Nowadays scalable IoT management is a bottleneck of IoT development due to the geographically dispersed distribution, fragmented ownerships, and ever-growing population of IoT devices. To intelligently manage massive decentralized applications (dApps) in IoT usecases, Edgence (EDGe + intelligENCE) uses edge clouds to access IoT devices and users, and then uses its in-built blockchain to realize self-governing and self-supervision of the edge clouds.

• Edgence proposes to use masternode technology to introduce IoT devices and users into a closed blockchain system, which can extend the range of blockchain to IoT-based dApps.
• Further, masternodes do good to scalability by raising the TPS (transactions per second) of the blockchain network.
• To support various dApps, a three-tier validation is proposed, namely script validation, smartcontract validation, and masternode validation.
• To avoid energy consumption resulted by blockchain consensus, Edgence proposes a random but verifiable way to elect a masternode to generate each new block.

Masternode layer as decentralized management

• The set of masternodes can be considered as another layer that is constructed on the blockchain network layer.
• It connects IoT usecases to the blockchain network.
• Everyone can join or leave the masternode layer at will, if she has an edge cloud and a fixed amount of fund as collateral.

Three-tier validation of Edgence

• Every masternode of Edgence contains a blockchain node and hardware resources, and can perform three-tier validation.
• Masternode network connect real world and blockchain, and generate various IoT dApps.

Decentralized AI training under the management of Edgence

• Feed-propagation and back-propagation are two ways of updating model parameters during AI training.
• The first several layers are trained at many edge clouds, which is to utilize the datasets of mobile users.
• The last several layers are trained at a remote cloud center, which keeps communicating with edge clouds during the whole training.
• Edgence's work is to supervise all activities of edge clouds and remote cloud center.

Publications

• Jinliang. Xu, Shangguang. Wang, Bhargava. K. Bharat, Fangchun. Yang, A Blockchain-enabled Trustless Crowd-Intelligence Ecosystem on Mobile Edge Computing, IEEE Transactions on Industrial Informatics, 2019, https://ieeexplore.ieee.org/document/8632682.
• Jinliang Xu, Shangguang Wang, Ning Zhang, Fangchun Yang, Xuemin Shen, Reward or Penalty: Aligning Incentives of Stakeholders in Crowdsourcing, IEEE Transactions on Mobile Computing, 2018, Doi: 10.1109/TMC.2018.2847350[PDF][Source-code].
• Shangguang. Wang, Jinliang. Xu, Ning. Zhang, Yujiong. Liu, A Survey on Service Migration in Mobile Edge Computing, IEEE Access, vol. 6, no.1, pp. 23511-23528, 2018[PDF][Demo].