scholarly journals A General Framework of LSTM and Transfer Learning Based CFDAMA Strategy in Broadband Satellite System

2021 ◽  
Author(s):  
Qiang He ◽  
Zheng Xiang ◽  
Peng Ren
Keyword(s):  
Transfer Learning ◽  
Delay Time ◽  
Multiple Access ◽  
Short Term Memory ◽  
Prediction Method ◽  
Satellite System ◽  
Satellite Networks ◽  
Data Traffic ◽  
Broadband Service ◽  
Satellite Systems

With the development of the economy and technology, people’s requirement for communication is also increasing. Satellite networks have been paid more and more attention because of its broadband service capability and wide coverage. In this paper, we investigate the framework of a long-short term memory (LSTM) and transfer learning-based Combined Free/Demand Assignment Multiple Access (CFDAMA) scheme (CFDAMA-LSTMTL), which is a new multiple access scheme in the broadband satellite system. Generally, there is a delay time T between sending a request from the user to the satellite and receiving a reply from the satellite. So far, the traditional multiple access schemes has not processed the data traffic generated in this period of time. So, in order to transmit the data traffic in time, we propose a new prediction method, which combines LSTM with transfer learning. We introduce the prediction method into the CFDAMA scheme so that it can reduce data accumulation by the way of sending the sum slots requested by the user and the predicted request slots generated in the delay time T. A comparison with CFDAMA-PA and CFDAMA-PB is provided through simulation results, which gives the effect of the CFDAMA-LSTMTL in a broadband satellite systems.

scholarly journals A CLSTM and transfer learning based CFDAMA strategy in satellite communication networks

PLoS ONE ◽  
2021 ◽  
Vol 16 (3) ◽  
pp. e0248271
Author(s):  
Qiang He ◽  
Zheng Xiang ◽  
Peng Ren
Keyword(s):  
Transfer Learning ◽  
Communication Networks ◽  
Delay Time ◽  
Multiple Access ◽  
Satellite Communication ◽  
Short Term Memory ◽  
Prediction Method ◽  
Broadband Service ◽  
Multiple Access Schemes ◽  
Service Capability

With the development of the economy and technology, people’s requirement for communication is also increasing. Satellite communication networks have been paid more and more attention because of their broadband service capability and wide coverage. In this paper, we investigate the scheme of convolutional long short term memory (CLSTM) network and transfer learning (TL) based combined free/demand assignment multiple access (CFDAMA) scheme (CFDAMA-CLSTMTL), which is a new multiple access scheme in the satellite communication networks. Generally, there is a delay time T between sending a request from the user to the satellite and receiving a reply from the satellite. So far, the traditional multiple access schemes have not processed the data generated in this period. So, in order to transmit the data in time, we propose a new prediction method CLSTMTL, which can be used to predict the data generated in this period. We introduce the prediction method into the CFDAMA scheme so that it can reduce data accumulation by the way of sending the slots request which is the sum of slots requested by the user and the predicted slots generated in the delay time. A comparison with CFDAMA-PA and CFDAMA-PB is provided through simulation results, which gives the effect of the CFDAMA-CLSTMTL in a satellite communication network.

scholarly journals Leveraging Label Information in a Knowledge-Driven Approach for Rolling-Element Bearings Remaining Useful Life Prediction

Energies ◽  
2021 ◽  
Vol 14 (8) ◽  
pp. 2163
Author(s):  
Tarek Berghout ◽  
Mohamed Benbouzid ◽  
Leïla-Hayet Mouss
Keyword(s):  
Transfer Learning ◽  
Short Term Memory ◽  
Remaining Useful Life ◽  
Accelerated Life Tests ◽  
Learning Path ◽  
Accelerated Life ◽  
Unseen Data ◽  
Label Information ◽  
Life Tests ◽  
Ill Posed

Since bearing deterioration patterns are difficult to collect from real, long lifetime scenarios, data-driven research has been directed towards recovering them by imposing accelerated life tests. Consequently, insufficiently recovered features due to rapid damage propagation seem more likely to lead to poorly generalized learning machines. Knowledge-driven learning comes as a solution by providing prior assumptions from transfer learning. Likewise, the absence of true labels was able to create inconsistency related problems between samples, and teacher-given label behaviors led to more ill-posed predictors. Therefore, in an attempt to overcome the incomplete, unlabeled data drawbacks, a new autoencoder has been designed as an additional source that could correlate inputs and labels by exploiting label information in a completely unsupervised learning scheme. Additionally, its stacked denoising version seems to more robustly be able to recover them for new unseen data. Due to the non-stationary and sequentially driven nature of samples, recovered representations have been fed into a transfer learning, convolutional, long–short-term memory neural network for further meaningful learning representations. The assessment procedures were benchmarked against recent methods under different training datasets. The obtained results led to more efficiency confirming the strength of the new learning path.

