从优化到学习:面向空中边缘计算的双方法资源分配(在执行不确定性下)
From Optimization to Learning: Dual-Approach Resource Allocation for Over-the-Air Edge Computing Under Execution Uncertainty
AI总结:
本文提出一种双方法框架,结合优化与深度强化学习,解决空中边缘计算中执行不确定性下的资源分配问题,通过优化获得基础洞察,利用学习实现实时适应性。
摘要:
随着移动设备和数据密集型应用在未来无线网络中的指数级增长,对资源受限设备的计算负担显著增加,从而催生了空中计算(AirComp)作为边缘智能的变革性范式。为了提高AirComp系统的效率和可扩展性,本文提出了一种全面的双方法框架,系统地从传统的数学优化过渡到深度强化学习(DRL)进行资源分配,以应对执行不确定性。具体而言,我们建立了一个严谨的系统模型,通过Gamma分布的计算工作负载捕捉执行不确定性,导致涉及复杂Gamma函数的具有挑战性的非线性优化问题。对于单用户场景,我们设计了先进的块坐标下降(BCD)和最大化解(MM)算法,这些算法能够产生半闭合形式的解,并具有可证明的性能保证。然而,传统优化方法在动态多用户环境中由于用户间干扰和资源竞争变得计算上不可行。为此,我们引入了一种基于深度Q网络(DQN)的DRL框架,能够通过环境交互自适应地学习最优策略。我们的双方法有效地弥合了分析可处理性和自适应智能之间的差距,利用优化获得基础洞察,并利用学习实现实时适应性。广泛的数值结果证实了通过增加边缘服务器密度所获得的性能提升,并验证了我们的优化到学习范式在下一代AirComp系统中的优越性。
英文摘要:
The exponential proliferation of mobile devices and data-intensive applications in future wireless networks imposes substantial computational burdens on resource-constrained devices, thereby fostering the emergence of over-the-air computation (AirComp) as a transformative paradigm for edge intelligence.} To enhance the efficiency and scalability of AirComp systems, this paper proposes a comprehensive dual-approach framework that systematically transitions from traditional mathematical optimization to deep reinforcement learning (DRL) for resource allocation under execution uncertainty. Specifically, we establish a rigorous system model capturing execution uncertainty via Gamma-distributed computational workloads, resulting in challenging nonlinear optimization problems involving complex Gamma functions. For single-user scenarios, we design advanced block coordinate descent (BCD) and majorization-maximization (MM) algorithms, which yield semi-closed-form solutions with provable performance guarantees. However, conventional optimization approaches become computationally intractable in dynamic multi-user environments due to inter-user interference and resource contention. To this end, we introduce a Deep Q-Network (DQN)-based DRL framework capable of adaptively learning optimal policies through environment interaction. Our dual methodology effectively bridges analytical tractability with adaptive intelligence, leveraging optimization for foundational insight and learning for real-time adaptability. Extensive numerical results corroborate the performance gains achieved via increased edge server density and validate the superiority of our optimization-to-learning paradigm in next-generation AirComp systems.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。