Machine-Learning-Based Combined Path Loss and Shadowing Model in LoRaWAN for Energy Efficiency Enhancement

Abstract

Many practical Internet of Things (IoT) applications require deploying End Nodes (ENs) in hard-to-access places where replacing batteries is difficult or impossible. As a result, the ENs demand high energy efficiency. Long Range Wide Area Network (LoRaWAN) is an IoT protocol that aims to achieve low energy consumption. However, the energy consumption in LoRaWAN is related to transmission power, which can be set mainly based on path loss and shadow fading modeling and link budget analysis. Hence, appropriately setting this transmission power parameter saves energy and guarantees reliable communication links. Traditional path loss and shadow fading modeling and transmission power setting do not consider the variations caused by different environmental effects. In this work, we show via real-life data analysis that path loss and shadow fading depend on environmental variables. We propose Machine Learning models to calculate the empirical path loss and shadow fading, which is used to set the transmission power to save ENs’ energy. Our models include the effects of distance, frequency, temperature, relative humidity, barometric pressure, particulate matter, and Signal to Noise Ratio. Specifically, the models are based on Multiple Linear Regression, Support Vector Regression, Random Forests, and Artificial Neural Networks, exhibiting a Root Mean Square Error (RMSE) up to 1.566 dB and R up to 0.94. For energy saving, the developed models serve to set the transmission power and Spreading Factor based on the Adaptative Data Rate (ADR) algorithm principles, which reduces the link margin saving energy up to 43% compared with the traditional ADR protocol. IEEE