deep Reinforcement Learning for Multi-Hop Offloading in UAV-Assisted Edge Computing DOI
Tiến Hoa Nguyễn, Do Van Dai, Le Lan

et al.

IEEE Transactions on Vehicular Technology, Journal Year: 2023, Volume and Issue: 72(12), P. 16917 - 16922

Published: July 6, 2023

In this paper, we propose a unmanned aerial vehicle (UAV)-assisted multi-hop edge computing (UAV-assisted MEC) system in which UE can offload its task to multiple UAVs fashion. particular, the offloads nearby UAV, and UAV execute part of received remaining neighboring UAV. The offloading process continues until execution is finished. benefit multihop that be finished faster, load shared among UAVs, thus avoiding overloading congestion. Each node, i.e., or needs determine size for minimize cumulative energy consumption latency over nodes. We formulate stochastic optimization problem under dynamics uncertainty UAV-assisted MEC system. Then, deep reinforcement learning (DRL) algorithm solve problem. Simulation results are provided demonstrate effectiveness DRL algorithm.

Language: Английский

Citations

15