High frequency(HF) communication is widely spread due to some merits like easy deployment and wide communication coverage. Spectrum prediction is a promising technique to facilitate the working frequency selection and...High frequency(HF) communication is widely spread due to some merits like easy deployment and wide communication coverage. Spectrum prediction is a promising technique to facilitate the working frequency selection and enhance the function of automatic link establishment. Most of the existing spectrum prediction algorithms focus on predicting spectrum values in a slot-by-slot manner and therefore are lack of timeliness. Deep learning based spectrum prediction is developed in this paper by simultaneously predicting multi-slot ahead states of multiple spectrum points within a period of time. Specifically, we first employ supervised learning and construct samples depending on longterm and short-term HF spectrum data. Then, advanced residual units are introduced to build multiple residual network modules to respectively capture characteristics in these data with diverse time scales. Further, convolution neural network fuses the outputs of residual network modules above for temporal-spectral prediction, which is combined with residual network modules to construct the deep temporal-spectral residual network. Experiments have demonstrated that the approach proposed in this paper has a significant advantage over the benchmark schemes.展开更多
The Longyangxia Gorge Key Water Control System is the first of the stairstep power sations along the Longyangxi-a-Qingtongxia river section. It has been playing an very important role in providing power, protecting fl...The Longyangxia Gorge Key Water Control System is the first of the stairstep power sations along the Longyangxi-a-Qingtongxia river section. It has been playing an very important role in providing power, protecting flood and ice run supplying and irrigation etc. in the northwestern China. Therefore, the study on trend prediction, variation on the flow into the Longyangxia Reservoir are of the great social and economic benefits. In the medium-and-long-range runoff forecast, all kinds of regression equation are often used for predicting future hydrologic regime. However, these regression models aren’t appropriate to super long -range runoff forecast because of the restricting on weather data and so on. So a new super long-range runoff forecast model don’t depend on Reai-time weather data and called “Period correcting for residual error series GM (1, 1) model” is presented based on analyzing for the relational hydrologic data and the variation on the flow into the Longyangxia Reservoir, and the forecast model was applied successfully to predict the recent and super long -term trends of the flow into the Longyangxia Reservoir. The results indicate that the annual flow into the Longyangxia Reservoir is in the ending minimum period of the runoff history. The runoff increasing is expected in for the coming years.展开更多
基金supported in part by the National Natural Science Foundation of China (Grants No. 61501510 and No. 61631020)Natural Science Foundation of Jiangsu Province (Grant No. BK20150717)+2 种基金China Postdoctoral Science Foundation Funded Project (Grant No. 2016M590398 and No.2018T110426)Jiangsu Planned Projects for Postdoctoral Research Funds (Grant No. 1501009A)Natural Science Foundation for Distinguished Young Scholars of Jiangsu Province (Grant No. BK20160034)
文摘High frequency(HF) communication is widely spread due to some merits like easy deployment and wide communication coverage. Spectrum prediction is a promising technique to facilitate the working frequency selection and enhance the function of automatic link establishment. Most of the existing spectrum prediction algorithms focus on predicting spectrum values in a slot-by-slot manner and therefore are lack of timeliness. Deep learning based spectrum prediction is developed in this paper by simultaneously predicting multi-slot ahead states of multiple spectrum points within a period of time. Specifically, we first employ supervised learning and construct samples depending on longterm and short-term HF spectrum data. Then, advanced residual units are introduced to build multiple residual network modules to respectively capture characteristics in these data with diverse time scales. Further, convolution neural network fuses the outputs of residual network modules above for temporal-spectral prediction, which is combined with residual network modules to construct the deep temporal-spectral residual network. Experiments have demonstrated that the approach proposed in this paper has a significant advantage over the benchmark schemes.
基金Ninth-Five-Year"Key Project of the State Science and Technology Commission (96-912-01-02-05 ) and National NaturalScience Fou
文摘The Longyangxia Gorge Key Water Control System is the first of the stairstep power sations along the Longyangxi-a-Qingtongxia river section. It has been playing an very important role in providing power, protecting flood and ice run supplying and irrigation etc. in the northwestern China. Therefore, the study on trend prediction, variation on the flow into the Longyangxia Reservoir are of the great social and economic benefits. In the medium-and-long-range runoff forecast, all kinds of regression equation are often used for predicting future hydrologic regime. However, these regression models aren’t appropriate to super long -range runoff forecast because of the restricting on weather data and so on. So a new super long-range runoff forecast model don’t depend on Reai-time weather data and called “Period correcting for residual error series GM (1, 1) model” is presented based on analyzing for the relational hydrologic data and the variation on the flow into the Longyangxia Reservoir, and the forecast model was applied successfully to predict the recent and super long -term trends of the flow into the Longyangxia Reservoir. The results indicate that the annual flow into the Longyangxia Reservoir is in the ending minimum period of the runoff history. The runoff increasing is expected in for the coming years.
