Congestion control method of wireless sensor network based on fuzzy control single neuron pid controller

Abstract

The invention discloses a congestion control method for a wireless sensor network based on a fuzzy control single neuron PID controller. The method belongs to an active queue control method and can overcome the problem of network collapse caused by the full queue existing in the existing method. The method includes the following steps: The steps are as follows: 1) definition of relevant parameters; 2) realization of PID method; 3) realization of NPID method; 4) improvement of NPID method by fuzzy control algorithm to obtain FNPID method; 5) calculation of discard probability p(k), Actively drop packets with drop probability p(k) before the queue is full. The invention uses the active queue management method FNPID to ensure that the network will not be full of queues, maintains a good control effect, reduces delay and packet loss rate, improves throughput, and maintains high network performance.

Description

technical field [0001] The invention belongs to the field of wireless sensor network congestion control, in particular to a wireless sensor network congestion control method based on a fuzzy control single neuron PID controller, and belongs to the category of node active queue management. Background technique [0002] In today's information age, with the development of 5G technology and the Internet of Everything, the application of Wireless Sensor Networks (WSN) is becoming more and more extensive, which can be seen in smart home, national defense and military, biomedicine, smart agriculture and other fields The figure of wireless sensor network. The wireless sensor network has the characteristics of distribution and is a multi-hop self-organizing network. A large number of sensor nodes in the monitoring area can cooperatively send the collected information to the sink node, and then transmit it to the users of the network. With the collection, processing and transmission...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to overcome the problem that the PID algorithm parameters in the prior art are fixed, and the parameters cannot be automatically adjusted to adapt to the time-varying load of the wireless sensor network, and a fuzzy control based single neuron PID controller is proposed. The active queue management method of wireless sensor network nodes, through the addition of single neuron technology, enables the parameters of the PID algorithm to have the ability of self-learning, and introduces the fuzzy control algorithm to adjust the fixed gain of the single neuron in real time, thereby accelerating the applied The rapid convergence of the control achieves a good control effect, avoids congestion, improves throughput, reduces delay, and reduces packet loss rate

Images