arXiv subjects

Amir Taherkordi

Publications and source records attributed to Amir Taherkordi.

15 recordsLinked to original sources

arXiv2026

GreenPipe: Power Modeling for Containerized DNN Inference on Kubernetes Edge Nodes

Distributed DNN inference is increasingly deployed in containerized edge-cloud environments, where workloads run on-device or are exposed to remote clients over the network. Accurate online power estimation on resource-constrained ARM nodes without hardware power counters such as RAPL remains a challenge, and CPU-only models fail to capture multi-resource behavior. We present GreenPipe, an automated profiling-training-validation pipeline that builds multi-resource regression models from external power meter measurements and attributes power to containers proportionally. GreenPipe is evaluated on a Raspberry Pi 4 edge node in a K3s edge-cloud testbed, covering DNN inference with three vision models, multiple precisions, thread counts, and both local and serving scenarios. System-level MAPE is 6.3-9.4%, improving over CPU-stress and utilization-only baselines by 26.9% MAPE on average. We jointly report inference latency and energy per inference, exposing performance-energy trade-offs across workload configurations.

cs.DC↗

arXiv2026

GAPL: Grounded Action-effect Policy Learning for LLM-Based Trajectory Planning

Trajectory planning for autonomous driving requires both high-level reasoning and precise low-level control. Large Language Models (LLMs) offer semantic-rich planning capabilities, however, their application is limited by hallucinated reasoning, poor grounding in environment dynamics, and limited numerical precision in control. We propose GAPL (Grounded Action-effect Policy Learning), a unified framework that integrates LLM-based effect estimation, simulation-based effect grounding, and policy optimization into a closed-loop system. GAPL consists of three modules: (1) an LLM-based Effect Evaluator for structured multi-dimensional action-effect estimation; (2) a Simulation-based Effect Grounder that predicts dynamics-consistent effects from simulator rollouts; and (3) an Effect-Aware Decision Maker that grounds LLM effect estimates against simulation via a distiller to guide Proximal Policy Optimization (PPO)-based policy learning. Experiments on four Highway-env scenarios demonstrate that GAPL consistently outperforms baselines, achieving average reductions of {0.76, 0.86, 2.00} in collision rate, average displacement error (ADE), and final displacement error (FDE), and an average reward gain of 1.44.

cs.RO↗

arXiv2026

Empirical Analysis of GPU Frequency Behavior Under ML Workloads

This work presents ongoing research on the frequency scaling behavior of NVIDIA GPUs when executing ML/AI workloads. Our preliminary findings show that, on lower-performance GPUs, the operating frequency is strongly affected by the recent workload history, typically within an 80ms window. This behavior challenges a common assumption underlying several state-of-the-art ML latency-prediction techniques, which treat individual GPU kernel latencies as independent and therefore estimate total execution time by summing isolated per-kernel measurements. Our results indicate that such an assumption does not always hold, as the GPU's dynamic frequency scaling introduces inter-kernel dependencies. We also outline several promising directions for leveraging this observation in future work, including improved latency-prediction models, GPU kernel-reordering strategies, and NAS-driven guidelines for frequency/latency/energy-aware model design.

cs.DC↗

arXiv2026

Joint Structural Pruning and Mixed-Precision Quantization for LLM Compression

Recently, the efficiency of Large Language Models (LLMs) deployment has become a critical concern in practical applications. While post-training quantization (PTQ) and structural pruning are established techniques for reducing memory footprint and inference latency, most existing PTQ approaches optimize quantization errors on a per-layer basis, overlooking how errors accumulate and propagate through the network, often resulting in suboptimal solutions. Traditional pipelines also tend to apply pruning and quantization in isolation or sequentially, further compounding sub-optimality. We introduce a novel end-to-end framework that addresses these limitations in two key ways. First, we propose a novel mixed-precision PTQ strategy that directly minimizes global error propagation across the entire model, rather than isolating layer-wise errors. Building on this, we develop a novel joint optimization approach that simultaneously learns structural pruning decisions and mixed-precision quantization policies within a unified search space. Extensive experiments show that, at ultra-low precisions (1-3 bits), our quantization method reduces WikiText perplexity by up to 21% compared to state-of-the-art (SoTA) weight-activation quantization baselines. Against leading weight-only quantization methods, it achieves up to 59% and 85% lower perplexity on WikiText and C4, respectively. Compared to the SoTA joint pruning-and-quantization techniques, our proposed method delivers superior perplexity and reasoning performance at ultra-low bits.

