2026· IEEE Transactions on Network Science and Engineering· Vol 13, pp. 10847-10862· 0 citations· 68 references
Computer Science
Abstract
A channel knowledge map (CKM) provides location-specific channel priors and can reduce the overhead of real-time channel state information (CSI) acquisition for 6G environment-aware communications. In practice, CKM generation is often constrained by sparse and noisy measurements due to the high cost of wireless data collection. In this paper, we propose PDiff, a physics-informed conditional diffusion framework for CKM generation under sparse observations. Specifically, PDiff incorporates an analytical free-space propagation prior to capture the dominant distance-dependent attenuation trend, and combines it with environmental geometry, observation masks, and sparse observations as structured conditions. These conditional inputs guide the generation process with explicit propagation-aware, environmental, and measurement constraints. To improve inference efficiency, we further develop Prop-Cache, a training-free acceleration mechanism that reuses slowly varying intermediate features across denoising steps to reduce redundant computation during sampling. Experiments on RadioMapSeer demonstrate that PDiff outperforms a wide range of baseline methods for CKM generation.
PACC designs a propagation-aware dissimilarity metric that adapts to line-of-sight and non-line-of-sight propagation conditions, thereby preserving both local neighborhood relationships and the intrinsic geometry of the radio environment.
Channel state information (CSI) acquisition, reconstruction, and prediction are fundamental yet costly tasks in modern MIMO-OFDM wireless systems. Direct coefficient-level prediction of raw CSI is fragile in realistic propagation environments, since small spatial perturbations, local scattering changes, and phase variations can cause large errors in the complex channel domain. However, the underlying wireless propagation field still contains stable and predictable structures that can be exploited across time, frequency, antenna, and carrier dimensions. Motivated by this observation, we propose a JEPA-based field-layer world model (FWM) that learns a shared latent propagation state from multi-resolution CSI observations across the considered carrier bands and predicts its task-relevant evolution in the latent domain. The proposed FWM maps multiple CSI observation resolutions to a shared latent propagation-field space through scale-specific tokenizer heads. A latent prediction backbone is then trained to infer masked or future field states, while an incremental multi-scale alignment strategy allows new observation scales to be incorporated without retraining the entire model from scratch. For downstream reconstruction, the predicted latent field is used as a structured prior and combined with sparse current pilots. Experiments on single-band and cross-band reconstruction demonstrate improved symbol detection and, more notably, substantial beamforming gains despite modest NMSE improvements, indicating that FWM captures task-relevant spatial propagation structure beyond coefficient-wise CSI fitting.
Yuzhi Yang, Brahim Mefgouda, Han Zou et al.· 0 citations
Wireless communication networks are evolving toward extremely large antenna arrays, millimeter-wave and terahertz bands, and dense heterogeneous deployments, all of which increase channel dimensionality and make channel acquisition increasingly costly. Channel knowledge map (CKM) establishes a mapping from geographical locations to channel characteristics, providing location-specific prior information to reduce the overhead of channel acquisition. Most existing CKM research, however, has focused on quasi-static propagation features shaped by quasi-static environmental structures such as buildings and terrain, leaving unaddressed the time-varying channel component introduced by dynamic scatterers, terminal attitude changes, and radio-frequency (RF) impairments. This article presents a new concept of dynamic CKM as a middle layer that links quasi-static environmental priors to physical-layer signal processing by providing time-evolving channel representations. We first introduce the fundamentals of dynamic CKM, clarifying its relationship with the quasi-static CKM and the physical layer. We then survey representative construction methods and discuss how dynamic CKM can support pilot design, interference suppression, and integrated sensing and communications. Finally, we outline key open research directions in the co-design of dynamic CKM construction and physical-layer signal processing. These discussions offer an architectural perspective on the role of dynamic CKM in emerging 6G systems.
Channel knowledge maps (CKMs) or radio maps are a key enabler for AI-native 6G networks, supporting proactive resource allocation, coverage optimization, and environment-aware wireless intelligence. Recent generative approaches have demonstrated improved realism and structural fidelity compared with purely discriminative regression, but often require many iterative sampling steps and incur non-negligible latency in dynamic scenarios. Motivated by the need for fast and high-fidelity CKM construction, we propose a conditional Flow Matching (FM) framework for channel gain map generation from lightweight environment priors. Specifically, our model takes as conditioning inputs (i) a binary/gray-scale building occupancy map and (ii) a transmitter (Tx) location mask, and learns a continuous-time probability flow that transports noise to the target channel gain map. We implement the flow field with a time-conditioned U-Net enhanced by multi-scale context aggregation and attention mechanisms (ASPP + CBAM), improving the model’s capability to capture sharp shadowing boundaries and long-range propagation patterns. At inference, the channel gain map is generated by solving an ODE with a small number of function evaluations, yielding efficient generating while preserving spatial structure. The proposed FM-based CKM constructor provides a promising alternative to diffusion models for workshop settings targeting wireless foundation models and AI-native 6G. The code is avilable at https://github.com/AiBiaoZ/FM-CKM
Fluid antenna systems (FAS) have emerged as a promising paradigm for wireless communications, enabling channel reconfigurability that offers a novel spatial degree of freedom. Nevertheless, efficiently acquiring accurate and high-resolution channel state information (CSI) in FAS remains challenging, primarily due to its dynamic spatial structure and limited coherence time. This paper proposes a novel diffusion framework that takes the partially observed CSI matrix as the terminal state of the Markov chain and operates exclusively on the unobserved ports. Built upon this framework, we design a UNet-based architecture, termed the channel extrapolation UNet (CEUNet), that integrates modified MaxViT (mMaxViT) blocks and residual blocks (ResBlocks) to jointly capture local and global channel dependencies for accurate CSI extrapolation. Extensive experiments on the Jakes’ channel model are conducted to evaluate CEUNet. Numerical results show that CEUNet consistently outperforms state-of-the-art deep learning models in estimation accuracy across all signal-to-noise ratios and observation ratios, even with only two sampling steps. Furthermore, a comprehensive complexity analysis is conducted to compare the computational efficiency of CEUNet with that of the baseline models, while ablation studies are carried out to quantitatively evaluate the contribution of each component integrated into the proposed CEUNet.
Xue-Feng Wang, Yu-Hang Li, Yang Lu et al.· IEEE Transactions on Wireles...· 0 citations
RadioTrace is proposed, a novel RM estimation framework without deployment-time fine-tuning that tightly integrates sparse RSS measurements with a frozen pre-trained diffusion prior and achieves competitive performance with state-of-the-art learning-based methods under random sampling, and maintains strong reconstruction quality under restricted-area sampling.
Liu Yang, Qiang Li, Zhuo Cao et al.· IEEE Transactions on Wireles...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
