RWP‐NSGA II: Reinforcement Weighted Probabilistic NSGA II for Workload Allocation in Fog and Internet of Things Environment DOI Creative Commons

Hafsa Raissouli,

Samir Brahim Belhaouari,

Ahmad Alauddin Ariffin

et al.

International Journal of Distributed Sensor Networks, Journal Year: 2024, Volume and Issue: 2024(1)

Published: Jan. 1, 2024

The explosion of the IoT and immense increase in number devices around world, as well desire to meet quality service best way possible, have challenged cloud computing. Fog computing has been introduced reduce distance between process time‐sensitive tasks an efficient speedy manner. can a portion workload locally offload rest fog layer. This is then allocated nodes. distribution nodes should account for constrained energy resources device, while still prioritizing primary objective computing, which minimize delay. study investigates allocation node by optimizing delay consumption. paper proposes improved version NSGA II, namely, reinforcement weighted probabilistic uses mutation. algorithm replaces random mutation with enhance exploration solution space. method domain‐specific knowledge improve convergence quality, resulting reduced better efficiency compared traditional II other evolutionary algorithms. results demonstrate that proposed reduces nearly 2 s also achieving improvement efficiency, surpassing state art 3 units.

Language: Английский

Machine learning methods for service placement: a systematic review DOI Creative Commons
Parviz Keshavarz Haddadha, Mohammad Hossein Rezvani, Mahdi Mollamotalebi

et al.

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(3)

Published: Feb. 17, 2024

Abstract With the growth of real-time and latency-sensitive applications in Internet Everything (IoE), service placement cannot rely on cloud computing alone. In response to this need, several paradigms, such as Mobile Edge Computing (MEC), Ultra-dense (UDEC), Fog (FC), have emerged. These paradigms aim bring resources closer end user, reducing delay wasted backhaul bandwidth. One major challenges these new is limitation edge dependencies between different parts. Some solutions, microservice architecture, allow parts an application be processed simultaneously. However, due ever-increasing number devices incoming tasks, problem solved today by relying rule-based deterministic solutions. a dynamic complex environment, many factors can influence solution. Optimization Machine Learning (ML) are two well-known tools that been used most for placement. Both methods typically use cost function. usually way define difference predicted actual value, while ML aims minimize simpler terms, gap prediction reality based historical data. Instead explicit rules, uses Due NP-hard nature problem, classical optimization not sufficient. Instead, metaheuristic heuristic widely used. addition, ever-changing big data IoE environments requires specific methods. systematic review, we present taxonomy problem. Our findings show 96% distributed architecture. Also, 51% studies on-demand resource estimation 81% multi-objective. This article also outlines open questions future research trends. literature review shows one important trends reinforcement learning, with 56% share research.

Language: Английский

Citations

14
Optimization of process parameters of selective laser melted nickel-based superalloy for densification by random forest regression algorithm and response surface methodology DOI Creative Commons

Hsiang-Tse Chung,

Chin-Cheng Tsai,

Kuo‐Kuang Jen

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: 22, P. 102182 - 102182

Published: May 3, 2024

In this study, Random Forest Regression (RFR) and Response Surface Methodology (RSM) were employed to predict the optimized processing parameters achieve highest densification of a nickel-based superalloy Mar-M247LC fabricated by selective laser melting (SLM). The RFR model considered input such as power, hatch distance, scanning speed. A dataset 223 samples, was used train model. As result, exhibited accuracy 99.57%, R2 value 0.976, Mean Square Error (MSE) 0.402, Absolute Percentage (MAPE) 0.426% on testing set. addition model, study also Central Composite Design (CCD) RSM optimize parameter sets. Subsequently, conducted Box-Behnken (BBD) experimentally validate end, set optimal tested resulted sample 99.959%, outperformed that in original database before building which 99.734%. summary, models able with accuracy, coupling RSM, could be obtained, so better build achieved.

Language: Английский

Citations

7
ETFC: Energy-efficient and deadline-aware task scheduling in fog computing DOI

Amir Pakmehr,

Majid Gholipour, Esmaeil Zeinali

et al.

Sustainable Computing Informatics and Systems, Journal Year: 2024, Volume and Issue: 43, P. 100988 - 100988

Published: April 16, 2024

Language: Английский

Citations

5
Joint routing and computation offloading based deep reinforcement learning for Flying Ad hoc Networks DOI
Na Lin,

Jinjiao Huang,

Ammar Hawbani

et al.

