arXiv subjects

Lingjia Liu

Publications and source records attributed to Lingjia Liu.

At least 19 recordsLinked to original sources

arXiv2026

ESN-DAGMM: A Lightweight Framework for Unsupervised Time-Series Data Monitoring in 5G O-RAN Networks

Open Radio Access Network (O-RAN) is an important 5G network architecture enabling flexible communication with adaptive strategies for different verticals. However, testing for O-RAN deployments involve massive volumes of time-series data (e.g., key performance indicators), creating critical challenges for scalable, unsupervised monitoring without labels or high computational overhead. To address this, we present ESN-DAGMM, a lightweight adaptation of the Deep Autoencoding Gaussian Mixture Model (DAGMM) framework for time series analysis. Our model utilizes an Echo State Network (ESN) to efficiently model temporal dependencies, proving effective in O-RAN networks where training samples are highly limited. Combined with DAGMM's integratation of dimensionality reduction and density estimation, we present a scalable framework for unsupervised monitoring of high volume network telemetry. When trained on only 10% of an O-RAN video-streaming dataset, ESN-DAGMM achieved on average 269.59% higher quality clustering than baselines under identical conditions, all while maintaining competitive reconstruction error. By extending DAGMM to capture temporal dynamics, ESN-DAGMM offers a practical solution for time-series analysis using very limited training samples, outperforming baselines and enabling operator's control over the clustering-reconstruction trade-off.

eess.SP↗

arXiv2026

Learning Low-Dimensional Representation for O-RAN Testing via Transformer-ESN

Open Radio Access Network (O-RAN) architectures enhance flexibility for 6G and NextG networks. However, it also brings significant challenges in O-RAN testing with evaluating abundant, high-dimensional key performance indicators (KPIs). In this paper, we introduce a novel two-stage framework to learn temporally-aware low-dimensional representations of O-RAN testing KPIs. To be specific, stage one employs an information-theoretic H-score to train a hybrid self-attentive transformer and echo state network (ESN) reservoir, called Transformer-ESN, capturing temporal dynamics and producing task-aligned $8$-dimensional embeddings. Stage two evaluates these embeddings by training a lightweight multilayer perceptron (MLP) predictor exclusively on them for key target KPIs such as reference signal received quality (RSRQ) and spectral efficiency. Using real-world O-RAN testbed data (video streaming with interference), our approach demonstrates a significant advantage specifically when training samples are very limited. In this scenario, the low-dimensional representations learned from the Transformer-ESN yield mean square error (MSE) reductions of up to 41.9\% for RSRQ and 29.9\% for spectral efficiency compared to predictions from the original high-dimensional data. The framework exhibits high efficiency for O-RAN testing, significantly reducing testing complexities for O-RAN systems.

eess.SP↗

arXiv2026

CGFormer: A Cross-Attention Based Grid-Free Transformer for Radio Map Estimation

Radio map estimation (RME), which predicts wireless signal metrics at unmeasured locations from sparse measurements, has attracted growing attention as a key enabler of intelligent wireless networks. The majority of existing RME techniques employ grid-based strategies to process sparse measurements, where the pursuit of accuracy results in significant computational inefficiency and inflexibility for off-grid prediction. In contrast, grid-free approaches directly exploit coordinate features to capture location-specific spatial dependencies, enabling signal prediction at arbitrary locations without relying on predefined grids. However, current grid-free approaches demand substantial preprocessing overhead for constructing the spatial representation, leading to high complexity and constrained adaptability. To address these limitations, this paper proposes a novel cross-attention grid-free based transformer model for RME. We introduce a lightweight spatial embedding module that incorporates environmental knowledge into high-dimensional feature construction. A cross-attention transformer then models the spatial correlation between target and measurement points. The simulation results demonstrate that our proposed method reduces RMSE by up to 6%, outperforming grid-based and gridfree baselines.

eess.SP↗

arXiv2026

ML-Based Real-Time Downlink Performance Prediction in Standalone 5G NR Using Smartphones

