Minimizing Forking in Blockchain-Based IoT Networks

Abstract

Blockchain is a special type of data structure in which data, usually termed as transactions, is linked together using cryptographic techniques. Because of these modular features, the applications of blockchain are being investigated in myriad domains such as cybersecurity, finance, transportation, and Internet-of-things (IoT). Although the applications of blockchain in IoT networks have much potential, many research challenges need the attention of researchers from both academia and industry. One of the open research challenges is the frequent occurrence of forking events in blockchain-based IoT networks. The forking of a blockchain can not only lead to potential security attacks but also poses excessive overhead in the largescale IoT networks. To tackle this inefficiency of blockchain-based IoT networks, this paper employs deep learning to minimize forking by reducing the transmission delays. Specifically, a deep neural network is used to reduce the transmission delay by improving the transmission rate. The deep learning approach is also compared with other benchmark techniques to show the superiority of the proposed method. We anticipate that this foundational work on blockchain-based IoT networks would pave the way for researchers to upscale the study into real-world implementations.