Wen Sun's research while affiliated with Northwestern Polytechnical University and other places

Edge intelligence has recently attracted great interest from industry and academia, and it greatly improves the processing speed at the edge by moving data and artificial intelligence to the edge of the network. However, edge devices have bottlenecks in battery capacity and computing power, making it challenging to perform computing tasks in dynamic and harsh network environments. Especially in disaster scenarios, edge (rescue) devices are more likely to fail due to unreliable wireless communications and scattered rescue requests, which makes it urgent to explore how to provide low-latency, reliable services through edge collaboration. In this article, we investigate the task offloading mechanism in mobile edge computing networks, aiming to ensure fault tolerance and rapid response of computing services in dynamic and harsh scenarios. Specifically, we design a fault-tolerant distributed task offloading scheme, which minimizes task execution time and system energy consumption through the multi-agent proximal policy optimization algorithm. Furthermore, we introduce logarithmic ratio reward functions and action masking to reduce the impact of different task queue lengths while accelerating model convergence. Numerical results show that the proposed algorithm is suitable for service failure scenarios, effectively meeting the reliability requirements of tasks while simultaneously reducing system energy consumption and processing latency.

The vision of Web 3.0 is to promote decentralized, intelligent, and autonomous Internet by self-learning and self-adaption of user demands. Such Internet evolution is enabled by ubiquitous and low-latency communication and powerful computing, imposing significant challenges on the Web 3.0 architecture and its network orchestration. The successful implementation ofWeb 3.0 relies on dynamic perception and intelligent decision-making, which is difficult to conceive owing to the heterogeneity and dynamics of networks. Digital twins, as an emerging technology, can map the real-time network status and make optimal decisions to enable intelligent low-latency communications. This article introduces a digital twin architecture to achieve networking virtualization and digitalization for Web 3.0. Based on the architecture, the digital twin-empowered low-latency communication scheme is proposed by disseminating tasks to the resource-sufficient infrastructure, while considering the communication cost of deploying digital twins. Illustrated results demonstrate the superiority of digital twins for low-latency communications in Web 3.0.

Terrestrial-satellite networks (TSNs) can provide worldwide users with ubiquitous and seamless network services. Meanwhile, malicious eavesdropping is posing tremendous challenges on secure transmissions of TSNs due to their widescale wireless coverage. In this paper, we propose an aerial bridge scheme to establish secure tunnels for legitimate transmissions in TSNs. With the assistance of unmanned aerial vehicles (UAVs), massive transmission links in TSNs can be secured without impacts on legitimate communications. Owing to the stereo position of UAVs and the directivity of directional antennas, the constructed secure tunnel can significantly relieve confidential information leakage, resulting in the precaution of wiretapping. Moreover, we establish a theoretical model to evaluate the effectiveness of the aerial bridge scheme compared with the ground relay, non-protection, and UAV jammer schemes. Furthermore, we conduct extensive simulations to verify the accuracy of theoretical analysis and present useful insights into the practical deployment by revealing the relationship between the performance and other parameters, such as the antenna beamwidth, flight height and density of UAVs.

Nowadays, researchers have started to conceptualize Metaverse with the vision of constituting a fully immersive, hyper spatiotemporal, and persistent interconnected virtualized world. Such network evolution poses sustainability concerns due to its enabling technologies, such as compute-intensive Artificial Intelligence (AI) and energy-consuming blockchain. Combining distributed learning and blockchain shows great potential to solve the energy efficiency issues in Metaverse through secure resource scheduling and decentralization of computing. However, with the expansion of the Metaverse scale, the increased energy consumption and storage of blockchain are still intolerable. Sharding blockchain becomes a feasible solution to efficiently improve energy efficiency and scalability by dividing blockchain into multiple smaller groups called shards. Toward this end, we have proposed a sustainable Metaverse architecture, combining distributed learning and sharding blockchain to tackle the energy efficiency challenges. The proposed sharding mechanism with incentive achieves the parallelization of computing and storage in Metaverse, while guaranteeing the security and activity of distributed learning. Numerical results show that the proposed framework improves energy efficiency and eases pressure on data storage.

The explosively growth of mobile applications imposes much burden on the current computing networks. Wireless Computing Power Network (WCPN), as an emerging computing architecture, can sense and coordinate computing resources through agile wireless communications, and realize distributed intelligence based on federated learning. However, the mobility and heterogeneity of WCPN nodes typically impact the security (e.g., malicious node disturbance) and efficiency of federated learning in WCPN. In light of this, this paper proposes a provable secure and decentralized federated learning based on blockchain for WCPN, where nodes can freely participate or leave the WCPN federated training without authorization and security threats. Particularly, we design a blockchain with proof-of-accuracy (PoAcc) consensus scheme to deeply integrate with the federated learning procedure, in which high-accuracy local models have the priority of aggregation, thus accelerating the convergence of federated learning and improving the efficiency of WCPN. The proposed PoAcc is proved to be secure as long as the ratio of honest to malicious nodes is above a lower bound. To further meet the security requirement of PoAcc, we then propose an evolutionary game-based incentive scheme that incentivizes honest nodes to participate the WCPN federated learning under malicious node disturbance. Numerical results show that the proposed scheme ensures the consistency and security of federated learning in WCPN, while outperforming the benchmarks in terms of model accuracy and resource consumption.

As a new direction of smart grids, the smart microgrid is a self-sufficient energy system that can generate and distribute energy in limited areas. However, existing work faces issues such as data privacy security, single-power supply mode, and unreasonable scheduling, which bring challenges to the application of smart microgrids. In light of this, we formalize a blockchain-based smart microgrid system, preserving the tracking capability of the system and ensuring the privacy of user data. In addition, we propose an intelligent dispatching scheme, in which meteorological factors are considered in power prediction and a prediction results-based intelligent allocation algorithm is designed. Furthermore, we introduce a credit bidding mechanism, which can make companies participate in the dispatching more fairly and proportionately. Numerical results show that our proposed scheme performs well in terms of prediction results and the cost of intelligent dispatching.

Presents the editorial for this issue of the publication.

Mobile edge computing (MEC) brings computational resources to the edge of network that triggers the paradigm shift of centralized machine learning towards federated learning. Federated learning enables edge nodes to collaboratively train a shared prediction model without sharing data. In MEC, heterogeneous edge nodes may join or leave the training phase during the federated learning process, resulting in slow convergence of dynamic communities and federated learning. In this paper, we propose a fine-grained training strategy for federated learning to accelerate its convergence rate in MEC with dynamic community. Based on multi-agent reinforcement learning, the proposed scheme enables each edge node to adaptively adjust its training strategy (aggregation timing and frequency) according to the network dynamics, while compromising with each other to improve the convergence of federated learning. To further adapt to the dynamic community in MEC, we propose a meta-learning-based scheme where new nodes can learn from other nodes and quickly perform scene migration to further accelerate the convergence of federated learning. Numerical results show that the proposed framework outperforms the benchmarks in terms of convergence speed, learning accuracy, and resource consumption.