Reinforcement Learning Methods for Computation Offloading: A Systematic Review

ACM Computing Surveys, Journal Year: 2023, Volume and Issue: 56(1), P. 1 - 41

Published: June 9, 2023

Today, cloud computation offloading may not be an appropriate solution for delay-sensitive applications due to the long distance between end-devices and remote datacenters. In addition, a can consume bandwidth dramatically increase costs. However, such as sensors, cameras, smartphones have limited computing storage capacity. Processing tasks on battery-powered energy-constrained devices becomes even more complex. To address these challenges, new paradigm called Edge Computing (EC) emerged nearly decade ago bring resources closer end-devices. Here, edge servers located end-device perform user tasks. Recently, several paradigms Mobile (MEC) Fog (FC) complement Cloud (CC) EC. Although are heterogeneous, they further reduce energy consumption task response time, especially applications. Computation is multi-objective, NP-hard optimization problem. A significant part of previous research in this field devoted Machine Learning (ML) methods. One essential types ML Reinforcement (RL), which agent learns how make best decision using experiences gained from environment. This article provides systematic review widely used RL approaches offloading. It covers complementary mobile computing, fog Internet Things. We explain reasons various methods technical point view. analysis includes both binary partial techniques. For each method, elements characteristics environment discussed regarding most important criteria. Research challenges Future trends also mentioned.

Language: Английский

---

An Energy-Aware Task Offloading and Load Balancing for Latency-Sensitive IoT Applications in the Fog-Cloud Continuum

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 14334 - 14349

Published: Jan. 1, 2024

With the voluminous information being produced by Internet of Things (IoT) smart gadgets, consumers with their countless service requests are also growing rapidly. As there is a huge distance between IoT devices and Cloud datacenter, some latency incurred in communication datacenter. This can be reduced introducing Fog layer therefore, it paramount to offload those tremendous data leverage overloaded storage computation Cloud-based systems Fog-assisted nodes. Moreover, these heavy computations consume significant energy from distributed servers as well datacenters. Therefore, this work addresses task migration problem Fog-Cloud system load balancing reduce rate, utilized time while increasing resource utilization for latency-sensitive systems. paper uses Fuzzy logic algorithm determining target layers offloading considering heterogeneity requirements ( i.e ., network bandwidth, size, sensitivity). A Binary Linear-Weight JAYA (BLWJAYA) scheduling has been proposed map incoming computation-rich nodes/virtual machines (VMs). Numerous experimental simulations have carried out appraise efficacy suggested method evident that outperforms other baselines an approximate improvement 26.2%, 12%, 7%, 8.63% 6% Resource utilization, Service Latency Energy consumption Load rate. The presented approach generic scalable concerning addressing unpredictability associated due criteria within layer.

Language: Английский

---

Autonomous computation offloading and auto-scaling the in the mobile fog computing: a deep reinforcement learning-based approach

Journal of Ambient Intelligence and Humanized Computing, Journal Year: 2020, Volume and Issue: 12(8), P. 8265 - 8284

Published: Sept. 25, 2020

Language: Английский

---

An energy-efficient cluster-based routing protocol using unequal clustering and improved ACO techniques for WSNs

Peer-to-Peer Networking and Applications, Journal Year: 2021, Volume and Issue: 14(3), P. 1334 - 1347

Published: March 3, 2021

Language: Английский

---

SMoSE: Artificial Intelligence-Based Smart City Framework Using Multi-Objective and IoT Approach for Consumer Electronics Application

IEEE Transactions on Consumer Electronics, Journal Year: 2024, Volume and Issue: 70(1), P. 3848 - 3855

Published: Feb. 1, 2024

This paper introduces an innovative framework at the convergence of Artificial Intelligence (AI), Multi-objective Optimization (MOO), and Internet Things (IoT), specifically tailored for applications in consumer electronics within smart cities. The seeks to revolutionize urban living by offering intelligent, responsive, interconnected solutions. In advancing evolution cities towards enhanced sharing interconnectedness, this scrutinizes city data technology grounded (IoT) cloud computing (CC) approaches. Employing machine learning methodologies, particularly Random Forest (RF) algorithm, facilitates autonomous communication between machines devoid human intervention. To solve multi-criteria problem, a hybrid algorithm is proposed, emulating behavioral traits Spotted Hyena (SHO) Emperor Penguin (EPO) algorithms. Experimental results underscore superior efficiency proposed optimization comparison with currently employed techniques.

Language: Английский

---

Partial offloading with stable equilibrium in fog-cloud environments using replicator dynamics of evolutionary game theory

Cluster Computing, Journal Year: 2022, Volume and Issue: 25(2), P. 1393 - 1420

Published: Jan. 18, 2022

Language: Английский

---

Energy-aware and carbon-efficient VM placement optimization in cloud datacenters using evolutionary computing methods

Soft Computing, Journal Year: 2022, Volume and Issue: 26(18), P. 9287 - 9322

Published: June 30, 2022

Language: Английский

---

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

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

Published: July 21, 2023

Language: Английский

---

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

Cluster Computing, Journal Year: 2024, Volume and Issue: 27(8), P. 10299 - 10324

Published: May 17, 2024

Language: Английский

---

A metaheuristic virtual machine placement framework toward power efficiency of sustainable cloud environment

Soft Computing, Journal Year: 2022, Volume and Issue: 27(7), P. 3817 - 3828

Published: Oct. 18, 2022

Language: Английский

---