We propose a machine learning (ML)-based framework for downlink performance prediction in 5G networks using real-time measurements from commercial off-the-shelf (COTS) user equipment (UE). Our experimental platform integrates the srsRAN 5G New Radio (NR) stack deployed on a Dell desktop serving as the 5G next generation nodeB (gNB), operating at 3.4 GHz. Two Google Pixel 7a smartphones are used to collect physical layer characteristics such as channel quality indicator (CQI), modulation and coding scheme (MCS), bit rate, transmission time interval (TTI), and block error rate (BLER), which are leveraged as predictors in model training. We use commercial-grade traffic generation tools, including Ookla, for stationary and mobility measurements under line-of-sight (LOS) and non-line-of-sight (nLOS) conditions. Test data includes global Ookla servers (e.g., USA, Portugal, Ghana, Egypt, Japan), iperf TCP/UDP data, and video streaming sessions from YouTube. To analyze inter-user interference, we also include scenarios with multiple UEs at the same location. We evaluate the predictive performance of five supervised regression models - linear regression, decision tree regression, random forest regression, extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM). Our results demonstrate that throughput and BLER can be accurately predicted using COTS hardware and standard ML techniques in diverse real-world 5G scenarios.

cs.NI↗

arXiv2026

ML and Smartphones Assisted Real-Time Uplink Performance Prediction in 5G Cellular System

We propose a machine learning (ML) and smartphone-assisted framework for uplink performance prediction in a private, realistic 5G cellular system using real-time measurements in both indoor and outdoor settings. This work presents a comprehensive data-driven evaluation of 5G performance prediction using a controllable software-defined radio test environment. The experimental platform is built on srsRAN 5G NR stack running on a Dell workstation configured as a gNB and 5G core operating at 3.4 GHz. Two commercial Google Pixel 7a devices are instrumented to capture uplink metrics, including channel quality indicator (CQI), modulation and coding scheme (MCS), throughput, transmission time interval (TTI), and block error rate (BLER). Different types of traffic are generated using industry-standard tools such as Ookla and iperf, spanning stationary, pedestrian, and mobility cases under both line-of-sight (LOS) and non-line-of-sight (nLOS) propagation environments. Additional datasets include YouTube video sessions and global server endpoints to introduce variability in path characteristics. The resulting measurements, including multi-UE interference conditions, serve as training data for several supervised regression models. Five learning algorithms-linear regression, decision tree, random forest, XGBoost, and LightGBM-are benchmarked for prediction accuracy. The study shows that reliable forecasting of throughput and BLER is feasible using only COTS smartphones and widely available ML methods, offering a practical pathway for real-world 5G network performance estimation.

cs.NI↗

arXiv2026

Rate-Distortion Bounds for Heterogeneous Random Fields on Finite Lattices

Since Shannon's foundational work, rate-distortion theory has defined the fundamental limits of lossy compression. Classical results, derived for memoryless and stationary ergodic sources in the asymptotic regime, have shaped both transform and predictive coding architectures, as well as practical standards such as JPEG. Finite-blocklength refinements, initiated by the non-asymptotic achievability and converse bounds of Kostina and Verdu, provide precise characterizations under excess-distortion probability constraints, but primarily for memoryless or statistically homogeneous models. In contrast, error-bounded practical lossy compressors for scientific computing, such as SZ, ZFP, MGARD, and SPERR, are designed for finite, high-dimensional, spatially correlated, and statistically heterogeneous random fields. These compressors partition data into fixed-size tiles that are processed independently, making tile size a central architectural constraint. Structural heterogeneity, finite lattice effects, and tiling constraints are not addressed by existing finite-blocklength analyses. This paper introduces a finite-blocklength rate-distortion framework for heterogeneous random fields on finite lattices, explicitly accounting for the tile-based architectures used in high-performance scientific compressors. The field is modeled as piecewise homogeneous with regionwise stationary second-order statistics, and tiling constraints are incorporated directly into the source model. Under an excess-distortion probability criterion, we establish non-asymptotic achievability, converse bounds and derive a second-order expansion that quantifies the impact of spatial correlation, region geometry, heterogeneity, and tile size on the rate and dispersion.

