Cross-layer congestion control of wireless sensor networks based on fuzzy sliding mode control

Wireless sensor networks (WSNs) act as a building block of Internet of Things and have been used in various applications to sense environment and transmit data to the Internet. However, WSNs are very vulnerable to congestion problem, resulting in higher packet loss ratio, longer delay and lower thro...

Full description

Saved in:
Bibliographic Details
Published in:Neural computing & applications 2020-09, Vol.32 (17), p.13505-13520
Main Authors: Qu, Shaocheng, Zhao, Liang, Xiong, Zhili
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
Computer simulation
Congestion
Control algorithms
Control systems design
Control theory
Data Mining and Knowledge Discovery
Fuzzy control
Image Processing and Computer Vision
Internet of Things
Original Article
Probability and Statistics in Computer Science
Queues
Queuing theory
Signal to noise ratio
Sliding mode control
Wireless networks
Wireless sensor networks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Wireless sensor networks (WSNs) act as a building block of Internet of Things and have been used in various applications to sense environment and transmit data to the Internet. However, WSNs are very vulnerable to congestion problem, resulting in higher packet loss ratio, longer delay and lower throughput. To address this issue, this paper presents a fuzzy sliding mode congestion control algorithm (FSMC) for WSNs. Firstly, by applying the signal-to-noise ratio of wireless channel to TCP model, a new cross-layer congestion control model between transmission layer and MAC layer is proposed. Then, by combining fuzzy control with sliding mode control (SMC), a fuzzy sliding mode controller (FSMC) is designed, which adaptively regulates the queue length of buffer in congested nodes and significantly reduces the impact of external uncertain disturbance. Finally, numerous simulations are implemented in MATLAB/Simulink and NS-2.35 by comparing with traditional control strategies such as fuzzy, PID and SMC, which show that the proposed FSMC effectively adapts to the change of queue length and has good performance, such as rapid convergence, lower average delay, less packet loss ratio and higher throughput.
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-020-04758-1