Efficient task scheduling in cloud and fog computing environments remains a significant challenge due to the diverse nature and critical processing requirements of tasks originating from heterogeneous devices. Traditional scheduling methods often struggle with high latency and inadequate processing times, especially in applications demanding strict computational efficiency. To address these challenges, this paper proposes an advanced fog-cloud integration approach utilizing a deep reinforcement learning-based task scheduler, DRLMOTS (Deep Reinforcement Learning based Multi Objective Task Scheduler in Cloud Fog Environment). This novel scheduler intelligently evaluates task characteristics, such as length and processing capacity, to dynamically allocate computation to either fog nodes or cloud resources. The methodology leverages a Deep Q-Learning Network model and includes extensive simulations using both randomized workloads and real-world Google Jobs Workloads. Comparative analysis demonstrates that DRLMOTS significantly outperforms existing baseline algorithms such as CNN, LSTM, and GGCN, achieving a substantial reduction in makespan by up to 26.80%, 18.84, and 13.83% and decreasing energy consumption by up to 39.60%, 30.29%, and 27.11%. Additionally, the proposed scheduler enhances fault tolerance, showcasing improvements of up to 221.89%, 17.05%, and 11.05% over conventional methods. These results validate the efficiency and robustness of DRLMOTS in optimizing task scheduling in fog-cloud environments.

This work presents an innovative method for scheduling tasks in a fog computing environments by combining the fuzzy logic with deep reinforcement learning. In Internet of Things there has been a significant raising the amount of data produced by different devices. This has created a need for more effective methods of processing and managing this data. Conventional cloud computing often fails to fulfill the need of IoT usage in terms of high bandwidth, low makespan, and real-time processing. Fog computing presents available solution by placing the processing resources near the data source but the issue of efficient task scheduling remains a major obstacle. We proposed a technique that combines an Hybrid task scheduling technique in fog computing using fuzzy logic and deep reinforcement learning (HTSFFDRL) algorithm with a Takagi-Sugeno fuzzy inference system. By continuously interacting with the environment, this hybrid technique allows for the dynamic prioritization of tasks and the real-time change of scheduling rules. The technique seeks to maximize many crucial performance measures, such as makespan, energy consumption, cost, and fault tolerance. Simulations extensively validate the suggested strategy, demonstrating significant enhancements compared to current approaches like LSTM, DQN, and A2C. The results indicate that combining fuzzy logic with reinforcement learning may greatly improve the effectiveness and dependability of task scheduling in fog computing, opening up possibilities for more resilient IoT applications.