VoXaaS: Safety-governed service orchestration with risk-aware volunteering for vehicular micro-edge computing

Document Type

Article

Source of Publication

Future Generation Computer Systems

Publication Date

3-1-2027

Abstract

Vehicular Edge Computing (VEC) enables connected vehicles to collaboratively provide sensing and computing services beyond their primary driving functions. However, existing orchestration approaches mostly optimize Quality-of-Service (QoS) metrics and treat vehicles as generic resource providers, without explicitly considering real-time driving safety. This may result in unsafe service participation under demanding traffic or operational conditions. To address this limitation, we propose VoXaaS (Vehicle-oriented eXecution as a Service), a safety-governed vehicular micro-edge computing framework that regulates service participation according to driving risk, resource availability, and provider reliability. The framework introduces Safety-Aware Volunteering (SAV), a continuous risk-driven mechanism for regulating participation in cooperative service execution. SAV determines service eligibility, contribution type, and contribution capacity while ensuring that safety constraints remain dominant over service optimization objectives. VoXaaS further combines risk-aware provider qualification with trust- and QoS-aware orchestration to support dependable cooperative vehicular services. We evaluate the proposed framework through extensive simulations using realistic vehicular mobility traces and increasing service demand levels. Experimental results show that VoXaaS reduces selected-provider risk by more than 80% compared with QoS-based and trust-based orchestration baselines while completely eliminating unsafe volunteering. Unlike conventional safety-preserving approaches that rely on admission throttling, VoXaaS maintains full task admission under increasing service load. As a result, it achieves the highest task success rate and delivers up to 14% higher throughput than competing approaches while incurring only moderate latency overhead. The results demonstrate that explicit safety governance can significantly improve orchestration dependability while maintaining strong service performance under the evaluated service-load conditions. By tightly integrating safety-aware volunteering, elastic trust regulation, and real-time driving risk into service orchestration, VoXaaS provides a step toward dependable and safety-governed vehicular micro-edge ecosystems.

ISSN

0167-739X

Publisher

Elsevier BV

Volume

188

Disciplines

Computer Sciences

Keywords

Connected vehicles, Micro-edge services, Safety-aware volunteering, Service orchestration, Trust-aware orchestration, Vehicular edge computing

Scopus ID

105052574444

Indexed in Scopus

yes

Open Access

no

Link to Full Text

Share

COinS