Attenuation prediction for fade mitigation using neural network with in situ learning algorithm

Roy, B. K.; Acharya, Rajat; Sivaraman, M. R.

doi:10.1016/j.asr.2011.10.010

Cited by 13 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mean (%), RMS (%), and STD (%) error experimented on the DBSG3 plus tropical database [21] AANN+ILA [14] Develop a rain attenuation prediction technique using a learning algorithm where measured attenuation is used to develop the model.…”

Section: Gradient Descent Methods Not Reportedmentioning

confidence: 99%

“…For better visualization, data range was rescaled from −5 to +15. Model Accuracy R 2 RMSE = 0.2578←25.78% (DBSG3) AANN+ILA [14] Accuracy = 95% (20 s interval) × RA [16] Accuracy = 97% × × = unavailable Figure 9. The bar chart shows the root mean square error (RMSE) of few LARA models.…”

Section: Gradient Descent Methods Not Reportedmentioning

confidence: 99%

“…Bijoy Roy et al [14] used three sites' attenuation data about the 11 GHz frequency to predict the short-term rain attenuation prediction for the standard fade mitigation technique (FMT) application. The technique is composed of AANN that enables predicting short-term rain attenuation while the ILA technique helps in case any rain event behavior is non-stationary (Figure 5).…”

Section: Lara Model With One Factormentioning

confidence: 99%

“…The model-specific contributions, optimization and evaluation criteria, accuracy level, and input-output parameter correlation (R 2 ) are compared in Tables 4 and 5, respectively. Figure 9 (Root-mean-square error (RMSE) versus model) shows that RA [15] has the least RMSE value following the minimum RMSE models, which are AANN+ILA [14] and SL FFBP [4]. Regarding model FFMLP+SL [12], we cannot get a comparative result, but following the remarks about Relative RMSE (RRMSE) accuracy [16], RRMSE = 8.5% can be considered as an excellent result, concerning the models' applicability.…”

Section: Comparison Of Lara Models Of Rain Attenuationmentioning

confidence: 99%

See 3 more Smart Citations

Learning-Assisted Rain Attenuation Prediction Models

Samad

Choi

2020

Applied Sciences

View full text Add to dashboard Cite

Rain attenuation becomes significant to degrade the earth-space or terrestrial radio link’s signal-to-noise ratio (SNR). So, to maintain the desired SNR level, with the help of fade mitigation techniques (FMTs), it needs to control transmitted signals power considering the expected rainfall. However, since the rain event is a random phenomenon, the rain attenuation that may be experienced by a specific link is difficult to estimate. Many empirical, physical, and compound nature-based models exist in the literature to predict the expected rain attenuation. Furthermore, many optimizations and decision-making functions have become simpler since the development of the learning-assisted (LA) technique. In this work, the LA rain attenuation (LARA) model was classified based on input parameters. Besides, for comparative analysis, each of the supported frequency components of LARA models were tabulated, and an accurate contribution of each model was identified. In contrast to all the currently available LARA models, the accuracy and correlation of input-output parameters are presented. Additionally, it summarizes and discusses open research issues and challenges.

show abstract

Section: Gradient Descent Methods Not Reportedmentioning

confidence: 99%

Section: Gradient Descent Methods Not Reportedmentioning

confidence: 99%

Section: Lara Model With One Factormentioning

confidence: 99%

Section: Comparison Of Lara Models Of Rain Attenuationmentioning

confidence: 99%

See 2 more Smart Citations

Learning-Assisted Rain Attenuation Prediction Models

Samad

Choi

2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Rain attenuation is a serious consideration in operational satellite communication systems utilizing frequencies above 10 GHz, particularly over tropical regions due to high rain rates and frequent occurrences of rain events (Das et al, ; Green, ; Ippolito Jr, ; Panagopoulos et al, ). Conventional fade mitigation techniques such as adaptive power control may not be an effective tool to overcome the rain attenuation in Ka/V band in which fading can be in excess of 20 dB for substantial percentage of time in a year (Green, ; Panagopoulos et al, ; Roy et al, ). In this scenario, diversity schemes are explored as alternatives to avoid such high fade situations by exploiting the space‐time variability of rainfall.…”

Section: Introductionmentioning

confidence: 99%

Site Diversity Prediction at a Tropical Location From Single‐Site Rain Measurements Using a Bayesian Technique

Das

Jameson²

2018

Radio Science

View full text Add to dashboard Cite

Site diversity is one of the few fade mitigation techniques that are actively explored to overcome the serious fading condition encountered in high‐frequency satellite communication, particularly over tropical regions. However, the study of site diversity performance is limited over tropical regions due to unavailability of simultaneous fade measurements from multiple locations as well as the lack of data on spatial rain pattern from radar measurements. We propose here a copula‐based Bayesian approach to study the site diversity performance utilizing only a single location's drop size distribution measurement. Study of diversity performance has been done for Ahmedabad, India, utilizing 3 years of disdrometer data. Effects of frequency, elevation angle, and site separation on diversity gain are investigated using the proposed method. Results are compared with two ITU‐R models, site diversity results from Italy, a temperate region, and Singapore, another tropical location. The spatial correlation obtained through this technique is also compared with radar observations in Oklahoma, a totally different climatic regime. The simple ITU‐R model is found to be underpredicting the diversity gain significantly for the present location whereas the explicit ITU‐R model shows overprediction above 8 dB for single‐site rain attenuation values. Comparison with measurements at Italy shows similar diversity gains for low single‐site attenuation values. The results reported for Singapore matches well with the present method. The study indicates room for improvement in the present ITU‐R model considering the different nature of tropical rain and that the proposed method is suitable for such a purpose.

show abstract