Delay Optimization in LoRaWAN by Employing Adaptive Scheduling Algorithm With Unsupervised Learning

Low Power Wide Area Network (LPWAN) technologies have been exponentially growing because of the tremendous growth Internet Things (IoT) devices across globe. Several LPWAN utilized by researchers to address certain issues like increased number collisions, retransmissions, delay, and energy consumption. However, Long Range (LoRaWAN) is most suitable attractive technology in terms delay optimization, low cost efficient The main issue which arises LoRaWAN its high packet drop rate due collision. reason behind this MAC scheme known as Pure Aloha used for transmission frames. (LoRa) End Devices (EDs) initiate communication with that leads a retransmissions. These retransmissions further enhance LoRa networks. This paper aims optimize using an Adaptive Scheduling Algorithm (ASA) unsupervised probabilistic approach called Gaussian Mixture Model (GMM). By ASA GMM, are reduced optimizes LoRaWAN. results show our approach, Packet Collision Rate (PCR) 39% compared conventional In addition, Success Ratio (PSR) also Dynamic Priority Technique (PST). Further, optimized 91% 79%. research could be effective environments where critical data patients need sent optimised minimum towards gateways.