COGNITIVEMONKEY: a fog-enabled cognitive framework for the monkey climbing algorithm using deep learning

Fog computing is emerging as a transformative paradigm capable of efficiently processing the massive volumes of data generated by Internet of Things (IoT) applications. By extending core principles of cloud computing to the network edge, it effectively addresses the critical latency challenges associated with scheduling and resource allocation tasks in cloud-based IoT environments. The paper presents the DL-EMC algorithm, a deep learning–enhanced metaheuristic that optimizes fog computing by intelligently mapping IoT tasks to cloud resources, reducing delays and improving efficient cloud service delivery. In contrast, the proposed DL-EMC algorithm integrates a deep learning model that learns from previous iterations, enabling more informed and adaptive decision-making. By leveraging deep learning models trained on historical data related to IoT workloads and fog computing performance, the algorithm can forecast future resource demands and potential bottlenecks. This predictive capability facilitates proactive optimization of application-resource mapping, thereby significantly reducing latency. Simulation results demonstrate that the DL-EMC algorithm dynamically and effectively manages cloud resources for IoT applications. It surpasses leading state-of-the-art methods by reducing delays and minimizing resource consumption, highlighting its strong potential to enhance IoT service delivery within fog computing environments.