cs.IT↗

arXiv2026

When Learning Hurts: Fixed-Pole RNN for Real-Time Online Training

Recurrent neural networks (RNNs) can be interpreted as discrete-time state-space models, where the state evolution corresponds to an infinite-impulse-response (IIR) filtering operation governed by both feedforward weights and recurrent poles. While, in principle, all parameters including pole locations can be optimized via backpropagation through time (BPTT), such joint learning incurs substantial computational overhead and is often impractical for applications with limited training data. Echo state networks (ESNs) mitigate this limitation by fixing the recurrent dynamics and training only a linear readout, enabling efficient and stable online adaptation. In this work, we analytically and empirically examine why learning recurrent poles does not provide tangible benefits in data-constrained, real-time learning scenarios. Our analysis shows that pole learning renders the weight optimization problem highly non-convex, requiring significantly more training samples and iterations for gradient-based methods to converge to meaningful solutions. Empirically, we observe that for complex-valued data, gradient descent frequently exhibits prolonged plateaus, and advanced optimizers offer limited improvement. In contrast, fixed-pole architectures induce stable and well-conditioned state representations even with limited training data. Numerical results demonstrate that fixed-pole networks achieve superior performance with lower training complexity, making them more suitable for online real-time tasks.

cs.LG↗

arXiv2026

Revolutionizing Future Connectivity: A Contemporary Survey on AI-empowered Satellite-based Non-Terrestrial Networks in 6G

Non-Terrestrial Networks (NTN) are expected to be a critical component of 6th Generation (6G) networks, providing ubiquitous, continuous, and scalable services. Satellites emerge as the primary enabler for NTN, leveraging their extensive coverage, stable orbits, scalability, and adherence to international regulations. However, satellite-based NTN presents unique challenges, including long propagation delay, high Doppler shift, frequent handovers, spectrum sharing complexities, and intricate beam and resource allocation, among others. The integration of NTNs into existing terrestrial networks in 6G introduces a range of novel challenges, including task offloading, network routing, network slicing, and many more. To tackle all these obstacles, this paper proposes Artificial Intelligence (AI) as a promising solution, harnessing its ability to capture intricate correlations among diverse network parameters. We begin by providing a comprehensive background on NTN and AI, highlighting the potential of AI techniques in addressing various NTN challenges. Next, we present an overview of existing works, emphasizing AI as an enabling tool for satellite-based NTN, and explore potential research directions. Furthermore, we discuss ongoing research efforts that aim to enable AI in satellite-based NTN through software-defined implementations, while also discussing the associated challenges. Finally, we conclude by providing insights and recommendations for enabling AI-driven satellite-based NTN in future 6G networks.

cs.NI↗

arXiv2026

A Universal Neural Receiver that Learns at the Speed of Wireless

Today we design wireless networks using mathematical models that govern communication in different propagation environments. We rely on measurement campaigns to deliver parametrized propagation models, and on the 3GPP standards process to optimize model-based performance, but as wireless networks become more complex this model-based approach is losing ground. Mobile Network Operators (MNOs) are counting on Artificial Intelligence (AI) to transform wireless by increasing spectral efficiency, reducing signaling overhead, and enabling continuous network innovation through software upgrades. They may also be interested in new use cases like integrated sensing and communications (ISAC). All we need is an AI-native physical layer, so why not simply tailor the offline AI algorithms that have revolutionized image and natural language processing to the wireless domain? We argue that these algorithms rely on off-line training that is precluded by the sub-millisecond speeds at which the wireless interference environment changes. We present an alternative architecture, a universal neural receiver based on convolution, which governs transmit and receive signal processing of any signal in any part of the wireless spectrum. Our neural receiver is designed to invert convolution, and we separate the question of which convolution to invert from the actual deconvolution. The neural network that performs deconvolution is very simple, and we configure this network by setting weights based on domain knowledge. By telling our neural network what we know, we avoid extensive offline training. By developing a universal receiver, we hope to simplify discussions about the proper choice of waveform for different use cases in the international standards. Since the receiver architecture is largely independent of technologies introduced at the base station, we hope to increase the rate of innovation in wireless.

cs.IT↗

arXiv2026

LiQSS: Post-Transformer Linear Quantum-Inspired State-Space Tensor Networks for Real-Time 6G

