Research Article
A Multi-Objective Service Selection Method Based on Ant Colony Optimization for QoE Restrictions in the Internet of Things
@INPROCEEDINGS{10.1007/978-3-030-21373-2_26, author={Chuxuan Zhang and Bing Jia and Lifei Hao}, title={A Multi-Objective Service Selection Method Based on Ant Colony Optimization for QoE Restrictions in the Internet of Things}, proceedings={Security and Privacy in New Computing Environments. Second EAI International Conference, SPNCE 2019, Tianjin, China, April 13--14, 2019, Proceedings}, proceedings_a={SPNCE}, year={2019}, month={6}, keywords={Internet of Things Ant Colony Optimization Service selection QoE}, doi={10.1007/978-3-030-21373-2_26} }- Chuxuan Zhang
Bing Jia
Lifei Hao
Year: 2019
A Multi-Objective Service Selection Method Based on Ant Colony Optimization for QoE Restrictions in the Internet of Things
SPNCE
Springer
DOI: 10.1007/978-3-030-21373-2_26
Abstract
With the development of Wireless Sensor Network (WSN), the number of Internet of Things (IoT) services has increased dramatically. In order to use IoT services conveniently, it has become a key issue to reasonably aggregate information, content and applications, and filter services according to users’ needs. Most of the existing service selection algorithms adopt heuristic search algorithm or Genetic Algorithm (GA). The heuristic algorithm is not stable, and GA cannot meet the needs of service selection because of the one-dimensional chromosome coding. For overcoming the disadvantages of these methods, this paper proposes a multi-objective service selection algorithm based on Ant Colony Optimization (ACO) for Quality of Experience(QoE) restrictions. The proposed method can get a feasible solution quickly and efficiently by utilizing the fast convergence speed of ACO. Specifically, QoE model was established firstly, and relevant constraints and quantitative methods are given. Secondly, a service selection model based on ACO was constructed to select specific services based on the above model. Finally, the proposed method is verified through simulations. Results show that, compared with GA-based method, the proposed algorithm can improve the recall rate and precision rate, and has a higher algorithm efficiency in solving the service selection problems.
