Blockchain-Based Incentive Energy-Knowledge Trading in IoT: Joint Power Transfer and AI Design

Abstract

Recently, edge artificial intelligence techniques (e.g., federated edge learning) are emerged to unleash the potential of big data from Internet of Things (IoT). By learning knowledge on local devices, data privacy-preserving and quality of service (QoS) are guaranteed. Nevertheless, the dilemma between the limited on-device battery capacities and the high energy demands in learning is not resolved. When the on-device battery is exhausted, the edge learning process will have to be interrupted. In this paper, we propose a novel Wirelessly Powered Edge intelliGence (WPEG) framework, which aims to achieve a stable, robust, and sustainable edge intelligence by energy harvesting (EH) methods. Firstly, we build a permissioned edge blockchain to secure the peer-to-peer (P2P) energy and knowledge sharing in our framework. To maximize edge intelligence efficiency, we then investigate the wirelessly-powered multi-agent edge learning model and design the optimal edge learning strategy. Moreover, by constructing a two-stage Stackelberg game, the underlying energy-knowledge trading incentive mechanisms are also proposed with the optimal economic incentives and power transmission strategies. Finally, simulation results show that our incentive strategies could optimize the utilities of both parties compared with classic schemes, and our optimal learning design could realize the optimal learning efficiency.

Blockchain-Empowered Mobile Edge Intelligence, Machine Learning and Secure Data Sharing

“…Different from the MEC servers with the constant power supply, IoTDs are battery-powered and not very convenient to recharge. Energy- knowledge trading was discussed in [47]. On-device Al applications would be useless when IoTDs' battery is exhausted.…”

Blockchain-Enabled Edge Intelligence for IoT: Background, Emerging Trends and Open Issues

“…Consortium blockchain was further introduced by them for reputation management. Moreover, blockchain-enabled reward systems were considered in Reference [4,[46][47][48][49][50]. Furthermore, the blockchain-enabled data integrity and sources validation could be realized by deep learning with convolutional neural networks [51], giving the trustworthiness of training data quality.…”

“…Therefore, knowledge and energy trading between edge servers and edge nodes is a research trend in this area. Lin et al [4] proposed a novel edge intelligence framework using wireless power transfer. By exploring the permissioned blockchain, the energy and knowledge trading was secured in the proposed framework.…”

“…Energy Trading [4] Propose a novel knowledge and energy trading frame work based on permissioned blockchain.…”

“…The computing operations also cost storage and energy resources. Therefore, a computing resource trading [4] and data sharing [5] framework or platform is needed to motivate edge servers. As a distributed ledger technology (DLT), blockchain has emerged as a potential solution for the above issues, due to its nature of data transparency, distributed operation, and reliability.…”