Zero Touch Predictive Orchestration: Automating Time-Series Models for the Cloud-Edge Continuum

2026-06-08

AI Summary

This work addresses the challenge of time-series forecasting in cloud-edge continua, where newly deployed nodes lack sufficient historical data for model training and generic models fail to capture node-specific hardware and software behaviors. To overcome this cold-start problem, the authors propose a fully automated prediction framework that employs a lightweight resource profiler to dynamically collect local telemetry data. They introduce a novel approach that fuses sparse local observations with the high-resolution public dataset TimeTrack and leverages neural architecture search (NAS) to automatically generate accurate, technology-agnostic forecasting models. Experimental results demonstrate that the proposed method significantly outperforms alternatives relying solely on local data, generic models, or standard surrogate datasets across key metrics—MSE, MAE, and MAPE—thereby enhancing prediction accuracy and accelerating model convergence.

Abstract

The Cloud-Edge Continuum (CEC) enables latency-critical applications by distributing resources to the far edge, but its extreme volatility makes proactive Zero Touch Management via time-series forecasting essential. However, orchestrators face a severe "cold start" problem: newly discovered nodes lack the historical data required to train localized predictive models, while generalized models fail to capture unique hardware and microservice behaviors. To solve this, we propose a fully automated time-series prediction architecture driven by a novel data-mixing methodology. At the infrastructure level, we introduce a lightweight, technology-agnostic Resource Exposer (RE) that dynamically discovers nodes and continuously collects customizable telemetry (e.g., compute, network, energy). To overcome the sparsity of these initial local samples, our framework automatically merges them with TimeTrack, our publicly available, high-resolution dataset collected at 45-second intervals. This synergizes TimeTrack's foundational, high-frequency temporal patterns with the precise calibration of the local node data. Processed through a Neural Architecture Search (NAS) engine, the system automatically generates highly accurate baseline models. Experimental results demonstrate that merging the target data with TimeTrack effectively mitigates the cold start challenge. This integration significantly improves forecasting accuracy measured in Mean Squared Error (MSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) and accelerates convergence compared to training on the sparse local samples alone, training solely on generic datasets, or mixing the target data with standard alternative datasets, establishing a robust foundation for continuous MLOps deployment.

Problem

• Cloud-Edge Continuum
• cold start
• time-series forecasting
• predictive orchestration
• Zero Touch Management

Innovation

• Zero Touch Management
• Cold Start Problem
• Data Mixing
• Neural Architecture Search
• Cloud-Edge Continuum