Multilevel scheduling mechanism for a stochastic fog computing environment using the HIRO model and RNN

Archana, R. A.; ., Pradeep K.

doi:10.1016/j.suscom.2023.100887

Cited by 4 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All of the works included in Table 3 highlight reliability improvements, but none of them take into account the learning model's dynamic scalability, suitability for learning challenging tasks, or significant advancements in the fog nodes. As a result, the comparison is made in terms of model dependability; however, as noted in [7], the suggested SEEDBACK-RL is assessed against existing non-scalable reinforcement learning techniques. The reliability measurement is carried out with a variety of jobs and a variety of fog nodes using the methodologies listed in Table 3 since this methodology is specifically intended to solve reliability concerns when the number of nodes and tasks is raised.…”

Section: Simulation Setupmentioning

confidence: 99%

Seedback-rl- Scalable and Efficient Deep-rl Equipped With Backup Queue for Task Assignment in Fault Tolerant Fog Computing

Archana

Kumar

2023

Preprint

View full text Add to dashboard Cite

Due to the present requirements of real-time applications, cloud computing has been superseded with fog computing, which, although addressing the issues of latency and energy consumption, cannot be totally characterised as fault-tolerant. The scalability of the nodes and tasks is one of the main causes of this problem, while there are other factors at play as well. So, it is difficult to execute big tasks in real time in fog computing. Executing all the tasks—regardless of how they scale up—and completing them all within the allotted time frame are crucial for achieving a higher throughput and a lower drop rate. SEEDBACK-RL, a unique distributed reinforcement learning technique, is suggested as a solution to the issue of obtaining reliability, scalability, and timely execution. No tasks are lost with the help of the backup plan that was discussed, regardless of how large the jobs are scaled up to be. The algorithm's capacity to identify the best nodes for task execution ensures that tasks are always carried out. The simulative evaluation demonstrates a significant improvement in reliability, drop rate, load balancing, and decreased delay computed as reliability = 9 with learning parameters compared to the state of the art, load balancing = 6.2, delay a = 5.3, and reliability = 9.

show abstract

Section: Simulation Setupmentioning

confidence: 99%

Seedback-rl- Scalable and Efficient Deep-rl Equipped With Backup Queue for Task Assignment in Fault Tolerant Fog Computing

Archana

Kumar

2023

Preprint

View full text Add to dashboard Cite

show abstract

Fog computing-enabled adaptive prognosis of cutting tool remaining life through multi-source data

Liang,

Wang,

et al. 2024

Journal of Computational Design and Engineering

View full text Add to dashboard Cite

Cutting tool remaining life during machining processes is essential for achieving sustainable production. Traditional prognosis methods are often crippled by the inability to adapt to diverse working conditions across the machining process lifecycle. This paper introduces a fog computing-enabled adaptive prognosis framework utilising multi-source data to address these challenges effectively. The key innovations include: (1) The proposed system integrates power and vibration data collected from LGMazak VTC-16A and IRON MAN QM200 machines. A standardised data fusion method combines multi-source data to enhance robustness and accuracy. (2) The transformer model is employed to improve prognosis accuracy of cutting tool remaining life, best accuracy of 98.24% and an average accuracy of 97.63% are achieved. (3) Finite Element Analysis (FEA) is incorporated to validate the model's predictions to validate reliability of deep learning model. (4) The fog computing optimisation mechanism based on the bees algorithm, which shows fitness value of 0.92 and convergence within 15 iterations. The proposed method reduces total data volume in cloud by 54.12%, prediction time by 33.64% and time complexity in the cloud layer by 4.62%. The effectiveness of fog computing in enhancing the operational efficiency and reliability of manufacturing systems is validated through advanced data integration and deep learning techniques.

show abstract

Reliability and Trust Aware Task Scheduler for Cloud-Fog Computing Using Advantage Actor Critic (A2C) Algorithm

Choppara,

Mangalampalli

2024

IEEE Access

View full text Add to dashboard Cite

Multilevel scheduling mechanism for a stochastic fog computing environment using the HIRO model and RNN

Cited by 4 publications

References 20 publications

Seedback-rl- Scalable and Efficient Deep-rl Equipped With Backup Queue for Task Assignment in Fault Tolerant Fog Computing

Seedback-rl- Scalable and Efficient Deep-rl Equipped With Backup Queue for Task Assignment in Fault Tolerant Fog Computing

Fog computing-enabled adaptive prognosis of cutting tool remaining life through multi-source data

Reliability and Trust Aware Task Scheduler for Cloud-Fog Computing Using Advantage Actor Critic (A2C) Algorithm

Contact Info

Product

Resources

About