The Use of Blockchain to Support Distributed AI Implementation in IoT Systems

Abstract : This paper presents a distributed and decentralized architecture for the implementation of Distributed Artificial Intelligence (DAI) using hardware platforms provided by the Internet of Things (IoT). A trained DAI system has been implemented over the IoT, where each IoT device acts as one or more of the neurons within the DAI layers. This is accomplished through the utilization of decentralized, self-managed blockchain technologies that allow trusted interactions and information to be exchanged between distributed neurons. The platform was built and customized to be used within the IoT system, and it is capable of handling DAI-related tasks. A new consensus mechanism based on Proof of Authority (PoA) and Proof of Work (PoW) has been designed and implemented, along with bespoke block and transaction formats. The proposed architecture was analyzed, implemented, and tested using a dedicated testbed with low-cost IoT devices. A quantitative measurement and performance evaluation of the system based on a real-world IoT application was conducted. The implemented DAI is found to have an accuracy of 92%-98%, with an energy cost of 0.12 joules (J) when utilizing a Raspberry Pi to run one neuron. The measured hash per joule (h/J) when using a Raspberry Pi for mining is 13.8Kh/J compared to 54Kh/J using an ESP32. The results showed that it is feasible to implement a DAI system utilizing the IoT hardware platform while maintaining the system’s accuracy. The integration of the blockchain has added an element of security and trust to the data and the interaction between system components.

 EXISTING SYSTEM :

 ? It provides an opportunity to extract new data and improve existing business processes, bring innovative products and services to market fast, and gather new information on consumer trends and preferences. ? Although the commitment of stakeholders to invest in a Blockchain platform is key, it takes further effort to integrate the functionalities into existing operations. ? But the challenge for the enterprise is to build on existing technology, infrastructure, and capabilities to accelerate time to value, and minimize the cost and complexity of IoT implementation. ? Apply it to existing infrastructure and capabilities, instead of starting from scratch.

 DISADVANTAGE :

 ? IoT devices are mainly utilized to tackle our everyday problems and to facilitate our life by sensing and collecting various kinds of information about our surrounding physical environment that are utilized to create novel digitized services. ? Besides, the scalability of the centralized architecture is another problem, which may not be a practical solution for the IoT system that increases in billions every year. ? Basically, the hash function is a mathematical problem that the minors need to crack to find a block. ? Minors are computers/agents that attempt to solve a complex mathematical problem (typically, a form of hash functions) to explore a new block.

 PROPOSED SYSTEM :

 • To secure the proposed architecture a new concept for consensus mechanism based on Honesty-Based Distributed Proof of Work (DPOW) were devised and tested. • Another work by proposed an EdgeChain framework based on blockchain and smart contract that allows IoT devices to access resources provided by the edge servers. • ModelChain proposed by, which aims at allowing multiple institutions to train the medical health prediction framework using blockchain and machine learning. • The work by proposed the BlockDeepNet framework, which combined the implementation of deep learning, blockchain, and smart contracts for data analyses in IoT.

 ADVANTAGE :

 ? They showed technological benefits and technical advantages of integrating blockchain and IoT in agriculture to improve security, transparency and overall efficiency. ? Then, they proposed that blockchain technology be integrated with the IoT to build an efficient identity management system to provide better trust and performance. ? While implementing blockchain on-premise is very costly, as it needs high-cost equipment to build the infrastructure and performance of the distributed ledger technology. ? Although the invention of fog/edge computing minimized the response time that allows real-time-based IoT applications to grow significantly, adopting AI approaches will have the capability to provide better performance in a very short response time.