基于LSTM的短波频率参数预测

A Prediction of Frequency Parameters Based on LSTM for High Frequency Communication

针对现有短波通信频率参数预测方法操作繁琐、预测精度不足的缺点,首次提出一种基于长短期记忆型循环神经网络(LSTM RNN)的预测方法。通过对电离层参数fOF2数据的分析,利用LSTM在处理时序相关数据时可以长期记忆网络历史数据的优势,对fOF2值进行预测。对比反向传播神经网络(BPNN),LSTM将误差降低了7%,并将均方误差控制在2%以下。研究结果表明:基于LSTM搭建的提前预报5天的fOF2值的模型是可行的且比BP神经网络更适合预测电离层的fOF2值。

Aimed at the problems that in the existing high frequency communication, the frequency parameter prediction methods are tedious formalities in operation and shortage in precision, this paper presents a prediction model of frequency parameters of short-wave communication based on long short-term memory recurrent neural networks. This neural network can break through the limitations of traditional neural networks and establish long-term correlations on data sequences. The experimental results show that the mean square error (MSE) can be control below 2% and the model reduced the error by 7 %. And this method is effective and superior to the traditional prediction method.