scispace - formally typeset
Patent

Co-channel interference prediction method for satellite-to-ground downlink under low earth orbit satellite constellation

Song Chunyi, +3 more
Reads0
Chats0
TLDR
In this paper, a co-channel interference prediction method for a satellite-to-ground downlink under a low earth orbit satellite constellation is proposed, which is based on a dropout wavelet neural network.
Abstract: 
Disclosed is a co-channel interference prediction method for a satellite-to-ground downlink under a low earth orbit satellite constellation. The method comprises: acquiring a co-channel interference value within a first pre-determined duration and a co-channel interference value within a second pre-determined duration; constructing, on the basis of a dropout wavelet neural network, a co-channel interference model according to the co-channel interference value within the first pre-determined duration; updating a parameter of the co-channel interference model; inputting the co-channel interference value within the second pre-determined duration into the updated co-channel interference model, and obtaining an accuracy level; determining whether the accuracy level is greater than an accuracy threshold; if so, re-constructing the co-channel interference model; if the accuracy level is less than or equal to the accuracy threshold, outputting the updated co-channel interference model; and predicting a co-channel interference value of each link at a next time point according to the updated co-channel interference model. The present invention realizes a prediction of a co-channel interference value on the basis of a dropout wavelet neural network, thereby lowering algorithm complexity while improving the prediction speed.

read more

References
More filters
Patent

Active interference suppression in a satellite communication system

Antony Duncan Craig, +2 more
TL;DR: In this paper, the authors proposed a method for active interference suppression in a satellite communication system, particularly but not exclusively to an apparatus and method for using active interference suppressing in order to suppress co-channel interference between user signals in the communication system.
Patent

Deep Q neural network anti-interference model and intelligent anti-interference algorithm

Wang Jinlong, +6 more
TL;DR: In this article, a deep Q neural network anti-interference model and an intelligent antiinterference algorithm is presented. But the model is not complete, the physical meaning is clear, the design algorithmis reasonable and effective, and the anti-Interference scene based on the deep reinforcement learning algorithm can be excellently described.
Patent

Method for evading co-channel interference through deflection antenna pointing and satellite communication system

Jin Jin, +4 more
TL;DR: In this article, the authors proposed a method for evading co-channel interference through deflection antenna pointing and a satellite communication system, which consists of the following steps: arranging more than one space-borne antenna on an NGEO communication satellite, determining a constellation configuration of the NGEO satellite communications system, and selecting variables to describe the normal orientation of the spaceborne antenna.
Patent

Resource reservation intelligent call admission control method and apparatus

Gang Zhu, +1 more
TL;DR: In this paper, admitting decision is implemented by using current number of system users to replace measurement outage probability in ICAC scheme, which includes three modules: fuzzy equivalent interference estimator, neural network interference predictor, and fuzzy call admission processor.
Patent

Satellite-ground downlink same-frequency interference estimation method under low-orbit mobile satellite constellation

Song Chunyi, +3 more
TL;DR: In this paper, a satellite-ground downlink same-frequency interference estimation method under a low-orbit satellite constellation is proposed, which comprises the following steps: firstly, acquiring a same frequency interference numerical value; selecting a prediction algorithm for processing a time sequence; establishing a model for predicting the level of the current moment by utilizing the samefrequency interference value CCI obtained in a past period of time; adjusting parameters of the prediction algorithm; enabling the output of the model to fit the rule that the CCI changes along with time; and calculating the precision of prediction algorithm by