High-Fidelity Network Management for Federated AI-as-a-Service: Cross-Domain Orchestration

To support the emergence of AI-as-a-Service (AIaaS), communication service providers (CSPs) are on the verge of a radical transformation-from pure connectivity providers to AIaaS a managed network service (control-and-orchestration plane that exposes AI models). In this model, the CSP is responsible not only for transport/communications, but also for intent-to-model resolution and joint network-compute orchestration, i.e., reliable and timely end-to-end delivery. The resulting end-to-end AIaaS service thus becomes governed by communications impairments (delay, loss) and inference impairments (latency, error). A central open problem is an operational AIaaS control-and-orchestration framework that enforces high fidelity, particularly under multi-domain federation. This paper introduces an assurance-oriented AIaaS management plane based on Tail-Risk Envelopes (TREs): signed, composable per-domain descriptors that combine deterministic guardrails with stochastic rate-latency-impairment models. Using stochastic network calculus, we derive bounds on end-to-end delay violation probabilities across tandem domains and obtain an optimization-ready risk-budget decomposition. We show that tenant-level reservations prevent bursty traffic from inflating tail latency under TRE contracts. An auditing layer then uses runtime telemetry to estimate extreme-percentile performance, quantify uncertainty, and attribute tail-risk to each domain for accountability. Packet-level Monte-Carlo simulations demonstrate improved p99.9 compliance under overload via admission control and robust tenant isolation under correlated burstiness.

AI-Paging: Lease-Based Execution Anchoring for Network-Exposed AI-as-a-Service

With AI-as-a-Service (AIaaS) now deployed across multiple providers and model tiers, selecting the appropriate model instance at run time is increasingly outside the end user's knowledge and operational control. Accordingly, the 6G service providers are envisioned to play a crucial role in exposing AIaaS in a setting where users submit only an intent while the network helps in the intent-to-model matching (resolution) and execution placement under policy, trust, and Quality of Service (QoS) constraints. The network role becomes to discover candidate execution endpoints and selects a suitable model/anchor under policy and QoS constraints in a process referred here to as AI-paging (by analogy to cellular call paging). In the proposed architecture, AI-paging is a control-plane transaction that resolves an intent into an AI service identity (AISI), a scoped session token (AIST), and an expiring admission lease (COMMIT) that authorizes user-plane steering to a selected AI execution anchor (AEXF) under a QoS binding. AI-Paging enforces two invariants: (i) lease-gated steering (without COMMIT, no steering state is installed) and (ii) make-before-break anchoring to support continuity and reliability of AIaaS services under dynamic network conditions. We prototype AI-Paging using existing control- and user-plane mechanisms (service-based control, QoS flows, and policy-based steering) with no new packet headers, ensuring compatibility with existing 3GPP-based exposure and management architectures, and evaluate transaction latency, relocation interruption, enforcement correctness under lease expiry, and audit-evidence overhead under mobility and failures.

Predictive-State Communication: Innovation Coding and Reconciliation under Delay

Shannon theory models communication as the reliable transfer of symbol sequences, with performance governed by capacity and rate-distortion limits. When both endpoints possess strong predictors -- as in modern large language models and related generative priors -- literal symbol transport is no longer the only operational regime. We propose predictive-state communication (PSC), in which the transmitter and receiver maintain an explicit shared predictive state, and the physical channel is used primarily to convey innovations, i.e., corrective information that reconciles the receiver's provisional trajectory with the transmitter's realized trajectory. This viewpoint replaces entropy-rate accounting by cross-entropy accounting under model mismatch, and it introduces feasibility constraints that depend jointly on capacity, delay, and perceptual continuity requirements; the resulting operating set is typically a bounded perception-capacity band rather than a one-sided threshold. We outline the protocol and architectural implications (state identifiers, anchors, bounded rollback, and patch-based updates) and provide a stylized illustrative example to visualize the induced feasibility region and its dependence on predictive quality.

On the Structure of the Optimal Detector for Sub-THz Multi-Hop Relays with Unknown Prior: Over-the-Air Diffusion

Amplify and forward (AF) relaying is a viable strategy to extend the coverage of sub-terahertz (sub-THz) links, but inevitably propagates noise, leading to cumulative degradation across multiple hops. At the receiver, optimal decoding is desirable, yet challenging under non-Gaussian input distributions (video, voice, etc), for which neither the Minimum Mean Square Error (MMSE) estimator nor the mutual information admits a closed form. A further open question is whether knowledge of Channel State Information (CSI) and noise statistics at the intermediate relays is necessary for optimal detection. Aiming for an optimal decoder, this paper introduces a new framework that interprets the AF relay chain as a variance-preserving diffusion process and employs denoising diffusion implicit models (DDIMs) for signal recovery. We show that each AF hop is mathematically equivalent to a diffusion step with hop-dependent attenuation and noise injection. Consequently, the entire multi-hop chain collapses to an equivalent Gaussian channel fully described by only three real scalars per block: the cumulative complex gain and the effective noise variance. At the receiver, these end-to-end sufficient statistics define a matched reverse schedule that guides the DDIM-based denoiser, enabling near-optimal Bayesian decoding without per-hop CSI. We establish the information-theoretic foundation of this equivalence, proving that decoding performance depends solely on the final effective Signal-to-Noise-Ratio (SNR), regardless of intermediate noise/channel allocation or prior distribution. Simulations under AWGN and Rician fading confirm that the proposed AF-DDIM decoder reduces mean-squared error, symbol error rate, and bit error rate, particularly at moderate SNRs and for higher-order constellations.

