arXiv subjects

Guoming Tang

Publications and source records attributed to Guoming Tang.

At least 19 recordsLinked to original sources

arXiv2026

ARTSN: Exact and Adaptive Self-triggered Traffic Scheduling for ARTS Networks

Autonomous real-time systems (ARTS), such as self-driving vehicles and robotic assembly lines, are increasingly deployed to improve efficiency, accuracy, and responsiveness with reduced human intervention. In ARTS networks, self-triggered (ST) traffic-initiated by internal decision-making rather than fixed schedules or external events-is becoming prevalent and plays a critical role in enabling timely autonomous actions. However, existing network schedulers do not adequately support ST traffic due to two inherent challenges: volatility, where bounded processing jitter leads to uncertain arrival times, and absence, where reserved network resources remain underutilized when ST traffic does not materialize. To address these challenges, we propose ARTSN, an ST-tailored scheduling paradigm built upon time-sensitive networking (TSN). ARTSN introduces two key techniques: (1) an exact offline scheduling method that leverages the inferable arrival information of ST traffic for precise time-slot reservation, and (2) an adaptive online slot-release mechanism that dynamically reclaims unused reservations when ST traffic is absent. Extensive experiments on both a TSN simulator and a real-world testbed show that ARTSN significantly improves schedulability, scalability, and efficiency over state-of-the-art methods while maintaining reliable transmission guarantees.

cs.NI↗

arXiv2025

SAGkit: A Python SAG Toolkit for Response Time Analysis of Hybrid-Triggered Jobs

For distributed control systems, modern latency-critical applications are increasingly demanding real-time guarantees and robustness. Response-time analysis (RTA) is useful for this purpose, as it helps analyze and guarantee timing bounds. However, conventional RTA methods struggle with the state-space explosion problem, especially in non-preemptive systems with release jitter and execution time variations. In this paper, we introduce SAGkit, a Python toolkit that implements the schedule-abstraction graph (SAG) framework. SAGkit novelly enables exact and sustainable RTA of hybrid-triggered jobs by allowing job absence on the SAG basis. Our experiments demonstrate that SAGkit achieves exactness with acceptable runtime and memory overhead. This lightweight toolkit empowers researchers to analyze complex distributed control systems and is open-access for further development.

cs.DC↗

arXiv2025

CaberNet: Causal Representation Learning for Cross-Domain HVAC Energy Prediction

Cross-domain HVAC energy prediction is essential for scalable building energy management, particularly because collecting extensive labeled data for every new building is both costly and impractical. Yet, this task remains highly challenging due to the scarcity and heterogeneity of data across different buildings, climate zones, and seasonal patterns. In particular, buildings situated in distinct climatic regions introduce variability that often leads existing methods to overfit to spurious correlations, rely heavily on expert intervention, or compromise on data diversity. To address these limitations, we propose CaberNet, a causal and interpretable deep sequence model that learns invariant (Markov blanket) representations for robust cross-domain prediction. In a purely data-driven fashion and without requiring any prior knowledge, CaberNet integrates i) a global feature gate trained with a self-supervised Bernoulli regularization to distinguish superior causal features from inferior ones, and ii) a domain-wise training scheme that balances domain contributions, minimizes cross-domain loss variance, and promotes latent factor independence. We evaluate CaberNet on real-world datasets collected from three buildings located in three climatically diverse cities, and it consistently outperforms all baselines, achieving a 22.9% reduction in normalized mean squared error (NMSE) compared to the best benchmark. Our code is available at https://github.com/SusCom-Lab/CaberNet-CRL.

cs.LG↗

arXiv2025

ZSPAPrune: Zero-Shot Prompt-Aware Token Pruning for Vision-Language Models

As the capabilities of Vision-Language Models (VLMs) advance, they can process increasingly large inputs, which, unlike in LLMs, generates significant visual token redundancy and leads to prohibitive inference costs. While many methods aim to reduce these costs by pruning visual tokens, existing approaches, whether based on attention or diversity, typically neglect the guidance of the text prompt and thus fail to prioritize task relevance. In this work, we propose a novel, zero-shot method that reframes the problem by introducing a prompt-aware perspective, explicitly modeling visual token pruning as a balance between task relevance and information diversity. Our hierarchical approach first selects a core set of task-relevant visual tokens and then supplements them with diversity tokens to preserve broader context. Experiments across multiple models and benchmarks show that our method achieves performance that matches or surpasses the state-of-the-art with only minimal accuracy loss, even when pruning up to 90\% of the tokens. Furthermore, these gains are accompanied by significant reductions in GPU memory footprint and inference latency.

