Research Article
Optimization of Multi-function Sensor Placement Satisfying Detection Coverage
@INPROCEEDINGS{10.1007/978-3-319-74176-5_11, author={Qingzhong Liang and Yuanyuan Fan}, title={Optimization of Multi-function Sensor Placement Satisfying Detection Coverage}, proceedings={Industrial Networks and Intelligent Systems. 3rd International Conference, INISCOM 2017, Ho Chi Minh City, Vietnam, September 4, 2017, Proceedings}, proceedings_a={INISCOM}, year={2018}, month={1}, keywords={WSN Placement Multi-objective Optimization}, doi={10.1007/978-3-319-74176-5_11} }
- Qingzhong Liang
Yuanyuan Fan
Year: 2018
Optimization of Multi-function Sensor Placement Satisfying Detection Coverage
INISCOM
Springer
DOI: 10.1007/978-3-319-74176-5_11
Abstract
Wireless Sensor Networks (WSNs) have become essential parts in Industrial Internet of Things (IIoT). However, owing to the type associated with data acquisition and the large scale of monitoring, sensors are often installed at a lot of locations and a wide variety of sensors make WSN topology more complex. To address these limitations, a complementary promising solution, known as software defined wireless sensor network (SDWSN), is proposed. SDWSN acquires desired information based on users’ demands from large-scale sensor networks by dynamically customizing its function. Thanks to the SDWSN, multi-type data sensing is able to enlarge the sensing scale and reduce the cost. Existing sensor placement techniques are usually focus on simple function sensor or multi-type sensor. Witness the development of SDWSN, it is ideal to explore such abilities such that the multi-type sensing functions can be conducted in a same node. Because each area covered by different multi-function sensor nodes has different detection requirements, multi-function sensor nodes placement faces many challenges. In this paper, based on multi-objective decomposition, we study the number and function redundancy of all nodes minimization problem in multi-function sensor nodes placement. Specially, we propose an improved MOEA/D-DE algorithms based on orthogonal experiment design. Simulation and evaluations validate the efficiency of our proposal.