This work proposes an Adaptive Fuzzy Prediction (AFP) method for the attenuation time series in Commercial Microwave links (CMLs). Time-series forecasting models regularly rely on the assumption that the entire data set follows the same Data Generating Process (DGP). However, the signals in wireless microwave links are severely affected by the varying weather conditions in the channel. Consequently, the attenuation time series might change its characteristics significantly at different periods. We suggest an adaptive framework to better employ the training data by grouping sequences with related temporal patterns to consider the non-stationary nature of the signals. The focus in this work is two-folded. The first is to explore the integration of static data of the CMLs as exogenous variables for the attenuation time series models to adopt diverse link characteristics. This extension allows to include various attenuation datasets obtained from additional CMLs in the training process and dramatically increasing available training data. The second is to develop an adaptive framework for short-term attenuation forecasting by employing an unsupervised fuzzy clustering procedure and supervised learning models. We empirically analyzed our framework for model and data-driven approaches with Recurrent Neural Network (RNN) and Autoregressive Integrated Moving Average (ARIMA) variations. We evaluate the proposed extensions on real-world measurements collected from 4G backhaul networks, considering dataset availability and the accuracy for 60 seconds prediction. We show that our framework can significantly improve conventional models’ accuracy and that incorporating data from various CMLs is essential to the AFP framework. The proposed methods have been shown to enhance the forecasting model’s performance by 30 − 40%, depending on the specific model and the data availability.
more »
« less
Short-Term Prediction of the Attenuation in a Commercial Microwave Link Using LSTM-based RNN
The signals of microwave links used for wireless
communications are prone to attenuation that can be significant due to rain. This attenuation may limit the capacity
of the communication channel and cause irreversible damage.
Accurate prediction of the attenuation opens the possibility
to take appropriate actions to minimize such damage. In this
paper, we present the use of the Long Short Time Memory
(LSTM) machine learning method for short term prediction of
the attenuation in commercial microwave links (CMLs), where
only past measurements of the attenuation in a given link are
used to predict future attenuation, with no side information. We
demonstrate the operation of the proposed method on real-data
signal level measurements of CMLs during rain events in Sweden.
Moreover, this method is compared to a widely used statistical
method for time series forecasting, the Auto-Regression Moving
Average (ARIMA). The results show that learning patterns from
previous attenuation values during rain events in a given CM
more »
« less
- Award ID(s):
- 1910757
- NSF-PAR ID:
- 10218479
- Date Published:
- Journal Name:
- 2020 28th European Signal Processing Conference (EUSIPCO)
- Page Range / eLocation ID:
- 1628 to 1632
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This work proposes an Adaptive Fuzzy Prediction (AFP) method for the attenuation time series in Commercial Microwave links (CMLs). Time-series forecasting models regularly rely on the assumption that the entire data set follows the same Data Generating Process (DGP). However, the signals in wireless microwave links are severely affected by the varying weather conditions in the channel. Consequently, the attenuation time series might change its characteristics significantly at different periods. We suggest an adaptive framework to better employ the training data by grouping sequences with related temporal patterns to consider the non-stationary nature of the signals. The focus in this work is two-folded. The first is to explore the integration of static data of the CMLs as exogenous variables for the attenuation time series models to adopt diverse link characteristics. This extension allows to include various attenuation datasets obtained from additional CMLs in the training process and dramatically increasing available training data. The second is to develop an adaptive framework for short-term attenuation forecasting by employing an unsupervised fuzzy clustering procedure and supervised learning models. We empirically analyzed our framework for model and data-driven approaches with Recurrent Neural Network (RNN) and Autoregressive Integrated Moving Average (ARIMA) variations. We evaluate the proposed extensions on real-world measurements collected from 4G backhaul networks, considering dataset availability and the accuracy for 60 seconds prediction. We show that our framework can significantly improve conventional models’ accuracy and that incorporating data from various CMLs is essential to the AFP framework. The proposed methods have been shown to enhance the forecasting model’s performance by 30 − 40%, depending on the specific model and the data availability.more » « less
