In this paper, we study relay selection and power allocation in two-way relaying networks consisting of a source, a destination and multiply half-duplex decode-and-forward (DF) relays. A transmission model with three time subslots is purposely introduced. In the first subslot, selected relay applies time-switching protocol to harvest radio frequency energy radiated by source and destination; in the remaining subslots, selected relay facilitates source and destination to exchange information. Due to finite-size data buffer and finite-size battery of relay, an optimal relay selection and power allocation policy is proposed, in order to maximize networks sum-throughput. One obstacle is the inherent non-convex property of the underlying sum-throughput optimization problem. By carefully decoupling the multiplicative variables and relaxing binary variable to a real number, we convert this problem into a convex optimization one and then Karush-Kuhn-Tucker (KKT) conditions are used to solve it. Extensive simulations have been conducted to demonstrate the improved sum-throughput with our proposed strategy.

翻译：在本文中,我们研究双向中继网络中的继电器选择和电力分配,由源、目的地和半双倍的分解分解-前向(DF)继电器组成。特意引入了一个具有3个时间子线的传输模式。在第一个子行中,选定继电器应用时间转换协议来收获源和目的地辐射的无线电频率能源;在其余的子行中,选定的继电器为交换信息的源和目的地提供便利。由于数据缓冲的有限和中继的有限尺寸电池,提出了最佳的中继选择和权力分配政策,以最大限度地扩大网络和通量。一个障碍是基础总吞吐优化问题的内在非电流属性。通过仔细拆分多倍变量和将二进变量放松到一个真实数字,我们将这一问题转换成一个螺旋式优化器,然后用Karush-Kuhn-Tuck(KKTT)的条件来解决这个问题。已经进行了广泛的模拟,以展示我们拟议战略的改进的平流。