On the Performance of ISAC over the D-Band in a Phase-Noise Aware OFDM Systems

Phase noise (PN) is a critical impairment at D-band frequencies (110 to 170 GHz), which are widely investigated as promising candidates for beyond 5G/6G ISAC systems. This paper evaluates OFDM based ISAC sensing performance under realistic oscillator impairments using a hardware-tuned 3GPP PN model at 130 GHz and FFT based radar processing. With a numerology of 480 kHz, results show that PN introduces range RMSE floors of 0.04 to 0.05 m and velocity RMSE floors of 0.12 to 0.18 m/s. Doppler sidelobe metrics also saturate, with PSLR around minus 6 dB and ISLR around minus 4 dB. These findings confirm that range accuracy remains bandwidth limited, while velocity estimation and sidelobe suppression are strongly PN-sensitive. The study highlights the importance of PN-aware waveform and numerology design for sub-THz ISAC and provides insights for future multi-band transceivers. Communication metrics and PN mitigation strategies such as PTRS and CPE tracking are left for future work.

Theoretical and Experimental Assessment of Large Beam Codebook at mmWave Devices: How Much is Enough?

Modern millimeter wave (mmWave) transceivers come with a large number of antennas, each of which can support thousands of phase shifter configurations. This capability enables beam sweeping with fine angular resolution, but results in large codebook sizes that can span more than six orders of magnitude. On the other hand, the mobility of user terminals and their randomly changing orientations require constantly adjusting the beam direction. A key focus of recent research has been on the design of beam sweeping codebooks that balance a trade-off between the achievable gain and the beam search time, governed by the codebook size. In this paper, we investigate the extent to which a large codebook can be reduced to fewer steering vectors while covering the entire angular space and maintaining performance close to the maximum array gain. We derive a closed-form expression for the angular coverage range of a steering vector, subject to maintaining a gain loss within \(\gamma\) dB (e.g., 2\, dB) with respect to the maximum gain achieved by an infinitely large codebook. We demonstrate, both theoretically and experimentally, that a large beam-steering codebooks (such as the \(1024^{16}\) set considered in our experiment) can be reduced to just a few steering vectors. This framework serves as a proof that only a few steering vectors are sufficient to achieve near-maximum gain, challenging the common belief that a large codebook with fine angular resolution is essential to fully reap the benefits of an antenna array.

Beam Codebook Refinement for mmWave Devices with Random Orientations: Concept and Experimental Validation

There is a growing interest in codebook-based beam-steering for millimeter-wave (mmWave) systems due to its potential for low complexity and rapid beam search. A key focus of recent research has been the design of codebooks that strike a trade-off between achievable gain and codebook size, which directly impacts beam search time. Statistical approaches have shown promise by leveraging the likelihood that certain beam directions (equivalently, sets of phase-shifter configurations) are more probable than others. Such approaches are shown to be valid for static, non-rotating transmission stations such as base stations. However, for the case of user terminals that are constantly changing orientation, the possible phase-shifter configurations become equally probable, rendering statistical methods less relevant. On the other hand, user terminals come with a large number of possible steering vector configurations, which can span up to six orders of magnitude. Therefore, efficient solutions to reduce the codebook size (set of possible steering vectors) without compromising array gain are needed. We address this challenge by proposing a novel and practical codebook refinement technique, aiming to reduce the codebook size while maintaining array gain within $\gamma$ dB of the maximum achievable gain at any random orientation of the user terminal. We project that a steering vector at a given angle could effectively cover adjacent angles with a small gain loss compared to the maximum achievable gain. We demonstrate experimentally that it is possible to reduce the codebook size from $1024^{16}$ to just a few configurations (e.g., less than ten), covering all angles while maintaining the gain within $\gamma=3$ dB of the maximum achievable gain.

A Downlink Puncturing Scheme for Simultaneous Transmission of URLLC and eMBB Traffic by Exploiting Data Similarity

Ultra Reliable and Low Latency Communications (URLLC) is deemed to be an essential service in 5G systems and beyond to accommodate a wide range of emerging applications with stringent latency and reliability requirements. Coexistence of URLLC alongside other service categories calls for developing spectrally efficient multiplexing techniques. Specifically, coupling URLLC and conventional enhanced Mobile BroadBand (eMBB) through superposition/puncturing naturally arises as a promising option due to the tolerance of the latter in terms of latency and reliability. The idea here is to transmit URLLC packets over resources occupied by ongoing eMBB transmissions while minimizing the impact on the eMBB transmissions. In this paper, we propose a novel downlink URLLC-eMBB multiplexing technique that exploits possible similarities among URLLC and eMBB symbols, with the objective of reducing the size of the punctured eMBB symbols. We propose that the base station scans the eMBB traffic' symbol sequences and punctures those that have the highest symbol similarity with that of the URLLC users to be served. As the eMBB and URLLC may use different constellation sizes, we introduce the concept of symbol region similarity to accommodate the different constellations. We assess the performance of the proposed scheme analytically, where we derive closed-form expressions for the symbol error rate (SER) of the eMBB and URLLC services. {We also derive an expression for the eMBB loss function due to puncturing in terms of the eMBB SER}. We demonstrate through numerical and simulation results the efficacy of the proposed scheme where we show that 1) the eMBB spectral efficiency is improved by puncturing fewer symbols, 2) the SER and reliability performance of eMBB are improved, and 3) the URLLC data is accommodated within the specified delay constraint while maintaining its reliability.