Digital twin (DT) is a virtual representation of physical entities or processes that enables real-time monitoring, analysis, and optimization in the field of intelligent manufacturing. By simulating and optimizing production processes, DT technology could predict and prevent equipment failures, and enhance the efficiency and quality of industrial parts production. However, effectively deploying DTs into Digital Twin Empowered Edge Network (DITEN) in complex Industrial Internet of Things (IIoT) environments remains a significant challenge. Particularly in scenarios with numerous physical entities within IIoT, optimizing the deployment of DTs on edge nodes to minimize interaction latency with physical entities, as well as reducing workload and energy consumption on edge nodes, becomes crucial. To address this challenge, this paper first designs a Bi-Layer DT architecture for IIoT. Furthermore, an Intrinsic Curiosity Module-based Multi-Agent Proximal Policy Optimization algorithm (ICM-MAPPO) is proposed to solve the optimal deployment problem for DTs in DITEN-Empowered IIoT. Numerical experiments validate the effectiveness of the ICM-MAPPO algorithm in minimizing deployment latency and interaction latency while achieving load balance and reducing energy consumption.

The Industrial Internet of Things (IIoT) imposes strict requirements on task processing delays. To ensure low-latency services, the edge Computing Power Network (CPN) integrates various multi-domain resources, including computing, storage and communication, enabling fast processing and responsiveness. However, the performance of the CPN is significantly influenced by the scheduling scheme for these multi-domain resources. To explore an optimal scheduling scheme, this paper proposes a mathematical optimization model for the resource scheduling problem. The problem is then transformed into a Markov Decision Process (MDP) and the Discrete Probabilistic Deep Deterministic Policy Gradient (DP-DDPG) algorithm, which modifies the actor network of the original DDPG to output a discrete probability vector, is introduced to obtain the optimal scheme. Experimental results demonstrate that the proposed approach reduces latency within the constraints of limited multi-domain resources, validating its feasibility and effectiveness in IIoT scenarios.

Unmanned aerial vehicle (UAV) assisted data collection has been extensively employed in various application scenarios, e.g., nonterrestrial networks for disaster management, agricultural crop protection, environmental monitoring. However, data collection and transmission model in different applications are not universal, and the timeliness of large-scale data collection and transmission also has been remained as a challenge. To address this issue, artificial intelligence (AI)-empowered intelligent search algorithms for path planning in UAV-assisted data collection networks are investigated in this article. With the constraints, including energy consumption, transmission distances, and full coverage of sensors, a data collection model using UAV in hovering mode is first established for minimizing the flight distances of UAVs, and an adaptive full coverage algorithm (AFCA) is proposed to optimize the Quality of Service through using the model. Subsequently, for optimizing the path planning of UAVs, an intelligent path planning algorithm (IPPA) is proposed through considering the loop and noncrossing characteristics presented by the optimal paths. In six testing cases with different sensor sizes, the experimental results have been shown to demonstrate that the proposed solution outperforms the traditional algorithms.

In the paradigm of ubiquitous edge computing, with those advantages, e.g., high mobility, fast response, flexibility and controllability, and low cost of use, Unmanned Aerial Vehicles (UAVs) could be used not only as relays to assist with data collection, but also as computing power nodes to process uncomplicated computational workloads from ground users. Especially, UAVs could be employed to provide alternative computing power resources in field, lake, post-disaster and other complex regional environments. In this paper, to address the issue of computing power scheduling in UAVs empowered aerial computing systems, a scenario where multiple UAVs from the same departure station cooperatively fly over hovering points and achieve the data collection and computation in a decentralized manner is investigated. Nevertheless, due to limited onboard battery capacities of UAVs and diverse service requests of ground users, it is necessary to optimize energy efficiency and service fairness for improving mission execution capabilities of UAVs and the quality of service (QoS) experienced by ground users, and a joint optimization problem of energy efficiency and service fairness is formulated. Through considering complex coupling associations among the departure station, flight paths and hovering points of UAVs, the problem is investigated from the trajectory planning of UAVs and the location planning for both the departure station and hovering points. Proving investigations to be Markov decision processes (MDP), multi-agent cooperation approaches are proposed as promising solutions, and simulation results have been shown to demonstrate that the performance achieved by the proposal outperforms that achieved by schemes commonly used in literatures.

Along with emerging mobile Internet applications embedded in tremendous growth of computing demand, mobile edge computing (MEC) could effectively address the issue of compute-intensive and latency-sensitive computation imposed on mobile terminals through performing computation offloading strategies. However, how to find optimal decisions of transmission power, computing capacity demand, and offloading demand at the end-user and how to determine the resource pricing and allocation at the MEC server with the limited computing capacity still remain challenging issues in operating the MEC system in an optimal fashion. For multiuser in signal cell network with MEC, a dynamic pricing-based computation offloading solution is investigated in this article. Through the use of Q-learning algorithm comprehensively considering those sensitive factors, e.g., time cost, energy consumption and dynamic pricing, the offloading decision at the end-user is achieved with the consideration of time-varying wireless channel conditions. According to the resources supply and demand relationship, a dynamic pricing algorithm for the MEC server is designed to adjust the pricing strategy to achieve the win–win situation. Simulation results have been shown to demonstrate the efficiency in making offloading decision while the wireless channel is fast fading and the resource pricing is adjusted dynamically, and in enhancing utilities for both end-users and the MEC server.

