Multi-Sensor Fusion and 3D Digital Twin Modeling Technologies, Collaborative Industrial Artificial Intelligence-based Internet of Things Factory and Mobile Edge Computing Networks, and Context-Aware Augmented Reality and Machine Learning-based Production Planning Systems for Autonomous Manufacturing Plants in the Virtual Environment of the Metaverse

Anomaly traffic detection offers essential technical support for securing Mobile Edge Computing (MEC) networks. The emerging Large Model (LM) has attracted much attention for their excellent data generation and processing capabilities, but it is difficult to deploy LM-based detection models in resource-constrained MEC networks. Existing solutions usually compress large models into tiny ones, but they tend to be impacted by data drift, resulting in decreased detection accuracy. To address this key challenge, we propose CL4Det, a novel multi-model anomaly traffic detection framework with LM-powered continuous learning, where the tiny models deployed in MEC networks can achieve the desired performance comparable to the large models via continuous retraining. Specifically, CL4Det periodically evaluates the model performance degradation caused by data drift in MEC networks and decides whether to generate retraining tasks and their configurations. Meanwhile, CL4Det schedules all traffic detection and retraining tasks with proper resource allocation, aiming to ensure real-time detection and maximize model accuracy. A case study with real-world traffic datasets verifies the effectiveness and superiority of CL4Det. Finally, we outline the challenges and future directions to fully exploit the collaborative potentials of MEC networks and LM in anomaly traffic detection.

To unveil the hidden value in the datasets of user equipments (UEs) while preserving user privacy, federated learning (FL) is emerging as a promising technique to train a machine learning model using the datasets of UEs locally without uploading the datasets to a central location. Customers require to train machine learning models based on different datasets of UEs, through issuing FL requests that are implemented by FL services in a mobile edge computing (MEC) network. A key challenge of enabling FL in MEC networks is how to minimize the energy consumption of implementing FL requests while guaranteeing the accuracy of machine learning models, given that the availabilities of UEs usually are uncertain. In this paper, we investigate the problem of energy minimization for FL in an MEC network with uncertain availabilities of UEs. We first consider the energy minimization problem for a single FL request in an MEC network. We then propose a novel optimization framework for the problem with a single FL request, which consists of (1) an online learning algorithm with a bounded regret for the UE selection, by considering various contexts (side information) that influence energy consumption; and (2) an approximation algorithm with an approximation ratio for the aggregator placement for a single FL request. We thirdly deal with the problem with multiple FL requests, for which we devise an online learning algorithm with a bounded regret. We finally evaluate the performance of the proposed algorithms by extensive experiments. Experimental results show that the proposed algorithms outperform their counterparts by reducing at least 13% of the total energy consumption while achieving the same accuracy.

Nowadays, mobile application services face the challenges of high speed, low latency and high reliability. The combination of digital twin (DT) technology and mobile edge computing (MEC) network can effectively solve these challenges. DT technology can help MEC network monitor and predict the network states. In this paper, we propose a DT-aided MEC network scenario with deep neural network (DNN) inference as the computing task of end devices (EDs). ED can offload part of DNN layers to MEC server. To allocate communication resources, we propose an algorithm based on asynchronous advantage actor-critic (A3C), which manages the transmission power and channel selection of EDs. Since DNN inference is continuous in real scenes, we consider the continuous DNN inference tasks. We convert the DNN optimal partition point solving problem to a min st-cut problem, and propose a graph theory based DNN optimal partition point solving algorithm to minimize the inference latency. Simulation results show that the proposed algorithm can effectively reduce the inference latency. Compared with actor-critic (AC) and deep Q network (DQN), the proposed algorithm has faster convergence speed and better convergence value. Compared with the traditional one-time DNN model partition algorithm, the proposed algorithm is more suitable for DNN continuous task arrival scenario.

This paper investigates the computation offloading problem in mobile edge computing (MEC) networks with dynamic weighted tasks. We aim to minimize the system utility of the MEC network by jointly optimizing the offloading decision and bandwidth allocation problems. The optimization of joint offloading decisions and bandwidth allocation is formulated as a mixed-integer programming (MIP) problem. In general, the problem can be efficiently generated by deep learning-based algorithms for offloading decisions and then solved by using traditional optimization methods. However, these methods are weakly adaptive to new environments and require a large number of training samples to retrain the deep learning model once the environment changes. To overcome this weakness, in this paper, we propose a deep supervised learning-based computational offloading (DSLO) algorithm for dynamic computational tasks in MEC networks. We further introduce batch normalization to speed up the model convergence process and improve the robustness of the model. Numerical results show that DSLO only requires a few training samples and can quickly adapt to new MEC scenarios. Specifically, it can achieve normalized system utility by using only four training samples per MEC scenario. Therefore, DSLO enables the fast deployment of computation offloading algorithms in future MEC networks.