cs.CV↗

arXiv2025

Energy Injection Identification enabled Disaggregation with Deep Multi-Task Learning

Non-Intrusive Load Monitoring (NILM) offers a cost-effective method to obtain fine-grained appliance-level energy consumption in smart homes and building applications. However, the increasing adoption of behind-the-meter (BTM) energy sources such as solar panels and battery storage poses new challenges for conventional NILM methods that rely solely on at-the-meter data. The energy injected from the BTM sources can obscure the power signatures of individual appliances, leading to a significant decrease in NILM performance. To address this challenge, we present DualNILM, a deep multi-task learning framework designed for the dual tasks of appliance state recognition and injected energy identification. Using a Transformer-based architecture that integrates sequence-to-point and sequence-to-sequence strategies, DualNILM effectively captures multiscale temporal dependencies in the aggregate power consumption patterns, allowing for accurate appliance state recognition and energy injection identification. Extensive evaluation on self-collected and synthesized datasets demonstrates that DualNILM maintains an excellent performance for dual tasks in NILM, much outperforming conventional methods. Our work underscores the framework's potential for robust energy disaggregation in modern energy systems with renewable penetration. Synthetic photovoltaic augmented datasets with realistic injection simulation methodology are open-sourced at https://github.com/MathAdventurer/PV-Augmented-NILM-Datasets.

cs.LG↗

arXiv2025

AGFT: An Adaptive GPU Frequency Tuner for Real-Time LLM Inference Optimization

The explosive growth of interactive Large Language Models (LLMs) has placed unprecedented demands for low latency on cloud GPUs, forcing them into high-power modes and causing escalating energy costs. Real-time inference workloads exhibit significant dynamic volatility, presenting substantial energy-saving opportunities. However, traditional static or rule-based power management strategies struggle to exploit these opportunities without compromising peak performance. To address this challenge, we propose AGFT (An Adaptive GPU Frequency Tuner), a framework that employs online reinforcement learning to autonomously learn an optimal frequency tuning policy. By monitoring real-time features like request load and latency, AGFT utilizes fine-grained frequency control for precise adjustments and intelligent action space pruning for stable, efficient decision-making. This creates a robust, automated energy management solution. We comprehensively evaluated AGFT in an environment simulating realistic, fluctuating inference requests. The experimental results demonstrate that AGFT successfully saves 44.3% of GPU energy consumption while introducing a minimal performance latency overhead of under 10%. This achievement translates into a comprehensive Energy-Delay Product (EDP) optimization of up to 40.3%, clearly showing that our framework can significantly enhance the energy efficiency and economic benefits of existing LLM inference clusters without compromising service quality.

cs.LG↗

arXiv2025

GPUnion: Autonomous GPU Sharing on Campus

A pronounced imbalance in GPU resources exists on campus, where some laboratories own underutilized servers while others lack the compute needed for AI research. GPU sharing can alleviate this disparity, while existing platforms typically rely on centralized oversight and persistent allocation models, conflicting with the voluntary and autonomous nature of academic resource ownership. We present GPUnion, a campus-scale GPU sharing platform enabling voluntary participation while preserving full provider autonomy. GPUnion incorporates three core mechanisms: i) container-based task dispatching and execution, ii) resource provider-first architecture, and iii) resilient execution featuring automatic check-pointing and migration. Case studies across multiple campus scenarios demonstrate 30% more GPU utilization improvement, 40% increase in interactive sessions, and 94% successful workload migration during provider departures.

cs.DC↗

arXiv2025

Trustworthy Pedestrian Trajectory Prediction via Pattern-Aware Interaction Modeling

