Treffer: Reinforcement learning-based framework for real-time task scheduling in IoT-Fog-Cloud environments.

Task scheduling in Fog-Cloud-IoT systems presents difficulties due to fluctuating workloads, task interdependencies, and resource limitations. Fog and cloud computing, when combined with the Internet of Things, create a robust framework for distributed processing. The dynamic characteristics of these environments, along with diverse job interdependencies, necessitate new solutions to guarantee maximum performance. This work tackles the job scheduling issue by using an innovative Deep Reinforcement Learning (DRL) model to improve the efficiency and scalability of task management in Fog-Cloud-IoT settings. We present a DRL model to efficiently manage interdependent activities in these contexts by dynamically scheduling them according to their execution duration, synchronization needs, and communication expenses. In contrast to conventional meta-heuristic methods, the suggested DRL model adaptively learns to reduce execution time, energy consumption, and task failure rates in unpredictable IoT contexts. Comprehensive simulations across several scenarios demonstrate that the suggested model decreases the average execution time by 25% and enhances the task success rate by 15% relative to the baseline algorithms. This methodology rectifies significant deficiencies in current techniques, such as restricted adaptability to fluctuating settings and the neglect of synchronization expenses. This study enhances effective and scalable job scheduling, presenting considerable implications for real-time IoT applications, including smart healthcare and autonomous systems. [ABSTRACT FROM AUTHOR]

Copyright of Cluster Computing is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)