Research On Service Composition Technologies In The Environment Of Internet Of Things

With the booming development of IoT technology,IoT smart devices with computing and cognitive capabilities as well as wireless communication capabilities are attracting increasing attention.In the IoT environment,the functions provided by smart devices are often distributed to the network as IoT services for people to invoke.IoT services are directly deployed on resource-constrained smart devices with characteristics such as spatial and temporal constraints and energy limitations.A single IoT service cannot meet the complex needs of users.Multiple IoT services need to be combined to provide users with the services they need.As more and more smart devices are deployed in the IoT,it becomes challenging to select IoT services with lower energy consumption and better QoS for service composition.This thesis presents an in-depth study of IoT service composition technology.A framework for IoT service composition is designed,focusing on techniques such as IoT service screening,IoT service composition optimization model construction and IoT service composition optimization model solving.First,the service composition requirement description document is parsed based on Dom4J to obtain the service function description information,user location information,user’s QoS preference and abstract service composition sequence.Then,the IoT services are filtered from three aspects,i.e.,the initial candidate service set is obtained by filtering the IoT services based on the service functional requirements using a multi-layer perceptron;the initial candidate service set is filtered based on the user’s geographical location using the GeoHash algorithm;the IoT service trustworthiness is calculated using Bayes’ theorem,and the IoT services with higher trustworthiness are selected services to generate the IoT trusted service set.Next,an IoT service composition optimization model is proposed,which takes energy consumption and service quality as the optimization objectives and considers the three types of energy consumption of IoT services,i.e.,execution energy,transmission energy and switching energy,as well as service quality.Finally,the genetic algorithm is improved and the improved genetic algorithm is used to solve the IoT service composition optimization model in order to obtain the optimal service composition solution.In order to improve the performance of the algorithm,the genetic algorithm is improved in two aspects.On the one hand,the reverse learning mechanism is introduced to improve the initial population generation strategy of the genetic algorithm,which improves the convergence speed of the algorithm;on the other hand,the crossover probability and variation probability are improved based on sigmoid and Gaussian distribution function,and adaptive crossover probability and variation probability are designed to avoid the algorithm falling into local optimum.The IoT service composition optimization model solution algorithm proposed in this thesis is experimentally compared with other related algorithms,and the results show that the algorithm in this thesis not only has obvious advantages in time efficiency,but also the IoT service composition solution obtained by using the algorithm in this thesis can balance energy consumption and service quality,so that the energy consumption and service quality required for the composition can be maintained relatively better.