Data Transmission Using K-Means Clustering in Low Power Wide Area Networks with Mobile Edge Cloud

Abstract

Low-power, long-range wireless communication has become important for IoT applications in wide space. A Low-Power Wide Area Network (LPWAN) has been proposed to support wireless communication. It provides very long communication distances with low data rates and uses a very simple transmission mechanism to deliver data packets over long distances. The simple transmission mechanism does not consider device characteristics according to generated data. If priority according to the device characteristics is considered during data transmission, the transmission efficiency of each service can be improved. Therefore, this paper proposes data transmission considering device characteristics. The proposed method employs a k-means clustering algorithm to classify devices according to the traffic characteristic. Each group of classified devices has different priority, and the wireless channel access time is determined by that priority. Using different channel access times according to priority allows end-devices to avoid collisions and improve transmission efficiency in LPWAN with long delay. The proposed method is compared to typical transmission methods in an LPWAN through the performance evaluation by computer simulations and its transmission efficiency is validated.