Nowadays, video surveillance is widespread used to achieve security life in the construction of smart city. As a result, prevalence of video surveillance equipments and technologies enables pedestrian identification and tracking to be research hotspots in the field of computer vision, whose development and application are of great significance to the construction of a good social security environment. However, pedestrian identification and tracking in monitoring scenarios still have problems of low recognition accuracy and high model complexity, and computer vision based adaptive recognition methods still have a large room for improvement and development. To address this issue, real-time pedestrian identification and tracking within adaptive collaboration edge computing environment is investigated in this paper. Within the paradigm of edge computing, the Raspberry Pi 3B+ acting as the edge computing node is adopted to handle the related issues of pedestrian identification and tracking. The combination of HOG (Histogram of Oriented Gradient) and SVM (Support Vector Machine) is investigated to achieve pedestrian identification, where, HOG is employed as the feature descriptor and SVM is employed as the classification algorithm. Furthermore, the pixel-based visual tracking algorithm is investigated to achieve effective and uninterrupted pedestrian tracking. By implementing a prototype on Raspberry Pi 3B+ using OpenCV libraries, the experimental results finally have been shown to demonstrate the efficiency of the investigations.

As an advanced method of multivariate data analysis, structural equation modeling (SEM) is to obtain relationships among latent variables in structural models. One characteristic of SEM models is that the same substructures exist in structural models with the same evaluated values. Thus, structural models can be obtained by searching for relationship subgraphs representing substructures. Based on the finding, a decision-making subgraph mining algorithm (DmSMA) is proposed to search for subgraphs which potentially belong to structural models. Experiments of SEM implemented by DmSMA are conducted to indicate that searching for decision-making subgraphs is helpful to obtain effective structural models. As shown by the experimental results including two performance metrics, DmSMA performs better than the compared algorithms to solve SEM through mining decision-making subgraphs.

With the development and application of Internet of Things (IoT) technology, IoT has been widely used in agriculture, industry, and urban construction. In the process of building Smart cities, setting up small-scale weather stations based on IoT technology can effectively monitor certain special environments where large weather stations cannot accurately assess and predict short-term extreme weather events. As the summer heat approaches, the number of heatstroke cases is continuously rising. The Wet Bulb Globe Temperature (WBGT) index, which is closely related to heatstroke, provides a simple method for evaluating the thermal work environment and thermal load of workers in hot conditions. In this paper, through adjusting the model structure and moving window, and optimizing the predictive model parameters, an improved Long Short Term Memory (LSTM) algorithm is proposed to forecast WBGT values at future time points: five minutes, thirty minutes, and sixty minutes ahead. The paper also conducts a simple analysis of the daily average performance of WBGT in relation to air humidity. Additionally, it compares dual-input models that include air humidity as input. Through a comparison of four prediction performance evaluation metrics, simple-input LSTM models demonstrate lower error.

Scheduling is significant in improving the production efficiency and reducing delivery delays for manufacturing enterprises. Unlike the flexible job-shop scheduling problem, two special constraints are encountered in real-world power supply manufacturing systems: 1) periodic maintenance and 2) mandatory outsourcing. As the characteristics of these constraints are not considered in existing scheduling algorithms, schedules generated by most existing approaches are not optimal or even conflict with these constraints. In this article, a self-organizing neural scheduler (SoNS) is proposed to overcome this limitation. A long short-term memory encoder is developed to transform the variable-length structural information into fixed-length feature vectors. Moreover, the reinforcement learning model is proposed to automatically select policies for improving candidate schedules. To validate the effectiveness of the proposed algorithm, extensive experiments are conducted on over 300 problem instances. The nonparametric Kruskal-Wallis tests confirm that the proposed algorithm outperforms several state-of-the-art methods in terms of effectiveness and robustness within a limited computational budget. It demonstrates that the proposed SoNS can solve scheduling problems with the periodic maintenance and mandatory outsourcing constraints effectively.

Two-echelon vehicle routing problem (2E-VRP) is an NP-hard combinatorial optimization problem and a basic mathematical model of modern city logistics. While it is difficult to obtain the optimal solution of 2E-VRP, this study finds a breakthrough that the structure of the optimal route planning for 2E-VRP is usually an embedded Hamiltonian graph. In the graph, routes can be drawn in a planar graph as Hamiltonian circuits without intersections. Based on this finding, an embedded Hamiltonian graph-guided heuristic algorithm is proposed to solve 2E-VRP. As a crucial part of the algorithm, an initialization scheme is designed to search for the farthest vertices from each route and insert the rest of the vertices. In the satellite-adjustment process, a dynamic adjustment for satellites scheme is proposed to adjust the state of satellites. The two schemes aim to construct Hamiltonian circuits with few intersections. Experiments have been conducted on 207 instances to demonstrate the effect of the proposed algorithm on solving 2E-VRP. Experimental results show that the proposed algorithm can obtain more solutions of 2E-VRP with significantly smaller objective-function values. Furthermore, the number of intersections in routes generated by the proposed algorithm is much less than those obtained by the compared algorithms. With the use of the two schemes, the embedded Hamiltonian graph-guided heuristic algorithm significantly outperforms the compared algorithms for 2E-VRP.