Harnessing Artificial Intelligence and Machine Learning to Transform Cloud Computing with Enhanced Efficiency and Personalization DOI Creative Commons
Veeramalai Sankaradass,

Ramsriprasaath Devasenan

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 20, 2024

Abstract This work seeks to evaluate how ML and GAI could be integrated into the cloud computing model with an effort of optimizing use resources, minimizing energy consumption providing value added services. Similar other systems its nature, which are large-scale distributed systems, have several topics concern including dynamic resource management, security issues, issues regarding user interface. To address these discrepancies, this proposes a single D-PAL framework that uses predictive application for synthetic data generation. In environments framework, it employs workload prediction scheduling estimation through ML, Reinforcement Learning, augmentation GAN. From experimental assessment one is able observe implicit improvements in performance consumption, customised regard, paper advances theoretical empirical understanding on personnel characteristics AI deploy new methods improve maintain usability. Future will more focused expanding proposed models scale integrating techniques increase control.

Language: Английский

Dynamic service provisioning in heterogeneous fog computing architecture using deep reinforcement learning DOI
Yaghoub Alizadeh Govarchinghaleh, Masoud Sabaei

The Journal of Supercomputing, Journal Year: 2024, Volume and Issue: 80(16), P. 23867 - 23910

Published: July 29, 2024

Language: Английский

Citations

1
Short-term solar power forecasting- An approach using JAYA based recurrent network model DOI
Venkateswarlu Gundu, Sishaj P. Simon, Krishna Kumba

et al.

Multimedia Tools and Applications, Journal Year: 2023, Volume and Issue: 83(11), P. 32411 - 32422

Published: Sept. 21, 2023

Language: Английский

Citations

3
A Load-Balanced Task Scheduling in Fog-Cloud Architecture: A Machine Learning Approach DOI
Rashmi Keshri, Deo Prakash Vidyarthi

Communications in computer and information science, Journal Year: 2024, Volume and Issue: unknown, P. 129 - 140

Published: Jan. 1, 2024

Language: Английский

Citations

0
Multi-objective application placement in fog computing using graph neural network-based reinforcement learning DOI Creative Commons
Isaac Lera, Carlos Guerrero

The Journal of Supercomputing, Journal Year: 2024, Volume and Issue: 80(19), P. 27073 - 27094

Published: Aug. 29, 2024

Abstract We propose a framework designed to tackle multi-objective optimization challenge related the placement of applications in fog computing, employing deep reinforcement learning (DRL) approach. Unlike other techniques, such as integer linear programming or genetic algorithms, DRL models are applied real time solve similar problem situations after training. Our model comprises process featuring graph neural network and two actor-critics, providing holistic perspective on priorities concerning interconnected services that constitute an application. The incorporates relationships between crucial factor decisions: Services with higher dependencies take precedence location selection. experimental investigation involves illustrative cases where we compare our results baseline strategies algorithms. observed comparable Pareto set negligible execution times, measured order milliseconds, contrast hours required by alternative approaches.

Language: Английский

Citations

0
Deployment options of AI components for network resource management in 5G‐enabled agile industrial production cell DOI Creative Commons
Géza Szabó,

József Pető,

Attila Vidács

et al.

International Journal of Communication Systems, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 8, 2024

Summary On‐demand manufacturing in Industry 4.0 requires flexibility of the networks which can be provided with fifth generation (5G) mobile communications wireless connectivity. A key component efficient utilization radio resources a scenario is network resource management (NRM). We show how NRM automated artificial intelligence (AI). introduce several futuristic industrial use cases that require AI various parts process. analyze components' benefits and disadvantages deployment scenarios. The findings used by business stakeholders interested deploying 5G cellular to choose best implementation strategy for particular case. there are many viable options process automation, but cost has considered all cases. Also, we point out an essential component, standardized information flow on status productivity performance indicators (KPIs), needed successful application AI.

Language: Английский

Citations

0
A Hybrid Seagull Optimization Algorithm for Effective Task Offloading in Edge Computing Systems DOI

Avishek Sinha,

Samayveer Singh, Harsh Kumar Verma

et al.

National Academy Science Letters, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 25, 2024

Language: Английский

Citations

0
Harnessing Artificial Intelligence and Machine Learning to Transform Cloud Computing with Enhanced Efficiency and Personalization DOI Creative Commons
Veeramalai Sankaradass,

Ramsriprasaath Devasenan

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 20, 2024

Abstract This work seeks to evaluate how ML and GAI could be integrated into the cloud computing model with an effort of optimizing use resources, minimizing energy consumption providing value added services. Similar other systems its nature, which are large-scale distributed systems, have several topics concern including dynamic resource management, security issues, issues regarding user interface. To address these discrepancies, this proposes a single D-PAL framework that uses predictive application for synthetic data generation. In environments framework, it employs workload prediction scheduling estimation through ML, Reinforcement Learning, augmentation GAN. From experimental assessment one is able observe implicit improvements in performance consumption, customised regard, paper advances theoretical empirical understanding on personnel characteristics AI deploy new methods improve maintain usability. Future will more focused expanding proposed models scale integrating techniques increase control.

Language: Английский

Citations

0