Accurate and reliable pedestrian trajectory prediction is critical for the application of intelligent applications, yet achieving trustworthy prediction remains highly challenging due to the complexity of interactions among pedestrians. Previous methods often adopt black-box modeling of pedestrian interactions. Despite their strong performance, such opaque modeling limits the reliability of predictions in real-world deployments. To address this issue, we propose InSyn (Interaction-Synchronization Network), a novel Transformer-based model that explicitly captures diverse interaction patterns (e.g., walking in sync or conflicting) while effectively modeling direction-sensitive social behaviors. Additionally, we introduce a training strategy, termed Seq-Start of Seq (SSOS), designed to alleviate the common issue of initial-step divergence in numerical time-series prediction. Experiments on the ETH and UCY datasets demonstrate that our model not only outperforms recent black-box baselines in prediction accuracy, especially under high-density scenarios, but also provides transparent interaction modeling, as shown in the case study. Furthermore, the SSOS strategy proves to be effective in improving sequential prediction performance, reducing the initial-step prediction error by approximately 6.58%. Code is avaliable at https://github.com/rickzky1001/InSyn

cs.CV↗

arXiv2025

AIMeter: Measuring, Analyzing, and Visualizing Energy and Carbon Footprint of AI Workloads

The rapid advancement of AI, particularly large language models (LLMs), has raised significant concerns about the energy use and carbon emissions associated with model training and inference. However, existing tools for measuring and reporting such impacts are often fragmented, lacking systematic metric integration and offering limited support for correlation analysis among them. This paper presents AIMeter, a comprehensive software toolkit for the measurement, analysis, and visualization of energy use, power draw, hardware performance, and carbon emissions across AI workloads. By seamlessly integrating with existing AI frameworks, AIMeter offers standardized reports and exports fine-grained time-series data to support benchmarking and reproducibility in a lightweight manner. It further enables in-depth correlation analysis between hardware metrics and model performance and thus facilitates bottleneck identification and performance enhancement. By addressing critical limitations in existing tools, AIMeter encourages the research community to weigh environmental impact alongside raw performance of AI workloads and advances the shift toward more sustainable "Green AI" practices. The code is available at https://github.com/SusCom-Lab/AIMeter.

cs.DC↗

arXiv2025

BandPilot: Toward Performance- and Contention-Aware GPU Dispatching in AI Clusters

Modern multi-tenant AI clusters are increasingly communication-bound, driven by high-volume and multi-round GPU-to-GPU collective communication. Consequently, the GPU dispatcher's choice of a physical GPU subset for each tenant largely determines the job's effective collective bandwidth and thus its performance ceiling. Existing dispatchers predominantly rely on static, topology-aware heuristics that prioritize GPU resource compactness, assuming that minimizing physical distance maximizes communication bandwidth. However, we reveal that this assumption often fails due to complex system-level bottlenecks, such as non-linear NIC saturation and inter-node link heterogeneity. This paper presents BandPilot, a performance- and contention-aware GPU dispatching primitive that optimizes effective collective bandwidth for multi-tenant AI clusters. Specifically, BandPilot learns a data-efficient bandwidth model from sparse NCCL measurements via a hierarchical design. Guided by the model, BandPilot uses an equilibrium-driven heuristic as a fast front end, and invokes a pruned elimination search when a controller predicts that further refinement is worthwhile. To account for multi-tenant interference, BandPilot virtually merges a candidate allocation with co-located cross-host jobs to conservatively estimate shared bottleneck capacity and predict contention-degraded bandwidth. Across a 32-GPU H100 cluster and heterogeneous simulations, BandPilot achieves 90-97% bandwidth efficiency relative to the best-found reference, improving average efficiency by 20-30% over topology-compactness heuristics.

cs.DC↗

arXiv2025

Prompting Large Language Models for Training-Free Non-Intrusive Load Monitoring

Non-intrusive load monitoring (NILM) aims to disaggregate total electricity consumption into individual appliance usage, thus enabling more effective energy management. While deep learning has advanced NILM, it remains limited by its dependence on labeled data, restricted generalization, and lack of explainability. This paper introduces the first prompt-based NILM framework that leverages large language models (LLMs) with in-context learning. We design and evaluate prompt strategies that integrate appliance features, contextual information, and representative time-series examples through extensive case studies. Extensive experiments on the REDD and UK-DALE datasets show that LLMs guided solely by prompts deliver only basic NILM capabilities, with performance that lags behind traditional deep-learning models in complex scenarios. However, the experiments also demonstrate strong generalization across different houses and even regions by simply adapting the injected appliance features. It also provides clear, human-readable explanations for the inferred appliance states. Our findings define the capability boundaries of using prompt-only LLMs for NILM tasks. Their strengths in generalization and explainability present a promising new direction for the field.

