能量收集网络的快速收敛学习辅助控制
Fast-Convergent Learning-aided Control in Energy Harvesting Networks
摘要：
在本文中，我们提出了一种新的学习辅助能量管理方案（$\mathtt{LEM}$）的多跳能量收集网络。与该问题的先前工作不同，我们的算法通过称为\emph{perturbed dual learning}的步骤显式地将信息学习纳入系统控制中。$\mathtt{LEM}$不需要系统动态的任何统计信息来实现，并且有效地解决了具有挑战性的能量中断问题。我们发现，$\mathtt{LEM}$实现了接近最佳的$[O(ε), O(\log(1/ε)^2)]$效用延迟权衡与$O(1/ε^{1-c/2})$能量缓冲区（$c\in(0,1)$）。更有趣的是，$\mathtt{LEM}$拥有$O(1/ε^{1-c/2} +1/ε^c)$的\emph{convergence time}，这比纯粹基于数据的技术的$Θ(1/ε)$时间或纯粹依赖于学习系统统计的方法的$Θ(1/ε^2)$时间快得多。这种快速收敛特性使得$\mathtt{LEM}$在动态环境中的资源分配中更具自适应性和效率。$\mathtt{LEM}$的设计和分析演示了如何通过学习来增强系统控制算法，以及其好处是什么。该方法和算法也可以应用于类似的问题，例如，处理网络，其中节点需要非零数量的内容来支持它们的动作。
英文摘要：
In this paper, we present a novel learning-aided energy management scheme ($\mathtt{LEM}$) for multihop energy harvesting networks. Different from prior works on this problem, our algorithm explicitly incorporates information learning into system control via a step called \emph{perturbed dual learning}. $\mathtt{LEM}$ does not require any statistical information of the system dynamics for implementation, and efficiently resolves the challenging energy outage problem. We show that $\mathtt{LEM}$ achieves the near-optimal $[O(ε), O(\log(1/ε)^2)]$ utility-delay tradeoff with an $O(1/ε^{1-c/2})$ energy buffers ($c\in(0,1)$). More interestingly, $\mathtt{LEM}$ possesses a \emph{convergence time} of $O(1/ε^{1-c/2} +1/ε^c)$, which is much faster than the $Θ(1/ε)$ time of pure queue-based techniques or the $Θ(1/ε^2)$ time of approaches that rely purely on learning the system statistics. This fast convergence property makes $\mathtt{LEM}$ more adaptive and efficient in resource allocation in dynamic environments. The design and analysis of $\mathtt{LEM}$ demonstrate how system control algorithms can be augmented by learning and what the benefits are. The methodology and algorithm can also be applied to similar problems, e.g., processing networks, where nodes require nonzero amount of contents to support their actions.
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。
