Skip to content
#edge computing Open access

Self-Evolving Virtual Network Orchestration From Devices to Cloud Over Shared Infrastructure for Dynamic Services

Dec 2026 · IEEE Transactions on Mobile Computing · Vol 25, pp. 22745-22761 · 0 citations · 34 references

TL;DR

A self-evolving dual-timescale VCNI orchestration framework to coordinate long-timescale inter-VCNI resource provisioning and short-timescale intra-VCNI user scheduling is proposed and a self-adaptive soft actor-critic algorithm, referred to as SaSAC is designed.

Abstract

End-to-end virtual computing network instance (VCNI) orchestration over shared device-to-cloud infrastructure is essential for supporting heterogeneous services with limited physical resources. However, existing network slicing, virtualization, and edge computing approaches usually focus on partial resource management or fixed orchestration intervals, and often neglect adaptive coordination across the full VCNI lifecycle. Motivated by this, we consider a dynamic device-to-cloud VCNI orchestration scenario that jointly accounts for heterogeneous service demands, wireless spectrum resources, cloud computing resources, and reconfiguration overhead. We propose a self-evolving dual-timescale VCNI orchestration framework to coordinate long-timescale inter-VCNI resource provisioning and short-timescale intra-VCNI user scheduling. The framework adaptively adjusts the VCNI reconfiguration frequency according to workload variations, thereby balancing resource consumption, reconfiguration overhead, and task failure penalties. To tackle this problem, we formulate the orchestration process as a hierarchical Markov decision process (MDP) and design a self-adaptive soft actor-critic algorithm, referred to as SaSAC. SaSAC adopts dual-timescale policies and shared twin critics to learn coordinated orchestration decisions under dynamic service states. Experimental results show that SaSAC achieves lower system cost and higher task success rate than learning-based and heuristic baselines. Moreover, additional ablation and post-training results further validate the effectiveness of SaSAC under varying system conditions and dynamic service demands.

Read PDF

Similar papers

#computer vision Review Sep 2017

Agile Software Development Methods: Review and Analysis

This publication proposes a definition and a classification of agile software development approaches and analyses ten software development methods that can be characterized as being "agile" against the defined criterion.

P. Abrahamsson, O. Salo, Jussi Ronkainen et al. · 727 citations · ⚡54
#computer vision Jun 2008

The impact of agile practices on communication in software development

The study shows that agile practices improve both informal and formal communication, but indicates that, in larger development situations involving multiple external stakeholders, a mismatch of adequate communication mechanisms can sometimes even hinder the communication.

M. Pikkarainen, Jukka Haikara, O. Salo et al. · 401 citations · ⚡48
#machine learning Review Open access Oct 2014

Software development in startup companies: A systematic mapping study

The results indicate that software engineering work practices are chosen opportunistically, adapted and configured to provide value under the constrains imposed by the startup context.

Nicolò Paternoster, Carmine Giardino, M. Unterkalmsteiner et al. · 394 citations · ⚡54

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

Microsoft Research Blog Oct 29, 2026

Microsoft Research Focus – Edition #97

Host Sowbhagya Suresh shares some of the latest news and cutting-edge research from across Microsoft—from understanding the challenges facing coding agents to uncovering how people use AI at work and improving extended-range weather forecasting. The post Microsoft Research Focus – Edition #97 appeared first on Microsoft Research.

MIT News · Artificial Intelligence Oct 28, 2026

Making machines that can listen

Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.