cs.LG↗

arXiv2025

ZSMerge: Zero-Shot KV Cache Compression for Memory-Efficient Long-Context LLMs

The linear growth of key-value (KV) cache memory and quadratic computational in attention mechanisms complexity pose significant bottlenecks for large language models (LLMs) in long-context processing. While existing KV cache optimization methods address these challenges through token pruning or feature merging, they often incur irreversible information loss or require costly parameter retraining. To this end, we propose ZSMerge, a dynamic KV cache compression framework designed for efficient cache management, featuring three key operations: (1) fine-grained memory allocation guided by multi-dimensional token importance metrics at head-level granularity, (2) a residual merging mechanism that preserves critical context through compensated attention scoring, and (3) a zero-shot adaptation mechanism compatible with diverse LLM architectures without requiring retraining. ZSMerge significantly enhances memory efficiency and inference speed with negligible performance degradation across LLMs. When applied to LLaMA2-7B, it demonstrates a 20:1 compression ratio for key-value cache retention (reducing memory footprint to 5\% of baseline) while sustaining comparable generation quality, coupled with triple throughput gains at extreme 54k-token contexts that eliminate out-of-memory failures. The code is available at https://github.com/SusCom-Lab/ZSMerge.

cs.CL↗

arXiv2024

Towards Real-world Deployment of NILM Systems: Challenges and Practices

Non-intrusive load monitoring (NILM), as a key load monitoring technology, can much reduce the deployment cost of traditional power sensors. Previous research has largely focused on developing cloud-exclusive NILM algorithms, which often result in high computation costs and significant service delays. To address these issues, we propose a three-tier framework to enhance the real-world applicability of NILM systems through edge-cloud collaboration. Considering the computational resources available at both the edge and cloud, we implement a lightweight NILM model at the edge and a deep learning based model at the cloud, respectively. In addition to the differential model implementations, we also design a NILM-specific deployment scheme that integrates Gunicorn and NGINX to bridge the gap between theoretical algorithms and practical applications. To verify the effectiveness of the proposed framework, we apply real-world NILM scenario settings and implement the entire process of data acquisition, model training, and system deployment. The results demonstrate that our framework can achieve high decomposition accuracy while significantly reducing the cloud workload and communication overhead under practical considerations.

eess.SY↗

arXiv2023

A Versatility-Performance Balanced Hardware Architecture for Scene Text Detection

Detecting and extracting textual information from natural scene images needs Scene Text Detection (STD) algorithms. Fully Convolutional Neural Networks (FCNs) are usually utilized as the backbone model to extract features in these instance segmentation based STD algorithms. FCNs naturally come with high computational complexity. Furthermore, to keep up with the growing variety of models, flexible architectures are needed. In order to accelerate various STD algorithms efficiently, a versatility-performance balanced hardware architecture is proposed, together with a simple but efficient way of configuration. This architecture is able to compute different FCN models without hardware redesign. The optimization is focused on hardware with finely designed computing modules, while the versatility of different network reconfigurations is achieved by microcodes instead of a strenuously designed compiler. Multiple parallel techniques at different levels and several complexity-reduction methods are explored to speed up the FCN computation. Results from implementation show that, given the same tasks, the proposed system achieves a better throughput compared with the studied GPU. Particularly, our system reduces the comprehensive Operation Expense (OpEx) at GPU by 46\%, while the power efficiency is enhanced by 32\%. This work has been deployed in commercial applications and provided stable consumer text detection services.

cs.AR↗

arXiv2021

BESS Aided Reconfigurable Energy Supply using Deep Reinforcement Learning for 5G and Beyond

