Quantum Inspired Task Optimization for IoT Edge Fog Computing Environment

Abstract

IoT-Edge-Fog Computing presents a trio-logical model for decentralized computing in a time-sensitive manner. However, to address the rising need for real-time information processing and decision modeling, task allocation among dispersed Edge Computing nodes has been a major challenge. State-of-the-art task allocation techniques such as Min–Max, Minimum Completion time, and Round Robin perform task allocation, butv several limitations persist including large energy consumption, delay, and error rate. Henceforth, the current work provides a Quantum Computing-inspired optimization technique for efficient task allocation in an Edge Computing environment for real-time IoT applications. Furthermore, the QC-Neural Network Model is employed for predicting optimal computing nodes for delivering real-time services. To acquire the performance enhancement, simulations were performed by employing 6, 10, 14, and 20 Edge nodes at different times to schedule more than 600 heterogeneous tasks. Empirical results show that an average improvement of 5.02% was registered for prediction efficiency. Similarly, the error reduction of 2.03% was acquired in comparison to state-of-the-art techniques.

Reinforcement Learning vs. Computational Intelligence: Comparing Service Management Approaches for the Cloud Continuum

“…Currently, simulation is one of the most-adopted evaluation techniques in the literature for evaluating the performance of different techniques in Edge-Fog-Cloud scenarios. The authors in [20] propose a simulation approach at different scales to evaluate their Quantum-inspired solution to optimize task allocation in an Edge-Fog scenario. Specifically, they use the iFogSim simulation toolbox [21] for their experiments and make a comparison between their concept and state-of-the-art strategies, showing improvement in prediction efficiency and error reduction.…”