Magnum: A Distributed Framework for Enabling Transfer Learning in B5G-Enabled Industrial IoT

In this article, we propose a lightweight blockchain-inspired framework—Magnum—as a magazine of transfer learning models in blocks. We propose the storage of these blocks on proximal fog nodes to simplify access to pretrained base models by industrial plants to tune them before deployment. We design Magnum for B5G-enabled scenarios to reduce the block transfer time. We formulate a demand-centric distribution scheme to further reduce the search and access time by adopting a nonlinear program model and solving it using the branch-and-bound method. Through extensive experiments and comparison with state-of-the-art solutions, we show that Magnum retains the accuracy of the models and present its feasibility with a maximum CPU and memory usage of 80% and 6%, respectively. Additionally, while Magnum requires a maximum of 10 s for writing models as large as 17 Mb on the blocks, it requires 16 ms for fetching the same.

[1]  Koenraad Laevens,et al.  Performance of Caching Algorithms for IPTV On-Demand Services , 2009, IEEE Transactions on Broadcasting.

[2]  Hongguang Yun,et al.  An Adaptive Approach for Ice Detection in Wind Turbine With Inductive Transfer Learning , 2019, IEEE Access.

[3]  Laurence T. Yang,et al.  A Secure High-Order CFS Algorithm on Clouds for Industrial Internet of Things , 2018, IEEE Transactions on Industrial Informatics.

[4]  Monica Nicoli,et al.  Federated Learning With Cooperating Devices: A Consensus Approach for Massive IoT Networks , 2019, IEEE Internet of Things Journal.

[5]  Yan Zhang,et al.  Blockchain and Federated Learning for Privacy-Preserved Data Sharing in Industrial IoT , 2020, IEEE Transactions on Industrial Informatics.

[6]  Wei-Chiang Hong,et al.  Machine Learning Adoption in Blockchain-Based Smart Applications: The Challenges, and a Way Forward , 2020, IEEE Access.

[7]  Tsukasa Ike,et al.  A CNN-based Transfer Learning Method for Defect Classification in Semiconductor Manufacturing , 2018, 2018 International Symposium on Semiconductor Manufacturing (ISSM).

[8]  Wenlong Fu,et al.  A Survey of Recent Advances in Transfer Learning , 2019, 2019 IEEE 19th International Conference on Communication Technology (ICCT).

[9]  Jian Zhou,et al.  A Multistage Deep Transfer Learning Method for Machinery Fault Diagnostics Across Diverse Working Conditions and Devices , 2020, IEEE Access.

[10]  Gian Antonio Susto,et al.  Machine Learning for Predictive Maintenance: A Multiple Classifier Approach , 2015, IEEE Transactions on Industrial Informatics.

[11]  Eryk Dutkiewicz,et al.  Deep Transfer Learning for IoT Attack Detection , 2020, IEEE Access.

[12]  Liang Gao,et al.  A New Deep Transfer Learning Based on Sparse Auto-Encoder for Fault Diagnosis , 2019, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[13]  Kin K. Leung,et al.  Adaptive Federated Learning in Resource Constrained Edge Computing Systems , 2018, IEEE Journal on Selected Areas in Communications.

[14]  Ian F. Akyildiz,et al.  Channel Modeling and Capacity Analysis for Electromagnetic Wireless Nanonetworks in the Terahertz Band , 2011, IEEE Transactions on Wireless Communications.

[15]  Yuming Mao,et al.  Data Poison Detection Schemes for Distributed Machine Learning , 2020, IEEE Access.

[16]  Tharam S. Dillon,et al.  A Global Manufacturing Big Data Ecosystem for Fault Detection in Predictive Maintenance , 2020, IEEE Transactions on Industrial Informatics.

[17]  Wang Zhen,et al.  A Blockchain-Based Trusted Data Management Scheme in Edge Computing , 2020, IEEE Transactions on Industrial Informatics.

[18]  Gang Feng,et al.  Federated Cooperation and Augmentation for Power Allocation in Decentralized Wireless Networks , 2020, IEEE Access.

[19]  Zhiguo Gong,et al.  A Common Topic Transfer Learning Model for Crossing City POI Recommendations , 2019, IEEE Transactions on Cybernetics.