Evolutionary Computing Approach to Optimize Superframe Scheduling on Industrial Wireless Sensor Networks (1812.01201v1)

Abstract: There has been a paradigm shift in the industrial wireless sensor domain caused by the Internet of Things (IoT). IoT is a thriving technology leading the way in short range and fixed wireless sensing. One of the issues in Industrial Wireless Sensor Network-IWSN is finding the optimal solution for minimizing the defect time in superframe scheduling. This paper proposes a method using the evolutionary algorithms approach namely particle swarm optimization (PSO), Orthogonal Learning PSO, genetic algorithms (GA) and modified GA for optimizing the scheduling of superframe. We have also evaluated a contemporary method, deadline monotonic scheduling on the ISA 100.11a. By using this standard as a case study, the presented simulations are object-oriented based, with numerous variations in the number of timeslots and wireless sensor nodes. The simulation results show that the use of GA and modified GA can provide better performance for idle and missed deadlines. A comprehensive and detailed performance evaluation is given in the paper.