Traffic sensing method based on large and small time scales under space-ground convergence network

Abstract

The invention discloses a traffic sensing method based on large and small time scales under a space-ground fusion network, which aims at a space-ground fusion architecture provided by a space-ground fusion network environment and can sense and collect network resource nodes in a region and process traffic information. The method can adapt to the characteristics of a heaven and earth fusion network, predicts the traffic in the region under a large time scale, and can judge whether the resources in the region can meet the resource requirements corresponding to the predicted traffic or not. Through delay-sensitive cross-node traffic transfer on a small time scale, a resource node overload condition caused by traffic burstiness on the small time scale can be reduced, and the resource utilization rate of idle nodes can be improved by performing queue caching and traffic transfer on delay-tolerant traffic.

Description

technical field [0001] The invention belongs to the field of sky-earth fusion information network, and particularly relates to a flow perception method based on large and small time scales under the sky-earth fusion network. Background technique [0002] In recent years, as an emerging network architecture that integrates satellite and terrestrial communication systems, the Sky-Earth Converged Network has received extensive attention from academia and industry. an important part of survivability. Thanks to its advantages of wide coverage, high throughput, and strong robustness, the integrated space-earth network can be applied to many practical fields such as earth observation and mapping, intelligent transportation systems, military missions, homeland security, and disaster rescue. Satellites with high throughput can provide seamless wireless access services globally, and densely deployed terrestrial network infrastructure supports high-speed data access. The integration ...

AI Technical Summary

Problems solved by technology

The integration of space-based and ground-based networks will bring about an increase in the type and quantity of services. In the past, traffic perception was performed on a large time scale, such as tens of minutes, to predict the network traffic in the region on a large time scale. Perception, resource scheduling based on prediction results to meet the resource requirements corresponding to the traffic, however, this kind of traffic prediction perception only solves the large-time-scale traffic changes, and cannot cope with the fine-grained granularity of small-time scales in a large number of business scenarios in the space-ground integrated network Traffic changes, such as seconds or hundreds of milliseconds, the traffic on a small time scale is bursty, which will cause overloading of some nodes in the area, thus affecting the quality of service in the entire area

[0004] At present, the research on traffic perception of space-ground integrated network is basically carried out on a large time scale, and the traffic changes on a small time scale are rarely considered. Previous traffic prediction algorithms only target a single network, either a satellite network or a ground network. Network, there are few studies on traffic forecasting of space-ground integrated network

There are two types of general traffic forecasting, namely linear and nonlinear. Among them, linear ones need to manually set parameters based on experience to fit the data, and the application range is small. The actual network traffic is nonlinear, periodic, bursty, and self-similar. Therefore, nonlinear traffic forecasting has a wide range of applications. However, because traditional traffic forecasting is carried out in a single network, without considering the characteristics of space-based networks and ground-based networks, it is not suitable for traffic in space-ground integrated networks. predict

[0005] Traditional traffic sensing processing is only for large time scales, and rarely considers small time scale traffic changes, and it is generally difficult to predict such traffic changes, so traffic changes on small time scales are often ignored. And this kind of sudden change of traffic will lead to different results of nodes at different times. When the sudden change of traffic is at the peak, it will be overloaded and cause congestion, which will cause a large service delay of the node, reduce the service quality of the node, or the sudden change of traffic is at the bottom When the node is idle, it will cause a waste of node resources

Images