Proactive and agentic control in Sixth-Generation (6G) Open Radio Access Networks (O-RAN) requires control-grade prediction under stringent Near-Real-Time (Near-RT) latency and computational constraints. While Transformer-based models are effective for sequence modeling, their quadratic complexity limits scalability in Near-RT RAN Intelligent Controller (RIC) analytics. This paper investigates a post-Transformer design paradigm for efficient radio telemetry forecasting. We propose a quantum-inspired many-body state-space tensor network that replaces self-attention with stable structured state-space dynamics kernels, enabling linear-time sequence modeling. Tensor-network factorizations in the form of Tensor Train (TT) / Matrix Product State (MPS) representations are employed to reduce parameterization and data movement in both input projections and prediction heads, while lightweight channel gating and mixing layers capture non-stationary cross-Key Performance Indicator (KPI) dependencies. The proposed model is instantiated as an agentic perceive-predict xApp and evaluated on a bespoke O-RAN KPI time-series dataset comprising 59,441 sliding windows across 13 KPIs, using Reference Signal Received Power (RSRP) forecasting as a representative use case. Our proposed Linear Quantum-Inspired State-Space (LiQSS) model is 10.8x-15.8x smaller and approximately 1.4x faster than prior structured state-space baselines. Relative to Transformer-based models, LiQSS achieves up to a 155x reduction in parameter count and up to 2.74x faster inference, without sacrificing forecasting accuracy.

cs.NI↗

arXiv2025

Developing an NTN Architecture for End-to-End Performance Evaluation

Non-Terrestrial Networks (NTN) are emerging as critical enablers of global connectivity, particularly in remote, unserved, underserved, or maritime regions lacking traditional infrastructure. While much of the existing work on NTN focuses on theoretical or simulated evaluations, practical implementations remain limited. In this paper, we present SpaceNET, a transparent NTN testbed that leverages the Starlink Low Earth Orbit (LEO) satellite constellation in conjunction with Mininet-based emulation to perform end-to-end performance assessments across real-world maritime and terrestrial endpoints that can also be applied to 5th generation (5G). Specifically, we establish a bidirectional link between a ground terminal located in Blacksburg, Virginia, and a maritime terminal aboard a cruise ship near Key West, Florida. We report detailed transmission control protocol (TCP) throughput, user datagram protocol (UDP) throughput, and latency measurements using two different user terminals - a) Smartphone, and b) very small aperture terminal (VSAT), emphasizing the transparent nature of the NTN payload, where the satellite acts solely as a relay node. Our results provide new insights into the performance limits and reliability of commercial LEO-based NTN applications. The SpaceNET testbed offers a reproducible and extensible platform for future research in NTN routing, mobility support, and cross-layer optimization.

cs.ET↗

arXiv2025

Agentic World Modeling for 6G: Near-Real-Time Generative State-Space Reasoning

We argue that sixth-generation (6G) intelligence is not fluent token prediction but the capacity to imagine and choose -- to simulate future scenarios, weigh trade-offs, and act with calibrated uncertainty. We reframe open radio access network (O-RAN) near-real-time (Near-RT) control via counterfactual dynamics and a world modeling (WM) paradigm that learns an action-conditioned generative state space. This enables quantitative "what-if" forecasting beyond large language models (LLMs) as the primary modeling primitive. Actions such as physical resource blocks (PRBs) are treated as first-class control inputs in a causal world model, and both aleatoric and epistemic uncertainty are modeled for prediction and what-if analysis. An agentic, model predictive control (MPC)-based cross-entropy method (CEM) planner operates over short horizons, using prior-mean rollouts within data-driven PRB bounds to maximize a deterministic reward. The model couples multi-scale structured state-space mixtures (MS3M) with a compact stochastic latent to form WM-MS3M, summarizing key performance indicators (KPIs) histories and predicting next-step KPIs under hypothetical PRB sequences. On realistic O-RAN traces, WM-MS3M cuts mean absolute error (MAE) by 1.69% versus MS3M with 32% fewer parameters and similar latency, and achieves 35-80% lower root mean squared error (RMSE) than attention/hybrid baselines with 2.3-4.1x faster inference, enabling rare-event simulation and offline policy screening.