The year of 2020 has witnessed the unprecedented development of 5G networks, along with the widespread deployment of 5G base stations (BSs). Nevertheless, the enormous energy consumption of BSs and the incurred huge energy cost have become significant concerns for the mobile operators. As the continuous decline of the renewable energy cost, equipping the power-hungry BSs with renewable energy generators could be a sustainable solution. In this work, we propose an energy storage aided reconfigurable renewable energy supply solution for the BS, which could supply clean energy to the BS and store surplus energy for backup usage. Specifically, to flexibly reconfigure the battery's discharging/charging operations, we propose a deep reinforcement learning based reconfiguring policy, which can adapt to the dynamical renewable energy generations as well as the varying power demands. Our experiments using the real-world data on renewable energy generations and power demands demonstrate that, our reconfigurable power supply solution can achieve an energy saving ratio of 74.8%, compared to the case with traditional power grid supply.

cs.DC↗

arXiv2021

FedNILM: Applying Federated Learning to NILM Applications at the Edge

Non-intrusive load monitoring (NILM) helps disaggregate the household's main electricity consumption to energy usages of individual appliances, thus greatly cutting down the cost in fine-grained household load monitoring. To address the arisen privacy concern in NILM applications, federated learning (FL) could be leveraged for NILM model training and sharing. When applying the FL paradigm in real-world NILM applications, however, we are faced with the challenges of edge resource restriction, edge model personalization and edge training data scarcity. In this paper we present FedNILM, a practical FL paradigm for NILM applications at the edge client. Specifically, FedNILM is designed to deliver privacy-preserving and personalized NILM services to large-scale edge clients, by leveraging i) secure data aggregation through federated learning, ii) efficient cloud model compression via filter pruning and multi-task learning, and iii) personalized edge model building with unsupervised transfer learning. Our experiments on real-world energy data show that, FedNILM is able to achieve personalized energy disaggregation with the state-of-the-art accuracy, while ensuring privacy preserving at the edge client.

cs.LG↗

arXiv2021

More Behind Your Electricity Bill: a Dual-DNN Approach to Non-Intrusive Load Monitoring

Non-intrusive load monitoring (NILM) is a well-known single-channel blind source separation problem that aims to decompose the household energy consumption into itemised energy usage of individual appliances. In this way, considerable energy savings could be achieved by enhancing household's awareness of energy usage. Recent investigations have shown that deep neural networks (DNNs) based approaches are promising for the NILM task. Nevertheless, they normally ignore the inherent properties of appliance operations in the network design, potentially leading to implausible results. We are thus motivated to develop the dual Deep Neural Networks (dual-DNN), which aims to i) take advantage of DNNs' learning capability of latent features and ii) empower the DNN architecture with identification ability of universal properties. Specifically in the design of dual-DNN, we adopt one subnetwork to measure power ratings of different appliances' operation states, and the other subnetwork to identify the running states of target appliances. The final result is then obtained by multiplying these two network outputs and meanwhile considering the multi-state property of household appliances. To enforce the sparsity property in appliance's state operating, we employ median filtering and hard gating mechanisms to the subnetwork for state identification. Compared with the state-of-the-art NILM methods, our dual-DNN approach demonstrates a 21.67% performance improvement in average on two public benchmark datasets.

cs.LG↗

arXiv2020

PLVER: Joint Stable Allocation and Content Replication for Edge-assisted Live Video Delivery

The live streaming services have gained extreme popularity in recent years. Due to the spiky traffic patterns of live videos, utilizing the distributed edge servers to improve viewers' quality of experience (QoE) has become a common practice nowadays. Nevertheless, current client-driven content caching mechanism does not support caching beforehand from the cloud to the edge, resulting in considerable cache missing in live video delivery. State-of-the-art research generally sacrifices the liveness of delivered videos in order to deal with the above problem. In this paper, by jointly considering the features of live videos and edge servers, we propose PLVER, a proactive live video push scheme to resolve the cache miss problem in live video delivery. Specifically, PLVER first conducts a one-tomultiple stable allocation between edge clusters and user groups, to balance the load of live traffic over the edge servers. Then it adopts proactive video replication algorithms to speed up the video replication among the edge servers. We conduct extensive trace-driven evaluations, covering 0.3 million Twitch viewers and more than 300 Twitch channels. The results demonstrate that with PLVER, edge servers can carry 28% and 82% more traffic than the auction-based replication method and the caching on requested time method, respectively.

cs.NI↗