TY - JOUR
T1 - Switching in the Rain
T2 - Predictive Wireless x-haul Network Reconfiguration
AU - Kadota, Igor
AU - Jacoby, Dror
AU - Messer, Hagit
AU - Zussman, Gil
AU - Ostrometzky, Jonatan
N1 - Publisher Copyright:
© 2023 Owner/Author.
PY - 2023/6/19
Y1 - 2023/6/19
N2 - 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. The full paper associated with this abstract can be found at https://doi.org/10.1145/3570616.
AB - 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. The full paper associated with this abstract can be found at https://doi.org/10.1145/3570616.
KW - 5g
KW - backhaul
KW - fronthaul
KW - machine learning
KW - millimeter-wave
KW - rain attenuation
KW - routing
KW - wireless networks
UR - http://www.scopus.com/inward/record.url?scp=85164254314&partnerID=8YFLogxK
U2 - 10.1145/3606376.3593574
DO - 10.1145/3606376.3593574
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:85164254314
SN - 0163-5999
VL - 51
SP - 101
EP - 102
JO - Performance Evaluation Review
JF - Performance Evaluation Review
IS - 1
ER -