论文标题
部分可观测时空混沌系统的无模型预测
D2D Multi-hop Energy Efficiency Toward EMS in B5G
论文作者
论文摘要
储层计算是预测湍流的有力工具，其简单的架构具有处理大型系统的计算效率。然而，其实现通常需要完整的状态向量测量和系统非线性知识。我们使用非线性投影函数将系统测量扩展到高维空间，然后将其输入到储层中以获得预测。我们展示了这种储层计算网络在时空混沌系统上的应用，该系统模拟了湍流的若干特征。我们表明，使用径向基函数作为非线性投影器，即使只有部分观测并且不知道控制方程，也能稳健地捕捉复杂的系统非线性。最后，我们表明，当测量稀疏、不完整且带有噪声，甚至控制方程变得不准确时，我们的网络仍然可以产生相当准确的预测，从而为实际湍流系统的无模型预测铺平了道路。
Beyond fifth generation (B5G), communication has attracted much attention from academia, industry, and mobile network operators due to network densification, ultra-low latency communication, and enhanced energy and spectrum efficiency. However, a post-disaster emergency management system (EMS), which increasingly relies heavily on wireless communication infrastructure, is falling far behind in innovation and funding. Because the B5G concept represents a telecommunications industry revolution, EMS provisioning is intended to be dispersed, autonomous, and robust to network weaknesses caused by human and natural calamities. When the network is congested, partially functioning, or entirely isolated, we provide multi-device-to-device (D2D) communication to extend the communication coverage area with improved energy efficiency. Furthermore, we examine D2D multi-hop energy efficiency performance in the proposed network. The results demonstrate that the improved D2D multi-hop energy efficiency can improve the EMS effectively and efficiently in extending the coverage area and enhancing energy efficiency. Moreover, the proposed approach has been proven to increase energy efficiency, which acts as a suitable network design to recover from natural disasters and potentially save many lives
