Search

Network digital twin is a key enabler for the human-centric wireless metaverse, requiring fine-grained replication, high-fidelity screen rendering, and the integration of emerging intelligent technologies. However, existing frameworks for the network digital twin overlook the integration of human-centric features within the metaverse and the importance of asynchronous data collection, both of which are indispensable for actualizing the metaverse and attaining self-maintenance capabilities. To address this issue, in this article, we propose a human-centric framework and a self-maintained mechanism for the network digital twin, utilizing continuous prediction and error tolerance to enhance the performance of DT decision-making. Specifically, by considering the interplay among different components, we present a human-centric framework for the network digital twin, comprising a device twin layer, a network twin layer, an artificial intelligence service layer, and a user intent layer. In consideration of asynchronous information, we propose a self-maintained mechanism facilitated by two key capabilities: error tolerance and continuous prediction. Furthermore, we conduct a resource allocation experiment to validate the efficiency of the proposed framework with request prediction and robust optimization. The results demonstrate that the framework can reduce the average latency compared to other baseline schemes, thus improving the user experience of wireless metaverse.

Urban sensing encourages the incredibly quick advancement of digitalization, intelligence, and ubiquitous perception, accelerating the construction of the metaverse. Various sensors construct the sensing network to capture human activities for the human-centered metaverse. However, effective management of ubiquitous urban sensing with various attributes is a challenge. In this article, we propose a virtual Internet of Things (VIoT) enabled by digital twin (DT) for building the metaverse. Specifically, we introduce an architecture of the VIoT, including a policy sensing layer, a 6G edge-cloud collaboration layer, a DT layer, and a user-friendly terminal layer. Furthermore, to address the sensing scheduling issue in the VIoT, we formulate a sensing profit maximization problem by considering the sensing coverage, data utility, and energy cost attributes of visual sensors and fabric sensors. To tackle this problem efficiently, we design a sensing scheduling policy based on the soft actor–critic (SSP-SAC) algorithm. The simulation results demonstrate that compared to the baseline schemes, the SSP-SAC scheme can significantly improve the sensing profit in diverse situations, indicating that the VIoT can provide an effective urban sensing policy.

Digital twin (DT)-assisted mobile edge network can achieve energy-efficient task offloading by optimizing the decision-making in real time. Although many DT-assisted task offloading solutions in mobile edge networks have been designed, stochastic asynchronizations between the DTs and physical entities are still ignored. In this paper, we investigate a task offloading problem in a DT-assisted URLLC-enabled mobile edge network which considered the uncertain deviation between DT estimated values and physical actual values. Specifically, we formulate a latency and energy consumption minimization problem by optimizing task offloading, resource allocation, and power management. To solve this problem, we propose a DT-assisted robust task offloading scheme (DTRTO) based on learning composed of decision and deviation networks. The deviation network predicts the worst-case deviations based on the pre-decision, and the decision network optimize the decision considered the worst-case deviation. The simulation results show that, compared to the baseline algorithms, the DTRTO scheme can realize low latency and energy consumption in task offloading while maintaining high robustness.

Sensing and computing based on intelligent fabrics can meet the ultra-reliable and low-latency communication (URLLC) needs of sixth-generation wireless (6G) by integrating sensing units into fabric fibers to perceive user data. Although some researchers have designed sensing or computing solutions, such solutions have not been well explored. In this paper, we consider the joint sensing adaptation and model placement in a 6G fabric space. We first propose an intelligent-fiber-driven 6G fabric computing network to minimize acquisition latency while ensuring accuracy. Then, we formulate an optimization model that takes the fabric sampling rate, sampling density, and model placement as variables. To solve the model, we propose an effective learning algorithm based on deep reinforcement learning. That is, by transforming the optimization problem into a state space, action space, and reward function, we design an optimal sensing and placement scheme. The simulation results show that our proposed scheme can achieve optimal sensing and computing compared with several baseline algorithms.

The significant achievements have been made in crowd detection and tracking due to the advancement of artificial intelligence in the autonomous driving. However, the image-based methods have strict requirements for the collection conditions of video, and the development of the new generation of flexible fabrics has become potential sensors to perceive context. In this paper, an intelligent fabric space enabled by multi-sensing sensors is established to track the motion objects. We propose a behavior analysis pipeline including the modules of data preparation, trajectory coupling, motion scenario segmentation, and motion pattern measurement to capture the crowd information from micro-level and macro-level over the intelligent fabric space. After making preprocess for the multi-sensing data, a coupling mechanism is formulated to fuse the video-based trajectory and fabric-based trajectory. And an automatic motion scenario segmentation model divides the surrounding scenario into main-crowd, sub-crowd, and background according to the motion behavior. Further, we define measurement metrics to analyze the motion pattern for the different crowds. Extensive experiments prove that our proposed methods effectively fuse multiple trajectories and realize the crowd segmentation and the motion description. This will greatly help autonomous vehicles and control system perceive the surrounding pedestrians and the environment to make precise driving decisions.

In this paper, we propose a label-less learning for emotion cognition (LLEC) to achieve the utilization of a large amount of unlabeled data. We first inspect the unlabeled data from two perspectives, i.e., the feature layer and the decision layer. By utilizing the similarity model and the entropy model, this paper presents a hybrid label-less learning that can automatically label data without human intervention. Then, we design an enhanced hybrid label-less learning to purify the automatic labeled data. To further improve the accuracy of emotion detection model and increase the utilization of unlabeled data, we apply enhanced hybrid label-less learning for multimodal unlabeled emotion data. Finally, we build a real-world test bed to evaluate the LLEC algorithm. The experimental results show that the LLEC algorithm can improve the accuracy of emotion detection significantly. [ABSTRACT FROM AUTHOR]

Caching content on mobile devices reduces not only the transmission of backhaul links but also the latency of content acquisition. However, in the existing caching schemes, the joint effect of the caching-aware indicator of users and content dimensions on the caching strategy is not considered. Thus, how to learn fine-grained caching- aware indicators and design caching schemes are still challenging issues. In order to solve these problems, in this article, we first propose the cognitive caching architecture and give the fine-grained caching-aware indicators metric. Then we design a cognitive caching scheme that includes what to do in cognitive caching and how to do cognitive caching. Finally, experimental results show that the proposed cognitive caching scheme is superior to other caching schemes in terms of learning regret and caching cost.