Mobile edge computing (MEC) networks have been recently adopted to accommodate the fast-growing number of mobile devices performing complicated tasks with limited hardware capability. Recently, edge nodes with communication, computation, and caching capacities are starting to be deployed in MEC networks. Due to the physical separation of these resources, efficient coordination and scheduling are important for efficient resource utilization and optimal network performance. In this paper, we study mobility load balancing for communication, computation, and caching-enabled heterogeneous MEC networks. Specifically, we propose to tackle this problem via a multi-agent deep reinforcement learning-based framework. Users served by overloaded edge nodes are handed over to less loaded ones, to minimize the load in the most loaded base station in the network. In this framework, the handover decision for each user is made based on the user’s own observation which comprises the user’s task at hand and the load status of the MEC network. Simulation results show that our proposed multi-agent deep reinforcement learning-based approach can reduce the time-average maximum load by up to 30% and the end-to-end delay by 50% compared to baseline algorithms.

Collaborative computation offloading and wireless charging scheduling in multi-UAV-assisted MEC networks: A TD3-based approach

Unmanned aerial vehicle (UAV)-assisted relaying and mobile edge computing (MEC) networks is a popular and promising technology to provide high-quality computation service to ground users (GUs). However, prior works on UAV-assisted relaying and MEC networks do not consider the complicated channel conditions in urban environment. Furthermore, the optimization of computation efficiency, defined as the ratio of computation resources (in terms of CPU frequency) and energy consumption, is not studied in prior works. In this work, we consider an UAV-assisted relaying and MEC networks composed of GUs, two MEC servers carried by one rotary-wing UAV and one base station (BS), respectively. Meanwhile, we consider the probabilistic Line-of-Sight (LoS) channel model and the Rician fading model in urban environments to make the channel model more practical and accurate to urban environments. Further, we aim to solve the maximization problem of computation efficiency by jointly optimizing computation resources, computation offloading, bandwidth and UAV trajectory. For the nonconvex formulated problem, we proposed an algorithm based on the Dinkelbachs method, the block coordinate descent (BCD) method and successive convex approximate (SCA) technique. Numerical results demonstrate that the proposed scheme can efficiently improve the computation efficiency compared to other traditional schemes in the practical simulation environment.

To support the application of IoT and smart city, high data-rate wireless transmission is required. To meet the demand of high data-rate, the techniques of multiple antennas and mobile edge computing (MEC) networks have been proposed in order to enhance the data transmission rate significantly. However, there still exist lots of challenges array signal processing assisted MEC networks. In this paper, we propose an intelligent framework of offloading strategy for MEC networks assisted by array signal processing, where one user with multiple antennas has some computational tasks. These tasks can be computed by the user itself which however has limited computational capability, or computed by the near-by computational access points (CAPs) which has a powerful computational capability at the cost of wireless transmission. We consider the system cost by jointly taking into account the computational price, the energy consumption and the latency. By minimizing the system cost, we propose an intelligent offloading strategy based on ant colony optimization (ACO) algorithm, where the ants randomly visit the CAPs in order to obtain the final results. To further enhance the MEC network performance, the array signal processing is utilized at the user, where either the maximum ratio transmission (MRT) or selection combining (SC) is used to assist the data transmission from the user to CAPs. Simulation results with MRT and SC are finally demonstrated to verify the effectiveness of the proposed ACO-based offloading strategy and array signal processing schemes.

