Pilot frequency signal strength prediction method based on AI model

Abstract

The invention discloses a pilot frequency signal strength prediction method based on an AI model. The method comprises the following steps: 1, data acquisition; 2, sample preprocessing; 3, predictionmodel acquisition; 4, model detection; 5, model-based prediction and use; and 6, model updating and maintenance. The method has the beneficial effects that the pilot frequency signal strength is accurately predicted; and in a scene that pilot frequency switching is performed on the UE to select a pilot frequency target cell or a plurality of auxiliary carriers are configured during carrier aggregation, a pilot frequency measurement process is avoided. The signal strength information of the pilot frequency neighbor cell is obtained without depending on a measurement time slot, and the problemsof inaccurate pilot frequency signal strength prediction caused by too large grid granularity and inaccurate pilot frequency signal strength prediction caused by failure of a prediction model due to the fact that grids are not updated periodically in the prior art are solved at the same time.

Description

technical field [0001] The invention belongs to the technical field of mobile communication, and in particular relates to a method for predicting different frequency signal strengths based on an AI (Artificial Intelligence, artificial intelligence) model. Background technique [0002] At present, with the gradual popularization of smart phones, the demand for mobile communication is rapidly developing. As a mainstream communication technology, Long Term Evolution (LTE) wireless network has more and more traffic. Carriers can no longer meet the needs of society. Therefore, operators usually deploy more wireless frequency bands to provide greater communication capacity, such as using multiple carriers to cover the same area to increase the communication capacity of the system. Due to the frequency difference and deployment difference of different frequency bands, the signal strength of different frequency bands at the same location may vary greatly. Therefore, the user equipme...

AI Technical Summary

Problems solved by technology

The disadvantage of the scheme is that when the area where users are concentrated is limited by the fixed step size (such as 5dB) and the number of adjacent cells, the grid division granularity is large, and the characteristics of different grids are very different, which leads to low prediction accuracy. Problem; if the fixed step size is too small, it will cause too many grids, resulting in too large storage space and too long search time; and the area with few users will not have reasonable statistical characteristics due to the small number of samples, which will lead to The raster is not available, or the prediction accuracy is not high after use

Images