cs.NI↗

arXiv2025

Communication in a Fractional World: MIMO MC-OTFS Precoder Prediction

As 6G technologies advance, international bodies and regulatory agencies are intensifying efforts to extend seamless connectivity especially for high-mobility scenarios such as Mobile Ad-Hoc Networks (\textit{MANETs}) types such as Vehicular Ad-Hoc Networks (\textit{VANETs}) and Flying Ad-Hoc Networks (\textit{FANETs}). For these environments to be considered for long term adoption and use they must support Multiple-Input-Multiple- (MIMO) technology, rapidly fluctuating channel conditions in these environments place a heavy burden on traditional time-frequency CSI feedback schemes required for MIMO precoding. This motivates a shift toward delay-Doppler representations like those employed by Orthogonal Time-Frequency Space(OTFS) modulation, which offers greater stability under mobility. We derive an expression for the variation over time in the OTFS I/O relationship. We then use this to create a physics informed complex exponential basis expansion model prediction framework that maximizes the usefulness of outdated Channel State Information (CSI) in the presence of integer and fractional delay-Doppler channels and facilitates high mobility MIMO communication.

eess.SP↗

arXiv2025

Rivaling Transformers: Multi-Scale Structured State-Space Mixtures for Agentic 6G O-RAN

In sixth-generation (6G) Open Radio Access Networks (O-RAN), proactive control is preferable. A key open challenge is delivering control-grade predictions within Near-Real-Time (Near-RT) latency and computational constraints under multi-timescale dynamics. We therefore cast RAN Intelligent Controller (RIC) analytics as an agentic perceive-predict xApp that turns noisy, multivariate RAN telemetry into short-horizon per-User Equipment (UE) key performance indicator (KPI) forecasts to drive anticipatory control. In this regard, Transformers are powerful for sequence learning and time-series forecasting, but they are memory-intensive, which limits Near-RT RIC use. Therefore, we need models that maintain accuracy while reducing latency and data movement. To this end, we propose a lightweight Multi-Scale Structured State-Space Mixtures (MS3M) forecaster that mixes HiPPO-LegS kernels to capture multi-timescale radio dynamics. We develop stable discrete state-space models (SSMs) via bilinear (Tustin) discretization and apply their causal impulse responses as per-feature depthwise convolutions. Squeeze-and-Excitation gating dynamically reweights KPI channels as conditions change, and a compact gated channel-mixing layer models cross-feature nonlinearities without Transformer-level cost. The model is KPI-agnostic -- Reference Signal Received Power (RSRP) serves as a canonical use case -- and is trained on sliding windows to predict the immediate next step. Empirical evaluations conducted using our bespoke O-RAN testbed KPI time-series dataset (59,441 windows across 13 KPIs). Crucially for O-RAN constraints, MS3M achieves a 0.057 s per-inference latency with 0.70M parameters, yielding 3-10x lower latency than the Transformer baselines evaluated on the same hardware, while maintaining competitive accuracy.

cs.NI↗

arXiv2025

Mutual Information-Driven Visualization and Clustering for Core KPI Selection in O-RAN Testing

O-RAN testing is becoming increasingly difficult with the exponentially growing number of performance measurements as the system grows more complex, with additional units, interfaces, applications, and possible implementations and configurations. To simplify the testing procedure and improve system design for O-RAN systems, it is important to identify the dependencies among various performance measurements, which are inherently time-series and can be modeled as realizations of random processes. While information theory can be utilized as a principled foundation for mapping these dependencies, the robust estimation of such measures for random processes from real-world data remains challenging. This paper introduces AMIF-MDS, which employs aggregate mutual Information in frequency (AMIF), a practical proxy for directed information (DI), to quantify similarity and visualize inter-series dependencies with multidimensional scaling (MDS). The proposed quantile-based AMIF estimator is applied to O-RAN time-series testing data to identify dependencies among various performance measures so that we can focus on a set of ``core'' performance measures. Applying density-based spatial clustering of applications with noise (DBSCAN) to the MDS embedding groups mutually informative metrics, organically reveals the link-adaptation indicators among other clusters, and yields a ``core'' performance measure set for future learning-driven O-RAN testing.

