
Alexandria Engineering Journal, Journal Year: 2024, Volume and Issue: 115, P. 469 - 478
Published: Dec. 26, 2024
Language: Английский
Alexandria Engineering Journal, Journal Year: 2024, Volume and Issue: 115, P. 469 - 478
Published: Dec. 26, 2024
Language: Английский
Sensors, Journal Year: 2024, Volume and Issue: 24(24), P. 7918 - 7918
Published: Dec. 11, 2024
Sensor networks generate vast amounts of data in real-time, which challenges existing predictive maintenance frameworks due to high latency, energy consumption, and bandwidth requirements. This research addresses these limitations by proposing an edge-cloud hybrid framework, leveraging edge devices for immediate anomaly detection cloud servers in-depth failure prediction. A K-Nearest Neighbors (KNNs) model is deployed on detect anomalies reducing the need continuous transfer cloud. Meanwhile, a Long Short-Term Memory (LSTM) analyzes time-series analysis, enhancing scheduling operational efficiency. The framework’s dynamic workload management algorithm optimizes task distribution between resources, balancing usage, consumption. Experimental results show that approach achieves 35% reduction 28% decrease 60% usage compared cloud-only solutions. framework offers scalable, efficient solution real-time maintenance, making it highly applicable resource-constrained, data-intensive environments.
Language: Английский
Citations
7Egyptian Informatics Journal, Journal Year: 2025, Volume and Issue: 30, P. 100660 - 100660
Published: March 31, 2025
Language: Английский
Citations
0Journal of Grid Computing, Journal Year: 2025, Volume and Issue: 23(2)
Published: April 11, 2025
Language: Английский
Citations
0SN Computer Science, Journal Year: 2025, Volume and Issue: 6(5)
Published: April 17, 2025
Language: Английский
Citations
0The Journal of Supercomputing, Journal Year: 2025, Volume and Issue: 81(6)
Published: April 21, 2025
Language: Английский
Citations
0Published: Oct. 23, 2024
Cloud computing has become increasingly popular among organizations. As a result, security major concern in the adoption of cloud environments. To ensure confidentiality and prevent data leakage, organizations have adopted various measures, including sophisticated authentication methods strong cryptography algorithms. However, implementing these measures generates additional overhead that could impact resource consumption performance at user level. This paper proposes modular architecture for full-stack model to estimate implementation costs each component can be used as blueprint implement needed particular scenario resulting overhead. It contributes literature by enabling administrators users leverage based on their needs budget. Preliminary experiments show our cost achieves high level accuracy, up 95%.
Language: Английский
Citations
0Alexandria Engineering Journal, Journal Year: 2024, Volume and Issue: 115, P. 469 - 478
Published: Dec. 26, 2024
Language: Английский
Citations
0