Reinforcement learning-based solution for resource management in fog computing: A comprehensive survey

Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 127214 - 127214

Опубликована: Март 1, 2025

Язык: Английский

---

Edge Learning for 6G-Enabled Internet of Things: A Comprehensive Survey of Vulnerabilities, Datasets, and Defenses

IEEE Communications Surveys & Tutorials, Год журнала: 2023, Номер 25(4), С. 2654 - 2713

Опубликована: Янв. 1, 2023

The deployment of the fifth-generation (5G) wireless networks in Internet Everything (IoE) applications and future (e.g., sixth-generation (6G) networks) has raised a number operational challenges limitations, for example terms security privacy. Edge learning is an emerging approach to training models across distributed clients while ensuring data Such when integrated network infrastructures 6G) can potentially solve challenging problems such as resource management behavior prediction. However, edge (including deep learning) are known be susceptible tampering manipulation. This survey article provides holistic review extant literature focusing on learning-related vulnerabilities defenses 6G-enabled Things (IoT) systems. Existing machine approaches 6G–IoT learning-associated threats broadly categorized based modes, namely: centralized, federated, distributed. Then, we provide overview enabling technologies intelligence. We also existing research attacks against classify threat into eight categories, backdoor attacks, adversarial examples, combined poisoning Sybil byzantine inference dropping attacks. In addition, comprehensive detailed taxonomy comparative summary state-of-the-art defense methods vulnerabilities. Finally, new realized, overall prospects IoT discussed.

Язык: Английский

---

Seagull optimization algorithm based multi-objective VM placement in edge-cloud data centers

Internet of Things and Cyber-Physical Systems, Год журнала: 2023, Номер 3, С. 28 - 36

Опубликована: Янв. 1, 2023

Edge-Cloud Datacenters (ECDCs) have been massively exploited by the owners of technology and industrial centers to satisfy user demand. At same time, amount energy used these data is considerable. To address this challenge, Virtual Machine (VM) placement ECDCs plays an important role; therefore, assigning VM properly physical machines (PM) can significantly decrease consumption. The applied technique simultaneously must consider additional objectives involving traffic power usage network elements, which makes it a challenging problem. This paper proposes multi-objective approach in edge-cloud centers, uses Seagull optimization optimize together. In strategy, among PMs reduced concentrating communications VMs on reduce transferred through PMs' consumption consolidating fewer PMs, consumes less energy. We evaluate with simulations CloudSim test two different topologies, VL2 (Virtual Layer 2) three-tier, validate that proposed effectively ECDCs. experimental results show our method 5.5% while reducing 70% components 80%.

Язык: Английский

---

Energy efficient task scheduling based on deep reinforcement learning in cloud environment: A specialized review

Future Generation Computer Systems, Год журнала: 2023, Номер 151, С. 214 - 231

Опубликована: Окт. 14, 2023

Язык: Английский

---

Reinforcement learning based task offloading of IoT applications in fog computing: algorithms and optimization techniques

Cluster Computing, Год журнала: 2024, Номер 27(8), С. 10299 - 10324

Опубликована: Май 17, 2024

Язык: Английский

---