Journal of Reliable Intelligent Environments Прикладные компьютерные науки
Reliability-aware energy minimization in vehicular edge-cloud continuum via risk-sensitive federated orchestration
Аннотация
Vehicular edge computing (VEC) supports latency-sensitive and computation-intensive workloads for intelligent transportation. Existing VEC optimization frameworks mostly minimize latency or energy in isolation and give limited attention to reliability under stochastic vehicular conditions. This paper proposes a reliability-aware energy minimization framework for a multi-tier vehicular edge–cloud continuum comprising vehicles, roadside units (RSUs), edge servers and a cloud-hosted federated aggregator. A joint stochastic optimization problem minimizes expected energy plus a conditional value-at-risk (CVaR) penalty on a failure cost, subject to per-task reliability targets, under stochastic mobility, time-varying wireless channels and node failures. The solution combines Lagrangian decomposition for the continuous resource allocation with a risk-sensitive federated reinforcement learning (FedRL) algorithm for the binary offloading decisions. In SUMO/OMNeT++/Veins simulations at 80 vehicles/km $$^2$$ 2 , the framework reduces per-task energy by 3.7–40.0% relative to four baselines (3.7% against the risk-neutral FedRL variant, 6.4% against an energy-only scheme, 23.0% against a latency-aware scheme and 40.0% against a greedy heuristic) while achieving a 97.3% task success rate; its CVaR $$_{0.95}$$ 0.95 of per-task energy is 21.3–46.1% lower than that of the baselines. At the highest density tested (120 vehicles/km $$^2$$ 2 ) the success rate is 94.7%, against 89.1% for the risk-neutral variant. The evidence is simulation-based, and the assumptions and limitations are stated in Sect. 8 .