In this paper, we study the resource allocation in D2D underlaying cellular network with uncertain channel state information (CSI). For satisfying the minimum rate requirement for cellular user and the reliability requirement for D2D user, we attempt to maximize the cellular user’s throughput whilst ensuring a chance constraint for D2D. Then, a robust resource allocation framework is proposed for solving the highly intractable chance constraint, where the CSI uncertainties are represented as a deterministic set and the reliability requirement is enforced to hold for any CSI within it. Then, a symmetrical-geometry-based learning approach is developed to model the uncertain CSI into polytope, ellipsoidal and box. After that, the chance constraint under these uncertainty sets is transformed into computation convenient convex constraints. To overcome the conservatism of symmetrical-geometry-based approach, we develop a support vector clustering (SVC)-based approach to model uncertain CSI as a compact convex uncertainty set. Based on that, the chance constraint is converted into a linear convex set. Then, we develop a bisection search-based power allocation algorithm for solving the resource allocation in D2D underlaying cellular network with the obtained convex constraints. Finally, we conduct the simulation to compare the proposed robust optimization approaches with the non-robust one.

中文翻译：

---

面向 D2D 底层蜂窝网络的基于学习的鲁棒资源分配

在本文中，我们研究了具有不确定信道状态信息（CSI）的 D2D 底层蜂窝网络中的资源分配。为了满足蜂窝用户的最低速率要求和D2D用户的可靠性要求，我们试图最大化蜂窝用户的吞吐量，同时确保D2D的机会约束。然后，提出了一个鲁棒的资源分配框架来解决高度棘手的机会约束，其中 CSI 不确定性表示为一个确定性集合，并且强制执行可靠性要求以适用于其中的任何 CSI。然后，开发了一种基于对称几何的学习方法，将不确定的 CSI 建模为多面体、椭圆体和盒子。之后，将这些不确定集下的机会约束转化为计算方便的凸约束。为了克服基于对称几何方法的保守性，我们开发了一种基于支持向量聚类 (SVC) 的方法，将不确定的 CSI 建模为紧凑的凸不确定性集。在此基础上，机会约束被转换为线性凸集。然后，我们开发了一种基于二等分搜索的功率分配算法，用于解决具有获得的凸约束的 D2D 底层蜂窝网络中的资源分配问题。最后，我们进行模拟以比较所提出的鲁棒优化方法与非鲁棒优化方法。我们开发了一种基于二等分搜索的功率分配算法，用于解决具有获得凸约束的 D2D 底层蜂窝网络中的资源分配问题。最后，我们进行模拟以比较所提出的鲁棒优化方法与非鲁棒优化方法。我们开发了一种基于二等分搜索的功率分配算法，用于解决具有获得凸约束的 D2D 底层蜂窝网络中的资源分配问题。最后，我们进行模拟以比较所提出的鲁棒优化方法与非鲁棒优化方法。