Haibin Yu’s research while affiliated with Chinese Academy of Sciences and other places

Industrial Internet, motivated by the deep integration of new-generation information and communication technology (ICT) and advanced manufacturing technology, will open up the production chain, value chain, and industry chain by establishing complete interconnections between humans, machines, and things. This will also help establish novel manufacturing and service modes, where personalized and customized production for differentiated services is a typical paradigm of future intelligent manufacturing. Thus, there is an urgent requirement to break through the existing chimney-like service mode provided by the hierarchical heterogeneous network architecture and establish a transparent channel for manufacturing and services using a flat network architecture. Starting from the basic concepts of process manufacturing and discrete manufacturing, we first analyze the basic requirements of typical manufacturing tasks. Then, with an overview on the developing process of industrial Internet, we systematically compare the current networking technologies and further analyze the problems of the present industrial Internet. On this basis, we propose to establish a novel “thin waist” that integrates sensing, communication, computing, and control for the future industrial Internet. Furthermore, we perform a deep analysis and engage in a discussion on the key challenges and future research issues regarding the multi-dimensional collaborative sensing of task–resource, the end-to-end deterministic communication of heterogeneous networks, and virtual computing and operation control of industrial Internet.

Grant-free access has been widely studied for ultra-reliable and low-latency communications in 5 G networks, wherein contention-based schemes are especially suitable for sporadic traffic. In this paper, we propose a q -Consecutive Repetition Coding based Contention scheme ( q -CRCC). By introducing an activation probability q for each repetition, q -CRCC effectively reduces access collisions for reliable transmissions. Furthermore, we establish an analytical reliability model of q -CRCC and jointly optimize the activation probability and the number of repetitions to improve the transmission reliability of q -CRCC. Besides, the multi-user detection technology is employed to alleviate collision failures. Finally, the accuracy of the obtained analytical reliability model and the advantages of q -CRCC are verified via extensive simulations.

Industrial wireless networks (IWNs) are generally time-sensitive and interference-limited to guarantee real-time and reliability for critical industrial tasks. However, the highconcurrent access of heterogeneous industrial tasks poses great challenges for IWNs which are generally resource-limited. By employing multi-access edge computing (MEC) to enhance the computing capability, this paper proposes a multi-priority computation offloading scheme to realize end-edge orchestrated computing for time-sensitive and interference-limited IWNs based on deep reinforcement learning. Specifically, we study a general scenario that multiple industrial end devices offload tasks to multiple MEC-enhanced industrial base stations to cooperatively accomplish a complex industrial work. By fully considering different task deadlines, edge computing capabilities, maximum transmit power and peak co-channel interference power, we formulate an overall task delay minimization problem with respect to computing decisions, offloading ratios and transmit powers. Due to the non-convexity of the problem, we reformulate it by Markov decision process and design a priority-driven reward, where multiple priorities are assigned according to different deadline requirements. To approximate the optimum solution in the explosive state space, we employ the double and dueling architectures on the basis of deep Q-network (namely D3QN), and propose the D3QN-based multi-priority computation offloading scheme (D3QN-MPCOS). Extensive experiments are performed to validate the suitability and superiority of D3QN-MPCOS for IWNs, where eight benchmark schemes are compared. The results show that D3QN-MPCOS can converge with a higher reward and a smaller overall task delay than other schemes, and satisfy the deadline requirements of heterogeneous industrial tasks under different interference constraints.

Real-time Fe content monitoring in iron ore slurry is crucial for evaluating concentrate quality and enhancing mineral processing efficiency. Laser-induced breakdown spectroscopy (LIBS) is a promising technique for the online monitoring of elemental content at industrial sites. However, LIBS measurements are hampered by the matrix effect and the self-absorption effect, limiting the precision of linear analytical processes. To overcome this, we propose to introduce a nonlinear processing unit based on the S-transform to incorporate nonlinearity into the data analysis process. This approach integrates a feature selection unit based on the spectral distance variable selection method (SDVS), a nonlinear processing unit based on the S-transform (ST), and a partial least squares regression model (PLS). To demonstrate the improvement in accuracy achieved through nonlinear processing, a comparative analysis involving five models, Raw-PLS, SDVS-PLS, ST-PLS, SDVS-ANN, and SDVS-ST-PLS, is conducted. The results reveal a significant improvement in the performance of the SDVS-ST-PLS model, effectively facilitating the successful application of the LIBSlurry analyzer to the mineral flotation process.

