The evolving landscape of edge computing envisions platforms operating as dynamic intermediaries between application providers and edge servers (ESs), where task offloading is coupled with payments for computational services. Ensuring efficient resource utilization and meeting stringent Quality of Service (QoS) requirements necessitates incentivizing ESs while optimizing the platforms operational objectives. This paper investigates a multi-agent system where both the platform and ESs are self-interested entities, addressing the joint optimization of revenue maximization, resource allocation, and task offloading. We propose a novel Stackelberg game-based framework to model interactions between stakeholders and solve the optimization problem using a Bayesian Optimization-based centralized algorithm. Recognizing practical challenges in information collection due to privacy concerns, we further design a decentralized solution leveraging neural network optimization and a privacy-preserving information exchange protocol. Extensive numerical evaluations demonstrate the effectiveness of the proposed mechanisms in achieving superior performance compared to existing baselines.

翻译：边缘计算的发展前景是将平台视为应用提供商与边缘服务器（ES）之间的动态中介，其中任务卸载与计算服务支付相结合。为确保高效的资源利用并满足严格的服务质量（QoS）要求，需要在优化平台运营目标的同时激励ES参与。本文研究一个多智能体系统，其中平台与ES均为自利实体，旨在协同优化收益最大化、资源分配与任务卸载。我们提出一种新颖的基于斯塔克尔伯格博弈的框架来建模利益相关者间的交互，并采用基于贝叶斯优化的集中式算法求解该优化问题。针对实际中因隐私问题导致信息收集的挑战，我们进一步设计了去中心化解决方案，该方案结合神经网络优化与隐私保护信息交换协议。大量数值评估表明，相较于现有基线方法，所提机制在实现更优性能方面具有显著效果。