Citation: Zhang, Z.; Wu, J.; Zhao, Y.;
Luo, R. Research on Distributed
Multi-Sensor Cooperative Scheduling
Model Based on Partially Observable
Markov Decision Process. Sensors
2022, 22, 3001. https://doi.org/
10.3390/s22083001
Academic Editor: Paolo Bellavista
Received: 16 March 2022
Accepted: 12 April 2022
Published: 14 April 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Research on Distributed Multi-Sensor Cooperative Scheduling
Model Based on Partially Observable Markov Decision Process
Zhen Zhang, Jianfeng Wu *, Yan Zhao and Ruining Luo
Air Defense and Missile Defense College, Air Force Engineering University, Xi’an 710051, China;
zz932785956@163.com (Z.Z.); zytyler@163.com (Y.Z.); luo_ruining@163.com (R.L.)
* Correspondence: wjf1331@163.com
Abstract:
In the context of distributed defense, multi-sensor networks are required to be able to
carry out reasonable planning and scheduling to achieve the purpose of continuous, accurate and
rapid target detection. In this paper, a multi-sensor cooperative scheduling model based on the
partially observable Markov decision process is proposed. By studying the partially observable
Markov decision process and the posterior Cramer–Rao lower bound, a multi-sensor cooperative
scheduling model and optimization objective function were established. The improvement of the
particle filter algorithm by the beetle swarm optimization algorithm was studied to improve the
tracking accuracy of the particle filter. Finally, the improved elephant herding optimization algorithm
was used as the solution algorithm of the scheduling scheme, which further improved the algorithm
performance of the solution model. The simulation results showed that the model could solve the
distributed multi-sensor cooperative scheduling problem well, had higher solution performance than
other algorithms, and met the real-time requirements.
Keywords:
distributed defense; multi-sensor scheduling; partially observable Markov decision
process; intelligent optimization algorithm
1. Introduction
In the context of distributed defense [
1
], sensors are deployed in a decentralized man-
ner. Multi-sensor collaborative scheduling is a multi-sensor resource management problem.
Traditional multi-sensor scheduling research is often aimed at static problems. However,
with the development of science and technology, the goal is gradually with the characteris-
tics of high mobility, stealth and changeable tactics, the real battlefield is often complex and
changeable, which makes the multi-sensor scheduling process more complicated.
Therefore, how to reasonably schedule multi-sensors in a dynamically changing
battlefield and continuously detect and track targets with high precision has become a
research hotspot.
In terms of the sensor scheduling model, Vikram et al. for example, used the hidden
Markov principle to build a sensor network scheduling model for the target detection
problem, and used stochastic dynamic programming to solve the optimal scheduling
strategy [
2
]. Atiyeh et al. used interactive multi-model and particle filter algorithms
for maneuvering targets to solve the sensor scheduling selection problem in the target
tracking process [
3
]. Ying He et al. solved the sensor scheduling problem in the target
tracking process by using the Monte Carlo sampling method based on the Markov decision
principle [
4
]. Wendong Xiao et al. saved energy consumption on the premise of ensuring
target tracking accuracy, and proposed a new adaptive sensor scheduling method [
5
]. In
the process of studying sensor network scheduling, Bo Hu et al. proposed an approximate
solution algorithm C-QMDP based on the POMDP model, which reduced the cumulative
loss and online computation [
6
]. Using POMDP and FISST theory, Wei Li et al. proposed a
dual-sensor control scheme to maximize the overall utility of the monitoring system [
7
].
Sensors 2022, 22, 3001. https://doi.org/10.3390/s22083001 https://www.mdpi.com/journal/sensors