Performance Enhancement of Encoding–Decoding Multidiagonal and Walsh Hadamard Codes for Spectral Amplitude Coding-Optical Code Division Multiple Access (SAC-OCDMA) Utilizing Dispersion Compensated Fiber

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Majidah H. Majeed ◽  
Riyadh Khlf Ahmed
Keyword(s):  
Multiple Access ◽  
Performance Enhancement ◽  
Optical Network ◽  
Spectral Amplitude ◽  
Q Factor ◽  
Data Traffic ◽  
Eye Diagram ◽  
Multiple User ◽  
Spectral Amplitude Coding ◽  
Code Division Multiple

AbstractSpectral Amplitude Coding-Optical Codes Division Multiple Access (SAC-OCDMA) is a future multiplexing technique that witnessed a dramatic attraction for eliminating the problems of the internet in optical network field such as multiple-user access and speed’s growth of the files or data traffic. In this research article, the performance of SAC-OCDMA system based on two encoding–decoding multidiagonal (MD) and Walsh Hadamard (WH) codes is enhanced utilizing three different schemes of dispersion compensating fiber (DCF): pre-, post- and symmetrical compensation. The system is simulated using Optisystem version 7.0 and Optigrating version 4.2. The performance of the proposed system is specified in terms of bit error rate (BER), Q-factor and eye diagram. It has been observed that the compensated system based on MD code is performs much better compared to the system based on WH code. On the other hand, the compensated SAC-OCDMA system with symmetrical DCF has the lowest values of BER and largest values of Q-factor, so it is considered the best simulated scheme contrasted with pre- and post-DCF.

scholarly journals Forecasting Energy Consumption of Wastewater Treatment Plants with a Transfer Learning Approach for Sustainable Cities

Electronics ◽  
2021 ◽  
Vol 10 (10) ◽  
pp. 1149
Author(s):  
Pedro Oliveira ◽  
Bruno Fernandes ◽  
Cesar Analide ◽  
Paulo Novais
Keyword(s):  
Wastewater Treatment ◽  
Energy Consumption ◽  
Transfer Learning ◽  
Short Term Memory ◽  
Wastewater Treatment Plants ◽  
Learning Approach ◽  
Sustainable Cities ◽  
Short Term ◽  
Long Short Term Memory ◽  
Gated Recurrent Units

A major challenge of today’s society is to make large urban centres more sustainable. Improving the energy efficiency of the various infrastructures that make up cities is one aspect being considered when improving their sustainability, with Wastewater Treatment Plants (WWTPs) being one of them. Consequently, this study aims to conceive, tune, and evaluate a set of candidate deep learning models with the goal being to forecast the energy consumption of a WWTP, following a recursive multi-step approach. Three distinct types of models were experimented, in particular, Long Short-Term Memory networks (LSTMs), Gated Recurrent Units (GRUs), and uni-dimensional Convolutional Neural Networks (CNNs). Uni- and multi-variate settings were evaluated, as well as different methods for handling outliers. Promising forecasting results were obtained by CNN-based models, being this difference statistically significant when compared to LSTMs and GRUs, with the best model presenting an approximate overall error of 630 kWh when on a multi-variate setting. Finally, to overcome the problem of data scarcity in WWTPs, transfer learning processes were implemented, with promising results being achieved when using a pre-trained uni-variate CNN model, with the overall error reducing to 325 kWh.

scholarly journals Interval prediction method based on Long-Short Term Memory networks for system integrated of hydro, wind and solar power

2019 ◽  
Vol 158 ◽  
pp. 6176-6182 ◽  
Author(s):  
Zhendong Zhang ◽  
Hui Qin ◽  
Liqiang Yao ◽  
Jiantao Lu ◽  
Liangge Cheng
Keyword(s):  
Solar Power ◽  
Short Term Memory ◽  
Prediction Method ◽  
Short Term ◽  
Term Memory ◽  
Interval Prediction ◽  
Long Short Term Memory

scholarly journals Artificial Neural Networks, Sequence-to-Sequence LSTMs, and Exogenous Variables as Analytical Tools for NO2 (Air Pollution) Forecasting: A Case Study in the Bay of Algeciras (Spain)

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1770
Author(s):  
Javier González-Enrique ◽  
Juan Jesús Ruiz-Aguilar ◽  
José Antonio Moscoso-López ◽  
Daniel Urda ◽  
Lipika Deka ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Short Term Memory ◽  
Prediction Method ◽  
Monitoring Network ◽  
Exogenous Variables ◽  
Prediction Horizon ◽  
Artificial Neural ◽  
Input Variables ◽  
Analytical Tools

This study aims to produce accurate predictions of the NO2 concentrations at a specific station of a monitoring network located in the Bay of Algeciras (Spain). Artificial neural networks (ANNs) and sequence-to-sequence long short-term memory networks (LSTMs) were used to create the forecasting models. Additionally, a new prediction method was proposed combining LSTMs using a rolling window scheme with a cross-validation procedure for time series (LSTM-CVT). Two different strategies were followed regarding the input variables: using NO2 from the station or employing NO2 and other pollutants data from any station of the network plus meteorological variables. The ANN and LSTM-CVT exogenous models used lagged datasets of different window sizes. Several feature ranking methods were used to select the top lagged variables and include them in the final exogenous datasets. Prediction horizons of t + 1, t + 4 and t + 8 were employed. The exogenous variables inclusion enhanced the model’s performance, especially for t + 4 (ρ ≈ 0.68 to ρ ≈ 0.74) and t + 8 (ρ ≈ 0.59 to ρ ≈ 0.66). The proposed LSTM-CVT method delivered promising results as the best performing models per prediction horizon employed this new methodology. Additionally, per each parameter combination, it obtained lower error values than ANNs in 85% of the cases.

Sign in / Sign up

Export Citation Format

Share Document