Aiming at the problem of network congestion caused by the large number of data\ntransmissions in wireless routing nodes of wireless sensor network (WSN), this paper puts forward\nan algorithm based on standard particle swarmââ?¬â??neural PID congestion control (PNPID). Firstly, PID\ncontrol theory was applied to the queue management of wireless sensor nodes. Then, the self-learning\nand self-organizing ability of neurons was used to achieve online adjustment of weights to adjust the\nproportion, integral and differential parameters of the PID controller. Finally, the standard particle\nswarm optimization to neural PID (NPID) algorithm of initial values of proportion, integral and\ndifferential parameters and neuron learning rates were used for online optimization. This paper\ndescribes experiments and simulations which show that the PNPID algorithm effectively stabilized\nqueue length near the expected value. At the same time, network performance, such as throughput\nand packet loss rate, was greatly improved, which alleviated network congestion and improved\nnetwork QoS.
Loading....