With the wide applications of industrial wireless network technologies, industrial control system (ICS) is evolving from wired and centralized to wireless and distributed, during which eavesdropping and attacking become serious problems. To guarantee the security of wireless and distributed ICS, this paper establishes an end-edge collaborative lightweight secure federated learning (LSFL) architecture and proposes a LSFL anomaly detection strategy. Specifically, we first design a residual multi-head self-attention convolutional neural network for local feature learning, where the variability and dependency of spatial-temporal features can be sufficiently evaluated. Then, to reduce the wireless communication cost for parameter exchange and edge federal learning, we propose a dynamic parameter pruning algorithm by evaluating the contribution of each parameter based on the information entropy gain. Furthermore, to ensure the parameter security during wireless transmission in the open radio environment, we propose an adaptive key generation algorithm for parameter encryption. Finally, the proposed strategy is experimentally validated on representative datasets, including Smart Meter, NSL-KDD, and UNSW-NB15. Experimental results demonstrate that the proposed strategy achieves 99% accuracy on different datasets, where at least 89.6% wireless communication cost is reduced and tampering/injecting attacks are defended.

Blockchain-based vehicular edge computing (VEC) is regarded as a promising computing paradigm that can enhance the computing capabilities of mobile vehicles while ensuring security during task offloading. However, the blockchain consensus for secure task offloading inevitably increases the communication and computation resource consumption. More importantly, the frequent handover among roadside units during the fast movement of vehicles also raises the communication cost for blockchain consensus. To address these issues, this paper proposes intelligent secure task offloading and caching (ISTOC) scheme for VEC networks. Specifically, we first establish a digital twin-assisted VEC network that migrates the blockchain consensus process from the physical space to the cyber space, supporting the dynamic handover of vehicles. Correspondingly, we propose a lightweight blockchain scheme named diffused delegated Byzantine fault tolerance (d2BFT). Then, aiming at simultaneously reducing the task processing latency and improving the blockchain transaction throughput, we formulate the joint blockchain, communication, computation, and caching (B3C) optimization problem subject to task division, communication bandwidth, computing frequency, cache storage, task deadline, and blockchain stability. Due to the non-convexity of B3C, we transform it into a Markov decision process, and propose a multi-agent double actor-critic (MADAC) algorithm in light of the distributed characteristic of blockchain. Through offline training and online execution, we jointly optimize the task division, communication bandwidth, computing frequency and cache storage allocation, block size, and block generation interval for ISTOC. Experimental results show that the proposed MADAC-based ISTOC scheme can stably converge with a much higher reward than the benchmark schemes based on MADDPG, SAC, DDPG, and TD3. The improvement of MADAC-ISTOC over SAC-ISTOC is more than 25.93%.

With the interdisciplinary advances of mobile communication and edge computing, massive heterogeneous tasks are accessing wireless networks and competing for the edge-end computing and communication resources. Digital twin (DT), which establishes the digital models of physical objects for simulation, analysis and optimization, provides a promising method for network scheduling and management. This paper proposes a DT-driven edge-end collaborative scheduling algorithm for heterogeneous tasks and heterogeneous computing/communication resources. Specifically, multiple end devices (EDs) cooperate with each other to accomplish a complex job, where each ED can offload individual task to multiple edge servers (ESs) for parallel computing. By fully considering deadline requirements of heterogeneous tasks, maximum computing capabilities of ESs and EDs, computing resource estimation deviations of DT, maximum transmit powers of EDs and tolerable peak interference powers to coexisting EDs, we formulate a job completion time minimization problem to jointly optimize the edge-end task division, transmit power control, computing resource type matching and allocation. To solve this non-convex problem, we first reformulate it by multi-agent Markov decision process, where a compound reward leveraging latency reward and deadline reward according to the task criticality is designed. Then, we propose a multi-agent deep reinforcement learning-based scheduling algorithm, where Actor-Critic framework with estimation and target networks is designed for policy and value iterations. Meanwhile, a step-by-step ϵ-greedy algorithm is proposed to balance exploration and exploitation, avoiding local optimal trap. Through offline centralized training by DT and online distributed execution by EDs, we realize edge-end collaborative computing for heterogeneous tasks. Experimental results demonstrate that, comparing with typical benchmark algorithms, the proposed algorithm converges with the highest reward and achieves the smallest job completion time, where the deadlines of heterogeneous tasks can be well satisfied respectively.

Ultra reliable low latency communication (URLLC) is a promising technology to enable critical industrial wireless control, such as tactile sensing and motion control. This article presents a novel software-defined URLLC prototype and establishes a human-in-loop robotic teleoperation platform for experimental evaluations. First, by studying the control and communication requirements of robotic teleoperation, the key challenges for URLLC-based industrial wireless control are analyzed. Then, the prototype development including protocol stack and hardware architecture design is introduced in detail, and extensive experiments are performed to evaluate the communication latency and control transparency for robotic teleoperation. Experimental results show that the prototype can realize millisecond-level latency with ultra-high reliability, and support wireless teleoperation with similar transparency as wired teleoperation. Finally, challenges and future research issues towards 6G are discussed.