Genetic Algorithm Using Deep Learning Model for Priority Scheduling in Cloud-Fog Environment

Cloud-fog architecture, as a hybrid distributed architecture, combines the powerful computing capabilities of cloud computing with the low-latency of fog computing, providing more efficient data processing services for Internet of Things (IoT) applications. In cloud-fog environment, efficient workflow scheduling algorithms are crucial to ensure the Quality of Service (QoS) of user applications, especially in terms of response time and energy consumption. To this end, this paper proposed an algorithm named Priority-Based Genetic Algorithm using deep learning model (PBGA). PBGA uses heuristic methods in the task sorting phase and introduces a modified genetic algorithm using a deep learning model to allocate resources to tasks. Additionally, the algorithm addresses resource overload by incorporating a task migration strategy. Experimental results indicate that compared to benchmark algorithms, PBGA achieves improvements of 3.5% to 57.4% in response time and 2.3% to 28.3% in energy consumption.