latency-aware optimization

Existing speed measurement tools focus on peak throughput and poorly reflect users’ perceived responsiveness; emerging metrics such as “latency under load” show promise but their sensitivity to Active Queue Management (AQM) configurations remains unclear. Method: We empirically evaluate three mainstream AQM schemes—CoDel, FQ-CoDel, and SFQ—in a controlled network environment, systematically analyzing their impact on throughput and latency distributions, particularly latency under load. Results: AQM significantly alters speed test outcomes, with distinct latency-throughput trade-offs observed across algorithms under high load. Current measurement platforms, if uncalibrated for AQM, yield misleading latency estimates, undermining the reliability of policy and regulatory decisions. This study is the first to quantitatively characterize the structural impact of AQM on emerging speed metrics, providing critical empirical evidence to inform standardization of measurement tools and evidence-based network governance.

This work addresses energy optimization for latency-sensitive network services under tail-latency SLA constraints. We propose a black-box, online co-tuning method that jointly optimizes interrupt coalescing (packet batching) and Dynamic Voltage and Frequency Scaling (DVFS), requiring no modifications to applications or the OS kernel. Our approach employs a generic, application- and system-agnostic Bayesian optimization controller that rapidly converges to the optimal energy-efficiency operating point under SLA constraints using minimal online probing. Key contributions include: (i) achieving up to 60% energy reduction while meeting tail-latency SLAs; (ii) revealing that specialized OS kernels improve energy efficiency by over 2× compared to general-purpose kernels; and (iii) demonstrating strong generalizability and stability across diverse hardware platforms. The method enables practical, deployment-ready energy-aware tuning for high-performance network services without sacrificing latency guarantees.

This work addresses a critical flaw in existing LLM inference benchmarks, where single-process clients under high concurrency suffer from Python’s Global Interpreter Lock (GIL), leading to severe distortion in Time-to-First-Token (TTFT) and Time Per Output Token (TPOT) metrics. The study is the first to model the client as an M/G/1 queue, uncovering systematic bias introduced by queuing effects. To rectify this, the authors propose a multi-process, unbiased evaluation framework accompanied by a normalized metric—Normalized Time Per Output Token (NTPOT). This approach effectively eliminates client-side bottlenecks, enabling accurate and reproducible performance evaluation at scale, supporting thousands of queries per second. It substantially reduces the latency overestimation—often several-fold—in conventional benchmarks, thereby reflecting the true performance of production-grade LLM services.

Existing software simulation of Time-Sensitive Networking (TSN) suffers from insufficient accuracy in measuring bridge delay and jitter, undermining the fidelity and reproducibility of TSN emulation. Method: This paper introduces the first systematic timestamping methodology for TSN simulation on Linux/Mininet, rigorously evaluating four timestamping mechanisms—including SO_TIMESTAMPING—under TSN traffic shaped by Credit-Based Shaping (CBS) and Asynchronous Traffic Shaping (ATS). Leveraging configurable Mininet topologies, the approach integrates scheduling solution generation, deployment validation, and cross-platform optimization—supporting both Intel Time-Coordinated Computing (TCC)-enabled and -disabled modes on industrial PCs and workstations. Contribution/Results: The framework achieves sub-microsecond bridge delay characterization and, for the first time, experimentally validates end-to-end deterministic guarantees on real hardware. It overcomes critical bottlenecks in clock synchronization precision and scheduling fidelity, significantly enhancing the trustworthiness and reproducibility of TSN simulation.

This paper addresses the inherent trade-off between computation and communication latency in distributed real-time state estimation. Method: We formulate the first rigorous optimization framework jointly modeling computation latency, communication latency, and estimation performance; theoretically prove that transmitting raw sensor data is generally suboptimal in heterogeneous networks; and propose a joint convex optimization algorithm for sensor subset selection and adaptive linear preprocessing—explicitly respecting per-node computational constraints and network heterogeneity. Contributions/Results: Leveraging Kalman filtering theory and heuristic subset search, we validate the approach on multivariate discrete-time systems. Experiments demonstrate that our method significantly reduces estimation error compared to full-sensor transmission, and that judicious local preprocessing substantially improves overall estimation accuracy.

This work addresses the lack of a standardized observability framework in quantum networks, which hinders effective fault diagnosis and adaptive control. It proposes the first multidimensional performance metric system tailored for quantum networks, encompassing key parameters such as entanglement fidelity, quantum bit error rate, dark count rate, and timing jitter, while integrating environmental sensor data. Building on this foundation, the authors design and implement a non-intrusive, integrable real-time monitoring prototype, which has been deployed and validated at Oak Ridge National Laboratory. The system enables real-time data acquisition, performance alerting, and dynamic feedback, thereby establishing a critical observability infrastructure for quantum software-defined networking and autonomous control.

This study addresses the stringent constraints on size, power, and computational resources faced by AI inference on resource-limited platforms such as small satellites. By conducting empirical characterization of quantized AI inference on Cortex-M-class processors using representative embedded vision neural networks, the work establishes the first measurement-based performance baseline for on-board embedded systems. It introduces an explicit multi-core/multi-device cooperative scheduling mechanism and integrates analysis of ALU/SIMD utilization with memory traffic to evaluate system behavior. Moving beyond conventional paradigms that rely on opaque OS-level scheduling, this research provides comparable latency and data-movement benchmarks for typical spaceborne processors like LEON and NOEL-V, thereby demonstrating the critical role of architecture-aware design and cooperative scheduling as key dimensions in optimizing embedded AI inference for satellite applications.

This work addresses the reproducibility challenges posed by the rapid evolution of large models and high-performance computing systems, where existing benchmarks lack sustainable and automated evaluation mechanisms. To bridge this gap, the authors propose a user-agnostic continuous benchmarking framework that integrates principles from software engineering—particularly continuous integration—to establish an automated pipeline. This pipeline seamlessly combines systematic workflows with community-driven collaboration, delivering a reproducible and scalable benchmarking infrastructure for artificial intelligence and neuroscience research. The framework significantly enhances the sustainability, transparency, and collaborative efficiency of scientific evaluation in these fields.

This study addresses the lack of a unified framework for fairly evaluating continuous multi-modal scheduling (CMMS) algorithms under multidimensional service-level objectives (SLOs) in heterogeneous edge clusters. The authors propose the first open-source benchmark platform, featuring a standardized controller interface, a closed-loop multi-modal workload generator, and an innovative dual-metric SLO scoring mechanism that distinguishes between raw and steady-state SLOs. Using this platform, they systematically evaluate multiple scheduling algorithms across 424 diverse scenarios. Their experiments reveal that scheduler performance rankings are highly sensitive to cluster configurations and load intensities: deep reinforcement learning–based schedulers achieve superior performance under light loads but suffer a nearly 29-percentage-point degradation under heavy loads, accompanied by decision-making overhead approximately 500 times higher, thereby challenging assumptions about algorithmic generality.