arXiv subjects

Demetris Trihinas

Publications and source records attributed to Demetris Trihinas.

4 recordsLinked to original sources

arXiv2026

Evaluating Accuracy and Probabilistic Reliability of Zero-Shot Time Series Foundation Models

Time Series Foundation Models (TSFMs) promise a paradigm shift toward zero-shot forecasting by eliminating task-specific training. However, existing works often overlook trade-offs between predictive accuracy and probabilistic calibration. This paper presents a benchmark study of six TSFMs evaluated on energy, traffic, and financial datasets. We contrast their performance against statistical baselines and a supervised DL model. The study reveals that while TSFMs outperform statistical methods and supervised models, they are subject to a fundamental trade-off between point accuracy and probabilistic reliability. Specifically, xLSTM architectures provide robust probabilistic calibration across horizons. In contrast, patch-based transformers offer competitive accuracy but face calibration issues at long horizons, while transformer-based models exhibit context saturation points for optimal zero-shot reasoning. These findings offer evidence-based guidance for balancing generalization and uncertainty quantification in real-world deployments.

cs.LG↗

arXiv2026

A Measurement Study of LLM Inference Trade-offs Across Edge Continuum Hardware

Large language models (LLMs) are increasingly used as backends for intelligent web services, but serving them across the edge continuum requires balancing quality, latency, model footprint, and energy. This paper presents a controlled measurement study of self-hosted LLM inference across edge and near-edge deployment nodes: an NVIDIA Jetson AGX Orin and a near-edge server with CPU-only and GPU-enabled inference modes. We evaluate multiple open-weight LLMs and quantization variants using a fixed question-answering workload, and compare them against GPT-4o as a cloud-hosted accuracy and latency reference. Our benchmarking pipeline reports accuracy, model footprint, per-token decoding latency, prefill latency, and overall execution energy. The results show that GPU-enabled server execution provides the lowest compute-side latency, while Jetson Orin shows lower measured energy, consistent with its lower platform power under our setup. CPU-only execution is consistently dominated in latency for our workload and shows higher measured energy. We also show that parameter count and downloaded weight-file size alone do not reliably predict observed accuracy or latency. Finally, using Pareto-frontier analysis, we study how deployment decisions may change under possible streamed-token delivery overheads, highlighting that compute-side inference metrics alone can lead to suboptimal placement for latency-sensitive interactive web services.

cs.DC↗

arXiv2023

Towards Energy Consumption and Carbon Footprint Testing for AI-driven IoT Services

Energy consumption and carbon emissions are expected to be crucial factors for Internet of Things (IoT) applications. Both the scale and the geo-distribution keep increasing, while Artificial Intelligence (AI) further penetrates the "edge" in order to satisfy the need for highly-responsive and intelligent services. To date, several edge/fog emulators are catering for IoT testing by supporting the deployment and execution of AI-driven IoT services in consolidated test environments. These tools enable the configuration of infrastructures so that they closely resemble edge devices and IoT networks. However, energy consumption and carbon emissions estimations during the testing of AI services are still missing from the current state of IoT testing suites. This study highlights important questions that developers of AI-driven IoT services are in need of answers, along with a set of observations and challenges, aiming to help researchers designing IoT testing and benchmarking suites to cater to user needs.

cs.DC↗

arXiv2020

A Self-stabilizing Control Plane for the Edge and Fog Ecosystems

Fog Computing is now emerging as the dominating paradigm bridging the compute and connectivity gap between sensing devices (a.k.a. "things") and latency-sensitive services. However, as fog deployments scale by accumulating numerous devices interconnected over highly dynamic and volatile network fabrics, the need for self-configuration and self-healing in the presence of failures is more evident now than ever. Using the prevailing methodology of self-stabilization, we propose a fault-tolerant framework for distributed control planes that enables fog services to cope and recover from a very broad fault model. Specifically, our model considers network uncertainties, packet drops, node fail-stop failures, and violations of the assumptions according to which the system was designed to operate, such as an arbitrary corruption of the system state. Our self-stabilizing algorithms guarantee automatic recovery within a constant number of communication rounds without the need for external (human) intervention. To showcase the framework's effectiveness, the correctness proof of the proposed self-stabilizing algorithmic process is accompanied by a comprehensive evaluation featuring an open and reproducible testbed utilizing real-world data from the intelligent transportation domain. Results show that our framework ensures a fog ecosystem recovery from faults in constant time, analytics are computed correctly, while the overhead to the system's control plane scales linearly towards the IoT load.

cs.DC↗