cs.AI↗

arXiv2026

E2LLM: Towards Efficient LLM Serving in Heterogeneous Edge/Fog Environments

Large Language Models (LLMs) have become integral to modern applications, yet their deployment remains challenging. Beyond executing the models themselves, practical deployment must address cost efficiency, low latency, and optimal resource utilization. Conventional approaches typically assume that an entire model can be hosted on a single device, which does not hold in many real-world scenarios, particularly in Edge and Fog environments where device resources are constrained. In this paper, we introduce E2LLM, a framework designed to enable efficient LLM deployment in such resource limited settings. Rather than simply partitioning a single model across all available devices, E2LLM replicates the full model across multiple groups of devices (replicas) and applies model parallelism within each replica. Each replica is assigned a specialized role PREFILL or DECODER based on its efficiency in handling input and output tokens. This separation leverages the inherent differences between these two phases of LLM inference. To effectively organize devices, we utilize a Genetic Algorithm to form clusters that maximize system performance. Within each cluster, we apply Dynamic Programming to determine an optimal partitioning strategy that minimizes bottlenecks in model-parallel execution. Experimental results demonstrate that our approach adapts robustly to varying workloads, including scenarios with significant variation in input and output token lengths. Compared to the Splitwise baseline, E2LLM reduces average waiting time by over 50% under high-demand conditions

cs.DC↗

arXiv2026

LLM Compression with Jointly Optimizing Architectural and Quantization choices

Deploying large language models (LLMs) is challenging due to their significant memory and computational requirements. While some methods address this by developing small or tiny language models from scratch, these approaches demand extensive GPU training. Compressing pre-trained LLMs for edge devices offers a compelling alternative. Beyond pruning and quantization, Neural Architecture Search (NAS) enables effective compression, yet prior NAS approaches often limit the search space and decouple architecture from quantization. We introduce a differentiable NAS framework that explores the entire space and jointly optimizes architectural configurations alongside mixed-precision quantization for linear layers of LLMs. Experiments demonstrate superior accuracy-latency trade-offs: our models achieve up to 1.4x faster inference than sequential NAS-then-quantization baselines at comparable accuracy, or up to 6% higher average accuracy across seven reasoning tasks at equivalent latency.

cs.LG↗

arXiv2026

C-TRAIL: A Commonsense World Framework for Trajectory Planning in Autonomous Driving

Trajectory planning for autonomous driving increasingly leverages large language models (LLMs) for commonsense reasoning, yet LLM outputs are inherently unreliable, posing risks in safety-critical applications. We propose C-TRAIL, a framework built on a Commonsense World that couples LLM-derived commonsense with a trust mechanism to guide trajectory planning. C-TRAIL operates through a closed-loop Recall, Plan, and Update cycle: the Recall module queries an LLM for semantic relations and quantifies their reliability via a dual-trust mechanism; the Plan module injects trust-weighted commonsense into Monte Carlo Tree Search (MCTS) through a Dirichlet trust policy; and the Update module adaptively refines trust scores and policy parameters from environmental feedback. Experiments on four simulated scenarios in Highway-env and two real-world levelXData datasets (highD, rounD) show that C-TRAIL consistently outperforms state-of-the-art baselines, reducing ADE by 40.2%, FDE by 51.7%, and improving SR by 16.9 percentage points on average. The source code is available at https://github.com/ZhihongCui/CTRAIL.

cs.AI↗

arXiv2026

PM2Lat: Highly Accurate and Generalized Prediction of DNN Execution Latency on GPUs

