Design and Explanation of a Hybrid IoT and UAV Model for Intelligent Monitoring of Industrial Equipment Performance with Edge Computing Approach (Case Study: Wind Turbines)

Investment in industrial equipment is a necessity for every industrial unit. In this study, a mathematical model for intelligent monitoring of the performance of industrial equipment of wind turbines using the Internet of Things and unmanned aerial vehicles (UAVs) with an edge computing approach is investigated. In this model, the performance of the UAV for intelligent monitoring of wind turbines is investigated in three stages: detection, computational offloading, and local computations. Considering the bi-objective nature of the final model, the model was solved by a genetic algorithm with non-dominated sorting and the epsilon constraint method using random numbers. According to the findings of the study, the epsilon constraint method loses its efficiency with increasing model dimensions and is not able to find the Pareto frontier in problems with large dimensions. For this purpose, the model was solved using the second version of the genetic metaheuristic algorithm with non-dominated sorting and a new structure for representing chromosomes. This algorithm was able to solve problems in large dimensions that the epsilon constraint method was unable to solve. According to the results, the epsilon constraint method and the genetic algorithm with non-dominated sorting differ only in the time to solve, and have similar performance in other criteria; as a result, the genetic algorithm with non-dominated sorting is proposed as the superior method.