Computer Networks, Journal Year: 2024, Volume and Issue: 249, P. 110514 - 110514

Published: May 20, 2024

Language: Английский

Citations

2
Delay reduction in MTC using SDN based offloading in Fog computing DOI Creative Commons

Zahra Arefian,

Mohammad Reza Khayyambashi, Naser Movahhedinia

et al.

PLoS ONE, Journal Year: 2023, Volume and Issue: 18(5), P. e0286483 - e0286483

Published: May 30, 2023

Fog computing (FC) brings a Cloud close to users and improves the quality of service delay services. In this article, convergence FC Software-Defined-Networking (SDN) has been proposed implement complicated mechanisms resource management. SDN suited practical standard for systems. The priority differential flow space allocation have applied arrange framework heterogeneous request in Machine-Type-Communications. delay-sensitive flows are assigned configuration queues on each Fog. Due limited resources Fog, promising solution is offloading other Fogs through decision-based controller. flow-based nodes modeled according queueing theory, where polling algorithms reduce starvation problem multi-queueing model. It observed that percentage processed flows, network consumption, average time mechanism improved by about 80%, 65%, 60%, respectively, compared traditional computing. Therefore, reductions based types task proposed.

Language: Английский

Citations

6
Collaborative Optimization Allocation of Grid-Forming and Grid-Following Reactive Power Resources Considering Auxiliary Equipment Services DOI Creative Commons
Shiwei Xue,

Siming Zeng,

Qingquan Jia

et al.

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 95840 - 95857

Published: Jan. 1, 2023

The large-scale integration of high-penetration distributed photovoltaic systems into distribution networks can result in significant grid voltage fluctuations within a short period. However, centralized regulation instructions for passive/reactive compensation, by themselves, are insufficient effectively suppressing these fluctuations. Thus, this study used the grid-forming and grid-following control characteristics modern power electronic inverters to propose an optimal allocation strategy reactive compensation equipment. This aimed address proactive support capacity equipment suppress short-time After establishing uncertain operation scenarios network, we analyzed respective multi-timescale behavioral traditional, grid-forming, devices. primary auxiliary objectives were minimize investment cost special deviation entire respectively. To achieve objectives, established collaborative model A cooperative was proposed decompose total demand curves at installation nodes different response levels then collaboratively allocate multiple comparative analysis three schemes IEEE 33-node 69-node shows that guarantees lower overall network voltages while reducing least 20% compared those other schemes.

Language: Английский

Citations

5
Ensemble classification using balanced data to predict customer churn: a case study on the telecom industry DOI

Omid Soleiman-garmabaki,

Mohammad Hossein Rezvani

Multimedia Tools and Applications, Journal Year: 2023, Volume and Issue: 83(15), P. 44799 - 44831

Published: Oct. 19, 2023

Language: Английский

Citations

3
An Online Auction Approach to UAV Scheduling and Trajectory Planning DOI
Kaiwei Mo, Xianglong Li, Chun Jason Xue

et al.

ICC 2022 - IEEE International Conference on Communications, Journal Year: 2024, Volume and Issue: unknown, P. 1011 - 1016

Published: June 9, 2024

Language: Английский

Citations

0
Sewage water management and healthcare monitoring in IoT using Optimized deep residual network DOI
Dipali Shende, Yogesh Angal

Journal of Experimental & Theoretical Artificial Intelligence, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 24

Published: Feb. 23, 2024

The Internet of Things (IoT) is termed as the interconnection different smart objects with respect to devices. In this research, two application scenarios are considered show efficiency Deep Residual Network (DRN) through multicast routing. entities involved in process IoT nodes, heads, and base stations (BS). nodes allowed capture information, collected data routed BS head node. routing made using CrowWhale optimisation algorithm that enables transfer packets from BS. sewage water management system, entering into fresh detected by DRN which trained an algorithm. healthcare heart disease prediction done detect normal abnormal cases more effectively. adopted CrowWhale-ETR+DRN offered energy, accuracy sensitivity 82.54, 0.967, 0.978 100 for environmental protection dataset. accuracy, obtained proposed model 83.232, 0.964, 0.974 dataset, respectively.

Language: Английский

Citations

0
Fault tolerant & priority basis task offloading and scheduling model for IoT logistics DOI Creative Commons
Asif Umer, Mushtaq Ali, Ali Daud

et al.

Alexandria Engineering Journal, Journal Year: 2024, Volume and Issue: 110, P. 400 - 419

Published: Oct. 14, 2024

Language: Английский

Citations

0