Method for determining wireless mesh network traffic

Abstract

The invention discloses a method and a system for determining wireless mesh network flow. The method comprises the following steps: constructing a deep belief network model; collecting end-to-end flowof the to-be-detected wireless grid network, and taking the end-to-end flow as a priori measurement value of the first network flow; performing zero-mean processing on the prior measurement value, and obtaining a low-frequency component and a high-frequency component of the processed zero-mean network flow value; inputting the low-frequency component into a deep belief network model to obtain a low-frequency prediction value of the network flow; predicting a high-frequency component by adopting a space-time compressed sensing technology to obtain a high-frequency prediction value of the network flow; and performing discrete wavelet transform on the low-frequency predicted value of the network flow and the high-frequency predicted value of the network flow to obtain a predicted value of the end-to-end flow, a flow value of the network to be detected. The network flow can be accurately predicted, and the method and the system have the characteristic of low prediction difficulty.

Description

technical field [0001] The invention relates to the technical field of network flow prediction, in particular to a method for determining wireless grid network flow. Background technique [0002] In recent years, with the development of the Internet of Things, Internet of Vehicles and time-sensitive networks, wireless mesh networks (wireless Mesh networks) have been widely used and become the supporting technology for current wireless network applications. The wireless Mesh network still adopts a communication protocol family similar to that of a traditional service provider (Internet Service Provider, ISP for short) network. For application scenarios such as the Internet of Things and the Internet of Vehicles, compared with the traditional ISP network, its characteristics are not only the difference between the physical layer and the data link layer, but also the difference in the network topology. That is to say, the topology of the traditional ISP network is relatively f...

AI Technical Summary

Problems solved by technology

However, wireless mesh networks have more high-frequency components, so traditional statistical models are difficult to accurately predict the traffic of wireless mesh networks

Images