Flying ad-hoc network channel access control method based on traffic prediction

Abstract

The invention discloses a flying ad-hoc network channel access control method based on traffic prediction, and the method comprises the steps: predicting the arrival traffic of a next time frame by using a neural network according to a historical value through a traffic prediction theory in combination with the autocorrelation of the packet arrival traffic of an unmanned aerial vehicle over time, so as to make a channel allocation scheme; by the neural network, adjusting parameters in the negative gradient direction of the target based on a gradient descent strategy, and stopping iteration until a training error is smaller than or equal to a preset error threshold value; and on the basis of a neural network algorithm, calculating the minimum transmission time required by the unmanned aerial vehicles for transmitting a video packet, so that the bandwidth of the video packet is preferentially guaranteed when the current channel resource cannot meet the service requirements of all the unmanned aerial vehicles. According to the method, the traffic prediction method can be used, the neural network is used to predict the traffic which is about to arrive in the unmanned aerial vehicle networking communication range in the next time frame, and channel resources are allocated to the traffic.

Description

technical field [0001] The present invention relates to the technical field of unmanned aerial vehicle ad hoc network architecture, in particular to a flow prediction-based channel access control method for an unmanned aerial vehicle ad hoc network. Background technique [0002] Flying adhoc Networks (FANETs) are becoming the main communication method for multiple unmanned systems due to their robustness, flexibility, and easy deployment. Due to the limited capacity of a single UAV, it can no longer meet the complex task requirements. Multi-UAV cooperative operations have the advantages of high efficiency, scalability, and wide coverage, and can effectively meet increasingly complex mission requirements. It is the development trend of future UAV operations. [0003] However, while having many advantages over a single unmanned system, multiple unmanned systems still have their unique challenges in terms of communication. Communication is the key to ensure the normal operati...

AI Technical Summary

Problems solved by technology

When a large number of nodes compete for the channel, the resulting conflicts will be very serious, directly affecting the communication performance of the network

Second, the high-speed movement of UAVs makes the nodes in the network frequently enter and exit the network

[0005] Thesis literature CU-MAC: A MAC Protocol for Centralized UVA Networks with Directional Antennas, Aijing LI, etc. (public date: May 1, 2020) disclosed a channel access control method for UAV ad hoc networks based on traffic prediction. Although the aforementioned technical literature also involves the channel resource allocation method of the UAV ad hoc network, the two only propose to use the historical average to obtain the arrival rate of each UAV business group according to the queue length, so as to formulate a channel allocation scheme; and It does not involve traffic forecasting, does not specify the traffic forecasting method, has low computing efficiency, and does not propose a specific and effective technical solution for the problem of integrating traffic forecasting into the process of MAC protocol construction

Images