eess.SP↗

arXiv2025

An Experimental Reservoir-Augmented Foundation Model: 6G O-RAN Case Study

Next-generation open radio access networks (O-RAN) continuously stream tens of key performance indicators (KPIs) together with raw in-phase/quadrature (IQ) samples, yielding ultra-high-dimensional, non-stationary time series that overwhelm conventional transformer architectures. We introduce a reservoir-augmented masked autoencoding transformer (RA-MAT). This time series foundation model employs echo state network (ESN) computing with masked autoencoding to satisfy the stringent latency, energy efficiency, and scalability requirements of 6G O-RAN testing. A fixed, randomly initialized ESN rapidly projects each temporal patch into a rich dynamical embedding without backpropagation through time, converting the quadratic self-attention bottleneck into a lightweight linear operation. These embeddings drive a patch-wise masked autoencoder that reconstructs 30% randomly masked patches, compelling the encoder to capture both local dynamics and long-range structure from unlabeled data. After self-supervised pre-training, RA-MAT is fine-tuned with a shallow task head while keeping the reservoir and most transformer layers frozen, enabling low-footprint adaptation to diverse downstream tasks such as O-RAN KPI forecasting. In a comprehensive O-RAN KPI case study, RA-MAT achieved sub-0.06 mean squared error (MSE) on several continuous and discrete KPIs. This work positions RA-MAT as a practical pathway toward real-time, foundation-level analytics in future 6G networks.

cs.NI↗

arXiv2025

Spreading over OFDM for Integrated Sensing and Communications (ISAC) Ranging: Multi-user Interference Mitigation

In the context of communication-centric integrated sensing and communication (ISAC), the orthogonal frequency division multiplexing (OFDM) waveform was proven to be optimal in minimizing ranging sidelobes when random signaling is used. A typical assumption in OFDM-based ranging is that the max target delay is less than the cyclic prefix (CP) length, which is equivalent to performing a \textit{periodic} correlation between the signal reflected from the target and the transmitted signal. In the multi-user case, such as in Orthogonal Frequency Division Multiple Access (OFDMA), users are assigned disjoint subsets of subcarriers which eliminates mutual interference between the communication channels of the different users. However, ranging involves an aperiodic correlation operation for target ranges with delays greater than the CP length. Aperiodic correlation between signals from disjoint frequency bands will not be zero, resulting in mutual interference between different user bands. We refer to this as \textit{inter-band} (IB) cross-correlation interference. In this work, we analytically characterize IB interference and quantify its impact on the integrated sidelobe levels (ISL). We introduce an orthogonal spreading layer on top of OFDM that can reduce IB interference resulting in ISL levels significantly lower than for OFDM without spreading in the multi-user setup. We validate our claims through simulations, and using an upper bound on IB energy which we show that it can be minimized using our proposed spreading. However, for orthogonal spreading to be effective, a price must be paid in terms of spectral utilization, which is yet another manifestation of the trade-off between sensing accuracy and data communication capacity

eess.SP↗

arXiv2025

Mobile Distributed MIMO (MD-MIMO) for NextG: Mobility Meets Cooperation in Distributed Arrays

Distributed multiple-input multiple-output (D\mbox{-}MIMO) is a promising technology to realize the promise of massive MIMO gains by fiber-connecting the distributed antenna arrays, thereby overcoming the form factor limitations of co-located MIMO. In this paper, we introduce the concept of mobile D-MIMO (MD-MIMO) network, a further extension of the D-MIMO technology where distributed antenna arrays are connected to the base station with a wireless link allowing all radio network nodes to be mobile. This approach significantly improves deployment flexibility and reduces operating costs, enabling the network to adapt to the highly dynamic nature of next-generation (NextG) networks. We discuss use cases, system design, network architecture, and the key enabling technologies for MD-MIMO. Furthermore, we investigate a case study of MD-MIMO for vehicular networks, presenting detailed performance evaluations for both downlink and uplink. The results show that an MD-MIMO network can provide substantial improvements in network throughput and reliability.

eess.SP↗