From a traditional point of view, the value of information does not change during transmission. The Shannon information theory considers information transmission as a statistical phenomenon for measuring the communication channel capacity. However, in modern communication systems, information is spontaneously embedded with a cognitive link during the transmission process, which requires a new measurement that can incorporate continuously changing information values. In this paper, we introduce the concept of cognitive information value and a method of measuring such information. We first describe the characteristics of cognitive information followed by an introduction of the concept of cognitive information in measuring information popularity. The new measurement is based on the mailbox principle in the information value chain. This is achieved by encapsulating the information as a mailbox for transmission where the cognition is continuously implemented during the transmission process. Finally, we set up a cognitive communication system based on a combination of the traditional communication system and cognitive computing. Experimental results attest to the impact of incorporating cognitive value in the performance of 5G networks. [ABSTRACT FROM AUTHOR]

With the development of recent innovative applications (e.g., augmented reality, natural language processing, and various cognitive applications), more and more computation-intensive and rich-media tasks are delay-sensitive. Edge cloud computing is expected to be an effective solution to meet the demand for low latency. By the use of content offloading and/or computation offloading, users' quality of experience is improved with shorter delay. Compared to existing edge computing solutions, this article introduces a new concept of computing task caching and gives the optimal computing task caching policy. Furthermore, joint optimization of computation, caching, and communication on the edge cloud, dubbed Edge-CoCaCo, is proposed. Then we give the solution to that optimization problem. Finally, the simulation experimental results show that compared to the other schemes, Edge-CoCaCo has shorter delay.

With the popularization of wearable devices, designing a network architecture that can meet the latency requirements of different wearable devices and can also efficiently utilize network communication, storage, and computation resources will be a challenging problem. In this article, we first propose a new 5G wearable network based on 5G ultra-dense cellular network and mobile edge computing, to meet the access and latency requirements of wearable devices. Then we use network slicing technology in the proposed 5G wearable network to enhance the network resource sharing and energy-efficient utilization. In addition, based on the service cognitive engine and network cognitive engine deployed in the network, we introduce data-driven network slicing management to adjust the network resources in accordance with the wearable service dynamics. Finally, some challenges and open issues are discussed.

Recently, there has been increasing interest of deploying computation-intensive and rich-media applications on mobile devices, and ultra-low latency has become an important requirement to achieve high user QoE. However, conventional mobile communication systems are incapable of providing considerable communication and computation resources to support low latency. Although 5G is expected to effectively increase communication capacity, it is difficult to achieve ultra-low end-to-end delay for the ever growing number of cognitive applications. To address this issue, this article first proposes a novel network architecture using a resource cognitive engine and data engine. The resource cognitive intelligence, based on the learning of network contexts, is aimed at a global view of computing, caching, and communication resources in the network. The data cognitive intelligence, based on data analytics, is critical for the provisioning of personalized and smart services toward specific domains. Then we introduce an optimal caching strategy for the small-cell cloud and the macro-cell cloud. Experimental results demonstrate the effectiveness of the proposed caching strategy, and its latency is lower than that of the two conventional approaches, that is, the popular caching strategy and the greedy caching strategy.

With the advent of the Internet of Everything, people can easily interact with their environments immersively. The idea of pervasive computing is becoming a reality, but due to the inconvenience of carrying silicon-based entities and a lack of fine-grained sensing capabilities for human-computer interaction, it is difficult to ensure comfort, esthetics, and privacy in smart spaces. Motivated by the rapid developments in intelligent fabric technology in the post-Moore era, we propose a novel computing approach that creates a paradigm shift driven by fabric computing and advocate a new concept of non-chip sensing in living spaces. We discuss the core notion and benefits of fabric computing, including its implementation, challenges, and future research opportunities.

With the rapid growth of traffic and power consumption in information and communication technology industry for decades, improving energy efficiency has become a challenging issue in recent years. Especially, the pervasive access to Internet via mobile devices will cause wireless traffic volume increment by 1000+ times in near future, which is expected to be carried by the fifth generation ultradense cellular network. Following this trend, the core network where optical fibers are deployed to deliver aggregated traffic needs upgrading to accommodate the increasing traffic volume. To match with the traffic growth rate, we should conduct efficient network planning over multiple time periods. Moreover, considering the heterogeneity in the bandwidth requirements among various network services, flexible mixed line rate scheme is adopted in network provisioning. In this paper, we study the long‐term multiperiod planning of optical core network by considering the traffic growth with the objective of high energy‐efficiency. Three planning strategies, say All‐period, Incremental, and End‐of‐Life, respectively, are studied and formulated as mixed integer linear programming models with the objective to minimize power consumption of optical core network. Given the estimation on the reduction of power consumed by various network devices, we can deploy network devices flexibly in each period through the optimization models. Performance of the proposed models is also evaluated and compared via case studies. Long‐term multiperiod planning of optical core network is studied by considering the traffic growth with the objective of high energy efficiency. Three planning strategies are studied and formulated as mixed integer linear programming models with the objective to minimize power consumption of optical core network. Deploying network devices flexibly in each period through the optimization models by giving the estimation on the reduction of power consumed by various network devices.