Time-sensitive network data traffic prediction method and system, and storage medium

Abstract

The invention relates to a time-sensitive network data traffic prediction method, which can be used for carrying out accurate traffic prediction on a constant bit rate service and a variable bit rate service with a fixed period so as to improve the network bandwidth utilization rate. The method comprises the following steps of: based on a flow data sequence of a basic transmission window before the current moment, acquiring a time sequence characteristic of the flow data sequence; using the time sequence characteristics as parameters, and calculating a flow data prediction value at the current moment by using a prediction model; the prediction model obtains a corresponding relation between the time sequence characteristics and the traffic data prediction value based on a historical traffic data sequence; the time sequence characteristics of the flow data sequence comprise a forward time sequence characteristic and a reverse time sequence characteristic. In order to improve the prediction accuracy, correlation features between the forward time sequence features, between the forward time sequence features and the reverse time sequence features and between the reverse time sequence features are further obtained based on the forward time sequence features and the reverse time sequence features.

Description

technical field [0001] The present disclosure relates to the field of Internet technologies, in particular to a time-sensitive network data flow prediction method, system and storage medium. Background technique [0002] Time Sensitive Networking (TSN) is an extended standard Ethernet technology that is backward compatible with standard Ethernet, allowing us to obtain low jitter, low latency, and robust communication channels through standard Ethernet, as an IEEE Standard, Time Sensitive Networking (TSN) will be an important part of real-time Ethernet communications in the future. The gating mechanism of Time Sensitive Network (TSN) such as figure 1 , the gate control contains multiple gate structures and a gate control list, figure 1 In the T1-T4 time slot, 0 and 1 correspond to the opening and closing of the door, and T1: 01111111 indicates that the leftmost door in the T1 time slot is in the open state, and the other doors are in the closed state. The number of gates i...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem that the existing variable bit rate service prediction is not accurate enough, the purpose of the present invention is to propose a time-sensitive network data traffic prediction method, which can not only accurately predict the traffic of constant bit rate services with a fixed period, but also Accurate traffic prediction for variable bit rate services, thereby improving network bandwidth utilization

Images