The rapid advancement of mobile networks highlights the limitations of traditional network planning and optimization methods, particularly in modeling, evaluation, and application. Network Digital Twins, which simulate networks in the digital domain for evaluation, offer a solution to these challenges. This concept is further enhanced by generative AI technology, which promises more efficient and accurate AI-driven data generation for network simulation and optimization. This survey provides insights into generative AI-empowered network digital twins. We begin by outlining the architecture of a network digital twin, which encompasses both digital and physical domains. This architecture involves four key steps: data processing and network monitoring, digital replication and network simulation, designing and training network optimizers, Sim2Real, and network control. Next, we systematically discuss the related studies in each step and make a detailed taxonomy of the problem studied, the methods used, and the key designs leveraged. Each step is examined with a focus on the role of generative AI, from estimating missing data and simulating network behaviors to designing control strategies and bridging the gap between digital and physical domains. Finally, we discuss the open issues and challenges of generative AI-based network digital twins.
23 July 2024 in IEEE Transactions on Wireless Communications
Accurately and efficiently modeling wireless channels, especially estimating path loss value, is crucial to wireless system design and performance optimization. This paper proposes a knowledge and data jointly driven path loss estimation method named PEFNet. PEFNet can predict the total electric field based on its mathematical relationship with the incident field by introducing the Volume Integration Equation into the loss function and scenario environmental information as input. Then, we let PEFNet learn in a supervised manner to compensate for residual error against measured data for refinement. We conduct extensive experiments on two publicly available path loss datasets, RadioMapSeer and RSRPSet, to exhibit the superiority of PEFNet over other state-of-the-art baselines. By comparing overall estimation performance, carrying out ablation study, testing estimation efficiency, and evaluating generalization ability, the results prove that PEFNet is an accurate and efficient method for estimating path loss.
Complex system simulation has been playing an irreplaceable role in understanding, predicting, and controlling diverse complex systems. In the past few decades, the multi-scale simulation technique has drawn increasing attention for its remarkable ability to overcome the challenges of complex system simulation with unknown mechanisms and expensive computational costs. In this survey, we will systematically review the literature on multi-scale simulation of complex systems from the perspective of knowledge and data. First, we will present background knowledge about simulating complex systems and the scales in complex systems. Then, we divide the main objectives of multi-scale modeling and simulation into five categories by considering scenarios with clear scale and scenarios with unclear scale, respectively. After summarizing the general methods for multi-scale simulation based on the clues of knowledge and data, we introduce the adopted methods to achieve different objectives. Finally, we introduce the applications of multi-scale simulation in typical matter systems and social systems.
27 September 2024 in IEEE Transactions on Wireless Communications
With the exponential growth of mobile users, ensuring high-quality network coverage has become paramount. Large-scale mobile networks consist of numerous base stations (BSs), each with adjustable parameters such as angles and beam widths. Automatically optimizing network coverage can be difficult due to environmental factors and the interdependence of the adjustable parameters. Due to the inherent uncertainties and unpredictable nature of large-scale wireless networks, traditional methods such as heuristics and meta-heuristics lack the adaptability and scalability required to cope with their dynamic environment. To address these challenges, we propose utilizing digital twin and reinforcement learning (RL) techniques within mobile networks characterized by multiple collaborating agents. We initially introduce DT-SimNet, a digital twin-enabled mobile network simulator to facilitate optimization evaluation. DT-SimNet can efficiently simulate communication behaviors of network elements within a complex environment while revealing user mobility patterns. Moreover, to address challenges arising from multifaceted relationships among users, BSs, and the parameters across BSs, we introduce an innovative strategy named Optimized Multi-Agent Proximal Policy Optimization with Self-supervised Prediction (OMAPPO-SSP). Compared to MAPPO, which leads to limited applicability and inferior performance due to the dynamic characteristics of 5G networks, this approach leverages network structure optimization and a self-supervised prediction mechanism, employing multi-agent reinforcement learning (MARL) principles to enhance efficiency. By harnessing collaborative neural networks, OMAPPO-SSP facilitates the explicit learning of behavioral interactions among all BSs, enabling effective decision-making in environments characterized by intricate spatial relationships, dynamic user behaviors, and diverse interactions. Extensive experiments are conducted to validate the efficiency and effectiveness of the OMAPPO-SSP. Within the target area, OMAPPO-SSP achieves a coverage ratio of 94.66% and an average throughput of 89746 bits per second (bps), demonstrating significant improvements compared to competing methods.
28 March 2024 in ACM Transactions on Intelligent Systems and Technology
Vessel trajectory prediction is the key to maritime applications such as traffic surveillance, collision avoidance, anomaly detection, and so on. Making predictions more precisely requires a better understanding of the moving trend for a particular vessel since the movement is affected by multiple factors like marine environment, vessel type, and vessel behavior. In this paper, we propose a model named VesNet, based on the attentional seq2seq framework, to predict vessel future movement sequence by observing the current trajectory. Firstly, we extract the route patterns from the raw AIS data during preprocessing. Then, we design a multi-task learning structure to learn how to implement route pattern classification and vessel trajectory prediction simultaneously. By comparing with representative baseline models, we find that our VesNet has the best performance in terms of long-term prediction precision. Additionally, VesNet can recognize the route pattern by capturing the implicit moving characteristics. The experimental results prove that the proposed multi-task learning assists the vessel trajectory prediction mission.
As a result of their high mobility and reduced cost, Unmanned Aerial Vehicles (UAVs) have been found to be a promising tool in wireless networks. A UAV can perform the role of a base station as well as a mobile relay, connecting distant ground terminals. In this paper, we dispatch a UAV to a disaster area to help relay information for victims. We involve a bandwidth efficient technique called the Dual-Sampling (DS) method when planning the UAV flight trajectory, trying to maximize the data transmission throughput. We propose an iterative algorithm for solving this problem. The victim bandwidth scheduling and the UAV trajectory are alternately optimized in each iteration, meanwhile a power balance mechanism is implemented in the algorithm to ensure the proper functioning of the DS method. We compare the results of the DS-enabled scheme with two non-DS schemes, namely a fair bandwidth allocation scheme and a bandwidth contention scheme. The DS scheme outperforms the other two non-DS schemes regarding max-min average data rate among all the ground victims. Furthermore, we derive the theoretical optimal performance of the DS scheme for a given scenario, and find that the proposed approach can be regarded as a general method to solve this optimization problem. We also observe that the optimal UAV trajectory for the DS scheme is quite different from that of the non-DS bandwidth contention scheme.