Abstract:LoRaWAN is a low-power long-range protocol that enables reliable and robust communication. This paper addresses the challenge of predicting the spreading factor (SF) in LoRaWAN networks using machine learning (ML) techniques. Optimal SF allocation is crucial for optimizing data transmission in IoT-enabled mobile devices, yet it remains a challenging task due to the fluctuation in environment and network conditions. We evaluated ML model performance across a large publicly available dataset to explore the best feature across key LoRaWAN features such as RSSI, SNR, frequency, distance between end devices and gateways, and antenna height of the end device, further, we also experimented with 31 different combinations possible for 5 features. We trained and evaluated the model using k-nearest neighbors (k-NN), Decision Tree Classifier (DTC), Random Forest (RF), and Multinomial Logistic Regression (MLR) algorithms. The combination of RSSI and SNR was identified as the best feature set. The finding of this paper provides valuable information for reducing the overall cost of dataset collection for ML model training and extending the battery life of LoRaWAN devices. This work contributes to a more reliable LoRaWAN system by understanding the importance of specific feature sets for optimized SF allocation.
Abstract:Signal transmission over underwater optical wireless communication (UOWC) experiences the combined effect of oceanic turbulence and pointing errors statistically modeled using the sum of two Meijer-G functions. There is a research gap in the exact statistical analysis of multi-aperture UOWC systems that use selection combining diversity techniques to enhance performance compared to single-aperture systems. In this paper, we develop a general framework for the continued product and positive integer exponent for the sum of Meijer-G functions to analyze the exact statistical performance of the UOWC system in terms of multivariate Fox-H function for both independent and non-identically distributed (i.ni.d.) and independent and identically distributed (i.i.d.) channels. We also approximate the performance of a multi-aperture UOWC system with i.i.d. channels using the single-variate Fox-H function. Using the generalized approach, we present analytical expressions for average bit-error rate (BER) and ergodic capacity for the considered system operating over exponential generalized gamma (EGG) oceanic turbulence combined with zero-boresight pointing errors. We also develop asymptotic expressions for the average BER at a high signal-to-noise (SNR) to capture insights into the system's performance. Our simulation findings confirm the accuracy of our derived expressions and illustrate the impact of turbulence parameters for i.ni.d. and i.i.d. models for the average BER and ergodic capacity, which may provide a better estimate for the efficient deployment of UOWC.