Mobile edge computing (MEC) networks can provide a variety of services for different applications. End-to-end performance analysis of these services serves as a benchmark for the efficient planning of network resource allocation and routing strategies. In this paper, we propose a performance analysis framework for the end-to-end data-flow in MEC networks based on stochastic network calculus (SNC). Due to the random nature of routing in the MEC networks, we introduce a probability parameter set in our proposed analysis model to characterize this randomness into our derived expressions. Taking actual communication scenarios into consideration, we analyze the end-to-end performance of video with the interference with voice over internet protocol (VoIP) and file transfer protocol (FTP). For scheduling of these network data-flows, we consider the preemptive priority scheduling scheme. Based on the arrival processes of the video-flow, the effect of interference on its performances and the service capacity of each node in the MEC network, we derive closed-form expression for showing the relationship between delay upper bound and violation probability of the video-flow. Simulation and analytical results show that delay performances of the video-flow is influenced by the number of hops in the network and the random probability parameters of interference-flow.

To support future 6G mobile applications, the mobile edge computing (MEC) network needs to be jointly optimized for computing, pushing, and caching to reduce transmission load and computation cost. To achieve this, we propose a framework based on deep reinforcement learning that enables the dynamic orchestration of these three activities for the MEC network. The framework can implicitly predict user future requests using deep networks and push or cache the appropriate content to enhance performance. To address the curse of dimensionality resulting from considering three activities collectively, we adopt the soft actor-critic reinforcement learning in continuous space and design the action quantization and correction specifically to fit the discrete optimization problem. We conduct simulations in a single-user single-server MEC network setting and demonstrate that the proposed framework effectively decreases both transmission load and computing cost under various configurations of cache size and tolerable service delay.

Resource allocation in RISs-assisted UAV-enabled MEC network with computation capacity improvement

Attention mechanism enhanced LSTM networks for latency prediction in deterministic MEC networks

With the development of 6G, the rapidly increasing number of smart devices deployed in the Industrial Internet of Things (IIoT) environment has been witnessed. The radio environment is showing a trend of complexity, and spectrum conflicts are becoming increasingly acute. User equipment (UE) can accurately sense and utilize spectrum resources through radio map (RM). However, the construction and dissemination of RM incur a heavy computational burden and large dissemination delay, which limit the real-time sensing of spatial spectrum situations. In this paper, we propose an RM construction and dissemination method based on deep reinforcement learning (DRL) in the context of mobile edge computing (MEC) networks. We formulate the dissemination modes selection and resource allocation problems during RM construction and dissemination as a mixed-integer nonlinear programming problem. Then, we propose an actor-critic-based joint offloading and resource allocation (ACJORA) algorithm for intelligent scheduling of computational offloading and resource allocation. We design a novel weighted loss function for the actor network, which combines the discrete actions for offloading decisions and the continuous actions for resource allocation. And the simulation results show that the proposed algorithm can reduce the cost of dissemination by optimizing the offloading strategies and resources, which is more applicable for real-time RM applications in MEC networks.

Using Unmanned aerial vehicles (UAVs) to assist mobile edge computing (MEC) network is a promising solution to provide flexible and low-latency computing service for resource limited user equipments (UEs). However, the computing resources that one UAV can provide are often limited and cannot provide computing services for massive mobile users, thus limiting the application of this technology. So, a novel multi-UAV-assisted MEC network is proposed in this paper. The optimization problem is formulated with the aim to make full use of network's computing resources to reduce the number of failed tasks and energy consumption. To solve this challenging problem, a novel solution is proposed. First, we use a swarm intelligence algorithm to investigate the deployment of UAVs. Second, we offer an efficient matching algorithm to explore the tasks assignments under the given deployment of UAVs. The simulation results show that the proposed solution can effectively reduce the number of failed tasks and energy consumption.

ABSTRACTConsidering the rapid growth in user count and increasing demand for higher data rates, we need to optimize network strategies to accommodate more users and increase the network throughput. Therefore, this work aims to accommodate maximum IoT nodes and increase the network's throughput simultaneously by optimizing the IoT node association and power allocation in the digital twin (DT)‐assisted mobile edge computing (MEC) network. The DT of each cloudlet is considered here which helps to optimize the power allocation and IoT node association. The DT technology helps make more accurate and optimized decisions in the MEC network by creating real‐time digital representations of physical objects. This work formulates the optimization problem as a mixed integer nonlinear programming problem. To solve the proposed problem, the outer approximation algorithm is used due to its lesser complexity. The proposed algorithm's convergence, effectiveness, and lesser complexity leads to ‐optimal solution = , achieved using standard problem solvers. The simulation results in terms of associated IoT nodes and the network's throughput demonstrate the effectiveness of the proposed approach.