Traffic prediction method and device, network training method and device and electronic equipment

Abstract

The embodiment of the invention discloses a traffic prediction method, a network training method and device and electronic equipment. The network training method comprises the following steps: obtaining a data set containing a plurality of pieces of first data, and obtaining first prediction data of a prediction time point based on the data set and a first network; the multiple pieces of first data are historical flow data before the prediction time point; obtaining a plurality of pieces of second data, and obtaining adjustment data based on the plurality of pieces of second data and a second network; adjusting the first prediction data according to the adjustment data and a dynamic adjustment parameter to obtain second prediction data, and generating prediction sequence data based on the obtained multiple pieces of second prediction data; and after the prediction sequence data is processed by a full-connection network, determining loss with target sequence data, and training the first network, the second network and the full-connection network according to the loss.

Description

technical field [0001] The invention relates to the field of traffic prediction, in particular to a traffic prediction method, a network training method, a device and an electronic device. Background technique [0002] In recent years, users' Internet traffic usage has increased year by year, especially this year's gradual application of 5G networks around the world has put forward higher requirements for operators. In order to improve service efficiency, operators must deal with the problem of network resource allocation. When some node resources are insufficiently allocated, users will be oversaturated, which will increase node service load and reduce user experience. On the contrary, when node resources are allocated too much , it will cause waste of resources, and may even cause problems such as excessive service pressure on surrounding nodes. In recent years, some common deep learning methods have also been applied in traffic prediction applications. [0003] The curr...

AI Technical Summary

Problems solved by technology

[0003] The current traffic forecasting technology does not take into account the impact of periodic data on forecasting, or the considered periodic data is not strictly periodic data for traffic forecasting, and traffic may have certain dynamics at the same period of time fluctuations, leading to certain deviations in the forecast results

Images