Optimizing energy task offloading technique using IoMT cloud in healthcare applications

The Internet of Medical Things (IoMT) has revolutionized patient data and healthcare surveillance, enabling continuous monitoring without costly human resources and low error rates. IoMT uses medical devices as nodes to monitor and collect patient data efficiently and cost-effectively. IoMT issues emergency alarms and monitors people in hospitals and at home to help physicians track their health. It analyzes EEGs, ECGs, blood sugar, blood pressure, and other health markers. Real-time analysis is essential in crucial situations, these latency-sensitive scenarios are suitable for cloud-based IoT platforms. This research proposes an Efficient Augmented Moth-Flame Optimization (EA-MFO) technique for task offloading. The method focuses on prioritizing critical tasks to ensure deadlines are met while optimizing energy consumption for other tasks. EA-MFO enhances the moth-flame optimization process by incorporating chaos-based initialization, adaptive position updates with weighted adjustments, and strategies to improve population diversity. The chaos-based logistic map is used to increase diversity during initialization. Simulation results reveal that EA-MFO outperforms E-PSO, GWO, MQGA, and MATO in terms of energy consumption, makespan, and total execution time (TEC). Specifically, EA-MFO achieves a total execution time of 0.63 s, a makespan of 52.13 s, and energy consumption of 592.78 kWh.