0000-0003-2963-7729 Isparta, Turkey
Abstract: Reaching a sufficient number of data sets, learning past experiences from many systems and using this experience in instant or future predictions are among the capabilities of artificial intelligence. The horizontal and vertical growth of industrial systems and the transfer of experience from each location to all other locations increase the quality of the process. However, the rapid growth of IoT (Internet of Things) and OT (Operational Technology) assets in recent years raises questions about data integrity, confidentiality and accessibility. It deploys edge computing and blockchain-based solutions for data security and secure transmission in the IoT ecosystem. In this study, a four-layer IoT ecosystem network is proposed that combines the learning capabilities of artificial intelligence-based systems used in different locations and offers a blockchain-based storage system for data security. These layers consist of node layer, edge layer, decision layer, and training and blockchain layer, respectively. The lowest layer, the node layer, is responsible for collecting the temperature and humidity values ​​in different locations with the developed node devices in order to evaluate them. The data generated in the node devices is transferred to the communicating edge device in the edge layer. The edge layer collects the data from the nodes in the edge system and transfers it to the server centrally. The training and blockchain layer provide the collection of data from edge devices, training the artificial intelligence model and transferring the weights to the decision layer. At the same time, the blockchain-based storage system works at this layer to securely store the processed data. As a result, with this study, it is aimed to develop a framework for transferring the local learning experiences of distributed IoT devices to all IoT devices and for the secure storage of data.
Keywords: Blockchain, Edge Computing, Distributed Learning, IoT
INTRODUCTION
IoT technology, which is one of the assets of the Industry 4.0 ecosystem, is becoming more and more widespread in our daily lives and is consolidating its place in the field of technology. Capable IoT devices for different purposes have been developed to meet the various needs of technology and people [1]. In developed IoT technologies, hardware has limited capacities and limited processing power. For this reason, various methods are preferred for the security and performance of IoT devices. While the developed IoT devices were combined with edge computing technology, they preferred server-client architecture with security protocols such as SSL (Secure Socket Layer) and TLS (Transport Layer Security). However, this situation creates a bottleneck threat due to continuous growth in the process and may cause delays and malfunctions as a result of blockages in network traffic [6]. With these developments, many problem areas that need to be developed in terms of efficiency, security requirements, resource usage and user security have emerged [3, 5]. Many IoT devices used to gather information from the environment do not have enough resources to deal with malicious cyber-attacks. Manipulating the data collected by these devices or intentionally uploading unwanted data disrupts the integrity of the system set up in terms of security [2].
Considering all these problem areas and processes, valuable features such as getting rid of single point centralization, data immateriality and transaction transparency have made the combined use of edge computing and blockchain technologies popular [4]. Security problems that may be encountered during the collection and distribution of data obtained from IoT devices using edge computing technology are tried to be eliminated by using blockchain technology [1, 6, 9]. In particular, keeping and securing transaction records has attracted the attention of many researchers. While some of the researchers care about the security dimension in storing transaction records [6], some of them have deepened their studies on analysis and scalability [8]. Many of the studies have focused on keeping and protecting the transaction records produced by IoT devices.
More than fifty countries have officially published strategy papers/regulations summarizing their official positions on cyberspace, cybercrime and cybersecurity [10, 11]. Prevention and detection of computer crimes are among the main objectives of cyber security and information security. The authorities take constitutional measures on this issue. In Turkey, Law No. 5651 came into force for “regulating the broadcasts made on the Internet and combating the crimes committed through these broadcasts”. With the General Data Protection Regulation (GDPR), a regulation on data protection and privacy has been prepared for individuals. GDPR primarily aims to give individuals control of their personal information and to bring companies in the EU into compliance with these regulations [12].
In order to ensure the confidentiality, integrity and security of the data in the proposed security models in the studies carried out, specific methods are presented for that study. In the healthcare field, patients’ health information is critical to the privacy of personal data. In studies built on this basis, alternative methods have been developed by combining blockchain technology to ensure the confidentiality of data collected from health devices and encryption algorithms to ensure security [7, 8]. Therapy, diagnostic and analytical data of bedridden patients, disabled individuals or individuals with mobility restrictions due to old age are monitored remotely. This has made it important to protect the ownership, storage and sharing of therapeutic data during the home therapy service, which has become popular during the pandemic period. The most suitable solution to this problem can be provided with blockchain technology [13]. In addition to data privacy, when considering data security and performance criteria, blockchain technology can be preferred in order not to resort to complex cryptographic methods. In order to provide low-time latency and real-time service, effective solutions to the secure communication problem in smart grid systems are also realized with blockchain technology [14]. Consensus and agreement between nodes is defined as a serious problem in resource allocation processes in wireless networks. This problem can be solved by optimizing the spectrum allocation, block sizes and block numbers with the consortium feature of blockchain technology to improve the service quality of users [15]. In order to increase the efficiency of authentication systems and collaborative sharing designs, systems in which edge computing and blockchain technology are used together have been proposed [16]. In Table 1, the years of studies using blockchain and edge computing technology together, the preferred consensus algorithms, the purpose of the study and literature contributions are shown in a table.
Table 1. Review of studies using blockchain and edge computing together