We present PM2Lat, a fast and generalized framework for accurately predicting the latency of deep neural network models on GPUs, with special focus on NVIDIA. Unlike prior methods that rely on deep learning models or handcrafted heuristics, PM2Lat leverages the Single-Instruction-Multiple-Thread architecture of GPUs to model execution time of DNN models. First, we dive into fine-grained GPU operation modeling by studying computational behavior and memory access patterns. After identifying these characteristics, we found that different GPU kernels exhibit significant performance disparities, even when serving the same purpose. Hence, the core idea of PM2Lat is to differentiate kernels based on their configurations and analyze them accordingly. This kernel-aware modeling enables PM2Lat to achieve consistently low prediction error across diverse data types and hardware platforms. In addition, PM2Lat generalizes beyond standard matrix multiplication to support complex GPU kernels such as Triton, Flash Attention, and Cutlass Attention. Experimental results show that PM2Lat consistently achieves error rates below 10% across different data types and hardware platforms on Transformer models, outperforming the state-of-the-art NeuSight by 10-20% for FP32 and by at least 50% for BF16. When applying to diverse kernels, the error rate is maintained at 3-8%.

cs.PF↗

arXiv2025

Cost Optimization for Serverless Edge Computing with Budget Constraints using Deep Reinforcement Learning

Serverless computing adopts a pay-as-you-go billing model where applications are executed in stateless and shortlived containers triggered by events, resulting in a reduction of monetary costs and resource utilization. However, existing platforms do not provide an upper bound for the billing model which makes the overall cost unpredictable, precluding many organizations from managing their budgets. Due to the diverse ranges of serverless functions and the heterogeneous capacity of edge devices, it is challenging to receive near-optimal solutions for deployment cost in a polynomial time. In this paper, we investigated the function scheduling problem with a budget constraint for serverless computing in wireless networks. Users and IoT devices are sending requests to edge nodes, improving the latency perceived by users. We propose two online scheduling algorithms based on reinforcement learning, incorporating several important characteristics of serverless functions. Via extensive simulations, we justify the superiority of the proposed algorithm by comparing with an ILP solver (Midaco). Our results indicate that the proposed algorithms efficiently approximate the results of Midaco within a factor of 1.03 while our decision-making time is 5 orders of magnitude less than that of Midaco.

cs.NI↗

arXiv2024

Variational autoencoder-based neural network model compression

Variational Autoencoders (VAEs), as a form of deep generative model, have been widely used in recent years, and shown great great peformance in a number of different domains, including image generation and anomaly detection, etc.. This paper aims to explore neural network model compression method based on VAE. The experiment uses different neural network models for MNIST recognition as compression targets, including Feedforward Neural Network (FNN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM). These models are the most basic models in deep learning, and other more complex and advanced models are based on them or inherit their features and evolve. In the experiment, the first step is to train the models mentioned above, each trained model will have different accuracy and number of total parameters. And then the variants of parameters for each model are processed as training data in VAEs separately, and the trained VAEs are tested by the true model parameters. The experimental results show that using the latent space as a representation of the model compression can improve the compression rate compared to some traditional methods such as pruning and quantization, meanwhile the accuracy is not greatly affected using the model parameters reconstructed based on the latent space. In the future, a variety of different large-scale deep learning models will be used more widely, so exploring different ways to save time and space on saving or transferring models will become necessary, and the use of VAE in this paper can provide a basis for these further explorations.

cs.LG↗

arXiv2024

Context-aware Container Orchestration in Serverless Edge Computing

Adopting serverless computing to edge networks benefits end-users from the pay-as-you-use billing model and flexible scaling of applications. This paradigm extends the boundaries of edge computing and remarkably improves the quality of services. However, due to the heterogeneous nature of computing and bandwidth resources in edge networks, it is challenging to dynamically allocate different resources while adapting to the burstiness and high concurrency in serverless workloads. This article focuses on serverless function provisioning in edge networks to optimize end-to-end latency, where the challenge lies in jointly allocating wireless bandwidth and computing resources among heterogeneous computing nodes. To address this challenge, We devised a context-aware learning framework that adaptively orchestrates a wide spectrum of resources and jointly considers them to avoid resource fragmentation. Extensive simulation results justified that the proposed algorithm reduces over 95% of converge time while the end-to-end delay is comparable to the state of the art.

