Federated Transfer Learning for IIoT Devices With Low Computing Power Based on Blockchain and Edge Computing

Zhang, Peiying; Sun, Hao; Situ, Jingyi; Jiang, Chunxiao; Xie, Dong

doi:10.1109/access.2021.3095078

Cited by 40 publications

(21 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transfer learning enables DNNs to initialize some parameters with weights learned from models pre-trained before and copes with problems that how to process distributed data. Zhang et al [81] proposed to apply transfer learning to improve the service performance of edge devices with poor computing capacity and obtained a high improvement in system-wide efficiency. Cartel [82], a collaborative transfer learning system applied in an edge-cloud environment, aimed to facilitate edge devices with better adaptability to the situation changes.…”

Section: Co-trainingmentioning

confidence: 99%

Edge Intelligence with Distributed Processing of DNNs: A Survey

Tang¹,

Cui²,

Qi³

et al. 2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

With the rapid development of deep learning, the size of data sets and deep neural networks (DNNs) models are also booming. As a result, the intolerable long time for models' training or inference with conventional strategies can not meet the satisfaction of modern tasks gradually. Moreover, devices stay idle in the scenario of edge computing (EC), which presents a waste of resources since they can share the pressure of the busy devices but they do not. To address the problem, the strategy leveraging distributed processing has been applied to load computation tasks from a single processor to a group of devices, which results in the acceleration of training or inference of DNN models and promotes the high utilization of devices in edge computing. Compared with existing papers, this paper presents an enlightening and novel review of applying distributed processing with data and model parallelism to improve deep learning tasks in edge computing. Considering the practicalities, commonly used lightweight models in a distributed system are introduced as well. As the key technique, the parallel strategy will be described in detail. Then some typical applications of distributed processing will be analyzed. Finally, the challenges of distributed processing with edge computing will be described.

show abstract

Section: Co-trainingmentioning

confidence: 99%

Edge Intelligence with Distributed Processing of DNNs: A Survey

Tang¹,

Cui²,

Qi³

et al. 2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

show abstract

“…Smart grid is an important component of industrial systems. Thanks to the smart grid, it is possible to distribute electricity according to the needs of end-users and with the greatest efficiency [9][10][11][12]. As in the Industrial Internet of Things, sensors are used to collect and process data, which then transmits data to central devices.…”

Section: Fig1 Examples Of Iiot Systems B Big Data Processing In Smart...mentioning

confidence: 99%

Big Data Аnalysis in Smart Grid Systems

Wang¹,

Hordiichuk-Bublivska²,

Yan³

et al. 2023

Proceedings of the 18th IMEKO TC10 Conference on Measurement for Diagnostics, Optimisation and Control

View full text Add to dashboard Cite

The problem of Big Data processing in large industrial systems requires the use of machine learning methods. A smart grid system is an example of improving the efficiency of traditional data processing systems, which allows much more efficient and flexible distribution of electricity to end-users. However, for a smart grid to work properly, it needs to constantly monitor data from sensors and meters. The Singular Value Decomposition (SVD) algorithm is used to improve the efficiency of Big Data processing and reduce its dimensionality. The paper proposes the use of advanced SVD, which can work in distributed industrial systems and ensure the reliability and speed of data processing.

show abstract

“…Another study [ 27 ] investigated the role of transfer learning in transferring knowledge for intrusion detection for new devices and transferring knowledge to detect new attacks. The model proposed in [ 28 ] uses the advantages of federated and transfer learning to improve the generalisation training efficiency of the detection system in an industrial IoT environment. With the integration of edge learning in the IIoT network to resolve resource-constrained IIoT devices, securing data transmission with the blockchain becomes crucial, along with the transfer learning model for the federated learning environment, to increase the versatility and efficiency of the training model.…”

Section: Related Workmentioning

confidence: 99%

Customised Intrusion Detection for an Industrial IoT Heterogeneous Network Based on Machine Learning Algorithms Called FTL-CID

Abosata

Al‐Rubaye

Tsourdos

2022

Sensors

View full text Add to dashboard Cite

Technological breakthroughs in the Internet of Things (IoT) easily promote smart lives for humans by connecting everything through the Internet. The de facto standardised IoT routing strategy is the routing protocol for low-power and lossy networks (RPL), which is applied in various heterogeneous IoT applications. Hence, the increase in reliance on the IoT requires focus on the security of the RPL protocol. The top defence layer is an intrusion detection system (IDS), and the heterogeneous characteristics of the IoT and variety of novel intrusions make the design of the RPL IDS significantly complex. Most existing IDS solutions are unified models and cannot detect novel RPL intrusions. Therefore, the RPL requires a customised global attack knowledge-based IDS model to identify both existing and novel intrusions in order to enhance its security. Federated transfer learning (FTL) is a trending topic that paves the way to designing a customised RPL-IoT IDS security model in a heterogeneous IoT environment. In this paper, we propose a federated-transfer-learning-assisted customised distributed IDS (FT-CID) model to detect RPL intrusion in a heterogeneous IoT. The design process of FT-CID includes three steps: dataset collection, FTL-assisted edge IDS learning, and intrusion detection. Initially, the central server initialises the FT-CID with a predefined learning model and observes the unique features of different RPL-IoTs to construct a local model. The experimental model generates an RPL-IIoT dataset with normal and abnormal traffic through simulation on the Contiki-NG OS. Secondly, the edge IDSs are trained using the local parameters and the globally shared parameters generated by the central server through federation and aggregation of different local parameters of various edges. Hence, transfer learning is exploited to update the server’s and edges’ local and global parameters based on relational knowledge. It also builds and customised IDS model with partial retraining through local learning based on globally shared server knowledge. Finally, the customised IDS in the FT-CID model enforces the detection of intrusions in heterogeneous IoT networks. Moreover, the FT-CID model accomplishes high RPL security by implicitly utilising the local and global parameters of different IoTs with the assistance of FTL. The FT-CID detects RPL intrusions with an accuracy of 85.52% in tests on a heterogeneous IoT network.

show abstract

Federated Transfer Learning for IIoT Devices With Low Computing Power Based on Blockchain and Edge Computing

Cited by 40 publications

References 39 publications

Edge Intelligence with Distributed Processing of DNNs: A Survey

Edge Intelligence with Distributed Processing of DNNs: A Survey

Big Data Аnalysis in Smart Grid Systems

Customised Intrusion Detection for an Industrial IoT Heterogeneous Network Based on Machine Learning Algorithms Called FTL-CID

Contact Info

Product

Resources

About