FUSION: Forecast-Embedded Agent Scheduling with Service Incentive Optimization over Distributed Air-Ground Edge Networks
Houyi Qi, Minghui Liwang, Seyyedali Hosseinalipour, Liqun Fu, Sai Zou, Xianbin Wang, Wei Ni, Yiguang Hong
TL;DR
FUSION tackles the challenge of provisioning compute in air-ground edge networks with heterogeneous HU/MU workloads and mobility-constrained APs by marrying forecasting, routing, and incentive design. The offline stage uses Pro-LNN for demand forecasting, eACO-VRP for APO routing, and Off-AIC^2 for matching ESs and APs with incentive-compatible contracts, aimed at maximizing social welfare. The online stage models task scheduling as an ordinal potential game (PG-BRD) among HU/MU SDs and SPs (ESs/APs), ensuring convergence to a Nash equilibrium while balancing delay, energy, and capacity constraints. Experiments on synthetic and real data show FUSION achieves higher social welfare and efficient resource utilization with near-truthful offline contracting and competitive online performance, highlighting its practical viability for large-scale, heterogeneous air-ground edge ecosystems.
Abstract
In this paper, we introduce a first-of-its-kind forecasting-driven, incentive-inherent service provisioning framework for distributed air-ground integrated networks that explicitly accounts for human-machine coexistence. In our framework, vehicular-UAV agent pairs (APs) are proactively dispatched to overloaded hotspots to augment the computing capacity of edge servers (ESs), which in turn gives rise to a set of challenges that we jointly address: highly uncertain spatio-temporal workloads, spatio-temporal coupling between road traffic and UAV capacity, forecast-driven contracting risks, and heterogeneous quality-of-service (QoS) requirements of human users (HUs) and machine users (MUs). To address these challenges, we propose FUSION, a two-stage optimization framework, consisting of an offline stage and an online stage. In the offline stage, a liquid neural network-powered module performs multi-step spatio-temporal demand forecasting at distributed ESs, whose outputs are exploited by an enhanced ant colony optimization-based routing scheme and an auction-based incentive-compatible contracting mechanism, to jointly determine ES-AP contracts and pre-planned service routes. In the online stage, we formulate the congestion-aware task scheduling as a potential game among HUs, MUs, and heterogeneous ES/UAVs, and devise a potential-guided best-response dynamics algorithm that provably converges to a pure-strategy Nash equilibrium. Experiments on both synthetic and real-world datasets show that FUSION consistently achieves higher social welfare and improved resource utilization, while maintaining latency and energy costs comparable to state-of-the-art baselines and preserving individual rationality, budget balance, and near-truthfulness.