cs.NI↗

arXiv2022

A Survey of Security and Privacy Issues in V2X Communication Systems

Vehicle-to-Everything (V2X) communication is receiving growing attention from industry and academia as multiple pilot projects explore its capabilities and feasibility. With about 50\% of global road vehicle exports coming from the European Union (EU), and within the context of EU legislation around security and data protection, V2X initiatives must consider security and privacy aspects across the system stack, in addition to road safety. Contrary to this principle, our survey of relevant standards, research outputs, and EU pilot projects indicates otherwise; we identify multiple security and privacy related shortcomings and inconsistencies across the standards. We conduct a root cause analysis of the reasons and difficulties associated with these gaps, and categorize the identified security and privacy issues relative to these root causes. As a result, our comprehensive analysis sheds lights on a number of areas that require improvements in the standards, which are not explicitly identified in related work. Our analysis fills gaps left by other related surveys, which are focused on specific technical areas but not necessarily point out underlying root issues in standard specifications. We bring forward recommendations to address these gaps for the overall improvement of security and safety in vehicular communication.

cs.CR↗

arXiv2021

Digital Twin-Assisted Controlling of AGVs in Flexible Manufacturing Environments

Digital Twins are increasingly being introduced for smart manufacturing systems to improve the efficiency of the main disciplines of such systems. Formal techniques, such as graphs, are a common way of describing Digital Twin models, allowing broad types of tools to provide Digital Twin based services such as fault detection in production lines. Obtaining correct and complete formal Digital Twins of physical systems can be a complicated and time consuming process, particularly for manufacturing systems with plenty of physical objects and the associated manufacturing processes. Automatic generation of Digital Twins is an emerging research field and can reduce time and costs. In this paper, we focus on the generation of Digital Twins for flexible manufacturing systems with Automated Guided Vehicles (AGVs) on the factory floor. In particular, we propose an architectural framework and the associated design choices and software development tools that facilitate automatic generation of Digital Twins for AGVs. Specifically, the scope of the generated digital twins is controlling AGVs in the factory floor. To this end, we focus on different control levels of AGVs and utilize graph theory to generate the graph-based Digital Twin of the factory floor.

cs.RO↗

arXiv2021

Active Learning for Network Traffic Classification: A Technical Study

Network Traffic Classification (NTC) has become an important feature in various network management operations, e.g., Quality of Service (QoS) provisioning and security services. Machine Learning (ML) algorithms as a popular approach for NTC can promise reasonable accuracy in classification and deal with encrypted traffic. However, ML-based NTC techniques suffer from the shortage of labeled traffic data which is the case in many real-world applications. This study investigates the applicability of an active form of ML, called Active Learning (AL), in NTC. AL reduces the need for a large number of labeled examples by actively choosing the instances that should be labeled. The study first provides an overview of NTC and its fundamental challenges along with surveying the literature on ML-based NTC methods. Then, it introduces the concepts of AL, discusses it in the context of NTC, and review the literature in this field. Further, challenges and open issues in AL-based classification of network traffic are discussed. Moreover, as a technical survey, some experiments are conducted to show the broad applicability of AL in NTC. The simulation results show that AL can achieve high accuracy with a small amount of data.

cs.NI↗

arXiv2021

A Comprehensive Survey on 6G Networks:Applications, Core Services, Enabling Technologies, and Future Challenges

Cellular Internet of Things (IoT) is considered as de facto paradigm to improve the communication and computation systems. Cellular IoT connects massive number of physical and virtual objects to the Internet using cellular networks. The latest generation of cellular networks, e.g. fifth-generation (5G), use evolutionary and revolutionary technologies to notably improve the performance of wireless networks. However, given the envisioned new use-cases, e.g., holographic communication, and the ever-increasing deployment of massive smart-physical end-devices in IoT, the volume of network traffic has considerably raised, and therefore, the current generation of mobile networks cannot wholly meet the ever-increasing demands. Hence, it is envisioned that the next generation, sixth generation (6G) networks, need to play a critical role to alleviate such challenges in IoT by providing new communication services, network capacity, and ultra-low latency communications (uRLLC). In this paper, first, the need for 6G networks is discussed. Then, the potential 6G requirements and trends, as well as the latest research activities related to 6G are introduced e.g., Tactile Internet and Terahertz (THz). Furthermore, the key performance indicators, applications, new services, and the potential key enabling technologies for 6G networks are presented. Finally, several potential unresolved challenges for future 6G networks are presented.

cs.NI↗