TY - JOUR
T1 - Machine-Learning-Assisted Transmission Power Control for LoRaWAN Considering Environments With High Signal- to -Noise Variation
AU - Gonzalez-Palacio, Mauricio
AU - Tobon-Vallejo, Diana
AU - Sepulveda-Cano, Lina M.
AU - Mauricio, Mario
AU - Roehrig, Christof
AU - Bao Le, Long
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2024
Y1 - 2024
N2 - To achieve an adequate tradeoff between range and energy efficiency, LoRaWAN End Nodes (ENs) choose their transmission parameters using an Adaptive Data Rate (ADR) scheme based on the maximum value of previous Signal-to-Noise (SNR) values. However, the ADR only performs well in favorable channel conditions. In fact, if the SNR exhibits high variability, these parameters could be inefficiently set and may negatively affect the Packet Delivery Rate (PDR). Therefore, a link margin could be overestimated to improve the PDR by the ADR algorithm, which may, however, waste the EN's energy. This paper proposes a novel ADR that does not rely on the past SNR values. Still, our proposed design directly predicts the current SNR and transmission parameters using Machine Learning. Specifically, the underlying Machine Learning models were trained using in-field measurements for six months in Medellín, Colombia, including different environmental variables and their effects on the SNR. Our ADR scheme improved energy consumption by 47.1% with a PDR of 99% and reduced collisions in dense networks up to 9.5% compared with the ADR scheme. Furthermore, we show that our proposed design outperforms some enhanced versions of the ADR scheme proposed in the literature in both energy consumption and collision rate. Finally, our proposed framework enables simple implementation since it runs directly in the ENs, improving the response time compared with the traditional ADR scheme.
AB - To achieve an adequate tradeoff between range and energy efficiency, LoRaWAN End Nodes (ENs) choose their transmission parameters using an Adaptive Data Rate (ADR) scheme based on the maximum value of previous Signal-to-Noise (SNR) values. However, the ADR only performs well in favorable channel conditions. In fact, if the SNR exhibits high variability, these parameters could be inefficiently set and may negatively affect the Packet Delivery Rate (PDR). Therefore, a link margin could be overestimated to improve the PDR by the ADR algorithm, which may, however, waste the EN's energy. This paper proposes a novel ADR that does not rely on the past SNR values. Still, our proposed design directly predicts the current SNR and transmission parameters using Machine Learning. Specifically, the underlying Machine Learning models were trained using in-field measurements for six months in Medellín, Colombia, including different environmental variables and their effects on the SNR. Our ADR scheme improved energy consumption by 47.1% with a PDR of 99% and reduced collisions in dense networks up to 9.5% compared with the ADR scheme. Furthermore, we show that our proposed design outperforms some enhanced versions of the ADR scheme proposed in the literature in both energy consumption and collision rate. Finally, our proposed framework enables simple implementation since it runs directly in the ENs, improving the response time compared with the traditional ADR scheme.
KW - adaptative data rate
KW - LoRaWAN
KW - machine learning
KW - transmission power control
UR - http://www.scopus.com/inward/record.url?scp=85190347221&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2024.3387457
DO - 10.1109/ACCESS.2024.3387457
M3 - Artículo
AN - SCOPUS:85190347221
SN - 2169-3536
VL - 12
SP - 54449
EP - 54470
JO - IEEE Access
JF - IEEE Access
ER -