-
4G, 5G, and smart city networks often rely on microwave and millimeter-wave x-haul links. A major challenge associated with these high frequency links is their susceptibility to weather conditions. In particular, precipitation may cause severe signal attenuation, which significantly degrades the network performance. In this paper, we develop a Predictive Network Reconfiguration (PNR) framework that uses historical data to predict the future condition of each link and then prepares the network ahead of time for imminent disturbances. The PNR framework has two components: (i) an Attenuation Prediction (AP) mechanism; and (ii) a Multi-Step Network Reconfiguration (MSNR) algorithm. The AP mechanism employs an encoder-decoder Long Short-Term Memory (LSTM) model to predict the sequence of future attenuation levels of each link. The MSNR algorithm leverages these predictions to dynamically optimize routing and admission control decisions aiming to maximize network utilization, while preserving max-min fairness among the nodes using the network (e.g., base-stations) and preventing transient congestion that may be caused by switching routes. We train, validate, and evaluate the PNR framework using a dataset containing over 2 million measurements collected from a real-world city-scale backhaul network. The results show that the framework: (i) predicts attenuation with high accuracy, with an RMSE of less than 0.4 dB for a prediction horizon of 50 seconds; and (ii) can improve the instantaneous network utilization by more than 200% when compared to reactive network reconfiguration algorithms that cannot leverage information about future disturbances.more » « less
-
Wireless x-haul networks rely on microwave and millimeter-wave links between 4G and/or 5G base-stations to support ultra-high data rate and ultra-low latency. A major challenge associated with these high frequency links is their susceptibility to weather conditions. In particular, precipitation may cause severe signal attenuation, which significantly degrades the network performance. In this paper, we develop a Predictive Network Reconfiguration (PNR) framework that uses historical data to predict the future condition of each link and then prepares the network ahead of time for imminent disturbances. The PNR framework has two components: (i) an Attenuation Prediction (AP) mechanism; and (ii) a Multi-Step Network Reconfiguration (MSNR) algorithm. The AP mechanism employs an encoderdecoder Long Short-Term Memory (LSTM) model to predict the sequence of future attenuation levels of each link. The MSNR algorithm leverages these predictions to dynamically optimize routing and admission control decisions aiming to maximize network utilization, while preserving max-min fairness among the base-stations sharing the network and preventing transient congestion that may be caused by re-routing. We train, validate, and evaluate the PNR framework using a dataset containing over 2 million measurements collected from a real-world city-scale backhaul network. The results show that the framework: (i) predicts attenuation with high accuracy, with an RMSE of less than 0.4 dB for a prediction horizon of 50 seconds; and (ii) can improve the instantaneous network utilization by more than 200% when compared to reactive network reconfiguration algorithms that cannot leverage information about future disturbancesmore » « less
-
Smart cities around the world are supported by high-capacity wireless communication networks, which are based on millimeter-waves links. The propagating waves are sensitive to hydrometeors, and their signal level is attenuated by rain. However, most of the links in such networks are shorter than 1 km, imposing large errors on the rain estimation results. In this paper we demonstrate, using actual measurements from the city of Rehovot, Israel, how high-resolution rain maps can be generated from the received signal level measurements collected by these links. We first propose a method for reducing the errors in converting signal attenuation to rainfall estimates in short, incity links. The proposed method requires calibration of model parameters using side information from either a rain gauge or a long link in the vicinity of the network. We empirically analyze the results of the calibrating method using either auxiliary measurements and show that the performance is satisfactory for both. Then, we apply a spatial interpolation method on the rainfall resulting estimates, and demonstrate the construction of an high-resolution 2-D map of the accumulated rain in a city, a product with great potential for improving well-being of life in urban areas.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.23919/Eusipco47968.2020.9287835
