The Industrial Internet of things (IIoT), which consists of massive IoT devices and wireless access points in industrial infrastructures to acquire intelligent services, has been considered as a vital physical information platform for implementing Industry 4.0. Further, mobile edge computing (MEC) has brought an opportunity to accelerate the development of IIoT. However, the existing MEC methods may not be directly used for IIoT scenarios due to the large size of IIoT devices and the characteristics of the applications, as well as the limited and heterogeneous resources of edge servers. In view of this, the computation offloading and resource allocation are formulated as a multi-objective optimization problem, and an end-edge-cloud collaborative intelligent optimization method is devised in this paper. Comprehensive experiments and evaluations are carried out to prove the effectiveness and efficiency of our proposed method with regard to the energy consumption and time consumption of IIoT devices, as well as resource utilization and load balancing of edge servers.

Internet-of-Things (IoT) has played a critical role in developing sustainable smart cities and emerging numerous latency-sensitive IoT applications. Mobile edge computing (MEC) federation has the capability to incorporate a transparent resource management approach, which enables the sharing and utilization of MEC services from edge infrastructure providers (EIPs) and provides agile access services to mobile devices (MDs). In this paper, we investigate the joint optimization problem of computation offloading, task migration, and resource allocation in the MEC federation. The objective is to minimize the weighted sum of latency and energy consumption while maintaining load balancing under the constraint of the long-term migration cost budget of EIPs. To address the problem, we decompose it into two sub-problems: 1) the MDs clustering sub-problem and 2) the sub-problem of joint computation offloading, task migration, and resource allocation. First, an MDs clustering matching (MDCM) algorithm is proposed to cluster the MDs in edge servers (ESs) according to the differences in channel gains. Afterward, the second sub-problem is simplified by the Lyapunov optimization technique, and then we propose a Transformer-based mobility prediction model and a decentralized deep deterministic policy gradient (DDPG)-based framework to solve it. Extensive simulation results demonstrate the cost-efficiency of the proposed algorithm.

Mobile edge computing is one of the key enabling technologies of smart industry solutions, providing agile and ubiquitous services for mobile devices (MDs) through offloading latency-critical tasks to edge service providers. However, it is challenging to make optimal decisions of computation offloading and resource allocation while ensuring the privacy and information security of MDs. Consequently, we consider a new vision of Digital Twin (DT) empowered edge networks where the optimization problem is formulated as a two-stage incentive mechanism. Firstly, the resource allocation strategy is determined by the interaction among DTs according to the credit-based incentives. Afterwards, a distributed incentive mechanism based on the Stackelberg-based alternating direction method of multipliers is opted to obtain the optimal offloading and privacy investment strategies in parallel. Numerical results show that the proposed two-stage incentive mechanism achieves effective resource allocation and computation offloading while simultaneously improving the privacy and information security of MDs.

With the significant increase in the number of motor vehicles, road-related issues such as traffic congestion and accidents have also escalated. The development of an accurate and efficient traffic flow forecasting model is essential for helping car owners plan their journeys. Despite advancements in forecasting models, there are three remaining issues: (i) failing to effectively use cyclical data; (ii) failing to adequately capture spatial dependencies; and (iii) high time complexity and memory usage. To tackle the aforementioned challenges, we present a novel Spatial-Temporal Graph Attention Gated Recurrent Transformer Network (STGAGRTN) for traffic flow forecasting. Specifically, the use of a Spatial Transformer module allows for the extraction of dynamic spatial dependencies among individual nodes, going beyond the limitation of only considering neighboring nodes. Subsequently, we propose a Temporal Transformer to extract periodic information from traffic data and capture long-term dependencies. Additionally, we utilize two additional classical techniques to complement the aforementioned modules for extracting characteristics. By incorporating comprehensive spatial-temporal characteristics into our model, we can accurately predict multiple nodes simultaneously. Finally, we have successfully optimized the computational complexity of the Transformer module from O(n2) to O(nlogn). Our model has undergone extensive testing on four authentic datasets, providing compelling evidence of its superior predictive capabilities.

With the advent of light and economical Unmanned Vehicles (UAVs), the Internet of Things (IoT) in air is gaining more popularity. However, IoT in air has its own set of requirements and challenges. It is unwise to upload legacy IoT applications to aerial computing networks. For instance, aerial computing in resource constraint UAVs demands energy-efficient solutions. Fortunately, mobile edge computing (MEC) can assist aerial computing by offloading partial or all applications to edge servers (ESs) in MEC. Nevertheless, ESs are subjected to finite resources, and there is a certain probability of failure, and the application in aerial computing is for high-reliability demands. Given the above issue, we investigate computation offloading for delay-sensitive applications under reliability constraints in MEC-enabled aerial computing network where the delay-sensitive applications are represented as scientific workflow applications. Technically, a two-phase reliability-aware computation offloading approach is proposed. More specifically, in the first stage, a multi-objective reliability-aware energy-efficient computation offloading strategy is proposed for the scientific workflow application. Secondly, an improved lazy shadowing scheme is proposed to enhance reliability, energy efficiency, and load balancing. Extensive experiments have been conducted to show the effectiveness and superiority of our proposed solution under different situations.

Industry 5.0 facilitates the intelligent upgrade of smart factories in Industrial Internet of Things (IIoT), and also introduces a plethora of data processing challenges. Mobile edge computing offloads data to edge servers for processing, easing the data processing pressure and reducing system cost. However, smart factories contain numerous sensitive information, and offloading them to edge servers directly may pose a risk of data leakage. To address these challenges, we investigate a localedge collaborative smart factory system. Specifically, we firstly model the tasks as a directed acyclic graph, and formulate the offloading problem as a Markov decision process, considering the optimization of latency, energy consumption and the number of overtime tasks. Then, we propose a security-aware computation offloading method using federated reinforcement learning in IIoT, named SCOF. SCOF employs federated learning, keeping data for local computation and uploading model parameters to edge servers for aggregation. The data transmission passes through an artificial noise channel to protect against eavesdropping. Meanwhile, SCOF utilizes differential privacy to protect data security and employs deep reinforcement learning for selecting near-optimal offloading decisions. Finally, abundant experiments are conducted under a real dataset. The results show that SCOF has better perfomance than the state-of-the-art baseline algorithms.