Predictive EQCi-Optimized Load Scheduling for Heterogeneous IoT-Data in Fog Computing Environments

This paper presents a pioneering predictive EQCi-optimized load scheduling technique tailored to the complexities of heterogeneous IoT data within fog computing environments. The proposed method strategically assigns tasks to fog nodes by considering Load Scheduling Policies (LSPs) and the computing capabilities of fog nodes. Incorporating an EQCi-technique, the model enhances load allocation precision for various LSPs, facilitated by representing LSPs as quantum bits (qubits). This representation enables efficient assessment of probabilistic Execution Index values and Node Availability Index (NAI) for fog nodes, facilitating real-time task allocation. Furthermore, the introduction of EQCi-NN introduces a predictive model that anticipates the optimal fog node for specific tasks with given LSPs. This predictive capability minimizes execution delays and enhances throughput within the fog computing environment. The proposed technique’s performance is rigorously validated through simulations using the iFogSim toolkit, and its efficacy is demonstrated against existing load scheduling methods. Comparative analysis with other predictive techniques highlights the precision and efficiency of the proposed prediction model. The research underscores the presented system’s effectiveness in predicting optimal computational nodes within fog computing platforms, particularly in scenarios necessitating real-time analytical outcomes. By synergizing quantum-inspired representation and predictive modeling, this study advances load scheduling methodologies in fog computing, optimizing resource utilization and bolstering the responsiveness of IoT-driven applications.