Dynamic multi-objective evolutionary algorithm for IoT services
- PDF / 2,607,529 Bytes
- 24 Pages / 595.276 x 790.866 pts Page_size
- 93 Downloads / 179 Views
Dynamic multi-objective evolutionary algorithm for IoT services Shun-shun Fang 1,2 & Zheng-yi Chai 1,2 & Ya-lun Li 3
# Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract The primary goal of the Internet of things(IoT) is to provide people with anywhere services in real life. But intelligent IoT shouldn’t only provide services, but also consider how to allocate heterogeneous resources reasonably, which has become a very challenging problem. To obtain the best resource allocation scheme, it is crucial to minimize the service cost and service time. Since the two objectives are contradictory, we have modelled IoT services as a dynamic multi-objective optimization problem. Then a dynamic multi-objective evolutionary algorithm for dynamic IoT services(dMOEA/DI) is proposed. In dMOEA/DI, we have designed operators such as the appropriate encoding method, dynamic detection operator, filtering strategy, differential evolution, and polynomial mutation. Based on the single service strategy and collaborative service strategy, experimental research is performed on the agricultural IoT services with dynamic requests under different distributions. The simulation experimental results prove that dMOEA/DI performs better than the contrasted algorithms on the IoT service optimization problems. Keywords Agriculture . Differential evolution . Dynamic multi-objective optimization . Internet of things . Multi-objective evolutionary algorithm
1 Introduction Internet of things (IoT) has been widely used in many real scenes, such as education, agriculture, medical treatment, industry, etc., to make life more efficient and convenient. With the promotion of energy conservation and environmental protection, the optimization of IoT resource allocation has become an urgent problem to be solved in many intelligent IoT services [1, 2]. Generally speaking, IoT services can be divided into four categories [3, 4]: namely, collaborative perception services, ubiquitous services, identity-related services, and information aggregation services. The focus of this paper is the abovementioned ubiquitous service optimization problem, which is a very challenging problem because there are many dynam-
* Shun-shun Fang [email protected] 1
School of Computer Science &technology, Tiangong University, Tianjin 300387, China
2
Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems, Tianjin 300387, China
3
School of Electronic and Information Engineering, Tiangong University, Tianjin 300387, China
ic connections and a large number of uncertainties. Some researchers have reported in this aspect, such as the application of sensing services is proposed in [5, 6]. A large-scale IoT service environment consists of thousands of evenly distributed sensing entities. As soon as a service request is detected, the most appropriate centralized service will be immediately selected from many candidate services to provide the best service. The IoT shouldn’t only be able to provide services for dynamic concurrent requests, but
Data Loading...
