The key technologies involved in the evolution of the Cloud-based Radio Access Network(C-RAN) are discussed in this paper. Taking the Frameless Network Architecture(FNA) as a starting point, a cell-lessbased network t...The key technologies involved in the evolution of the Cloud-based Radio Access Network(C-RAN) are discussed in this paper. Taking the Frameless Network Architecture(FNA) as a starting point, a cell-lessbased network topology for a multi-tier Heterogeneous Network(Het Net) and ultra-dense network is proposed. The FNA network topology modeling is researched with centralized processing and distributed antenna deployments. The Antenna Element(AE) is released as a new dimensional radio resource that is included in the centralized Radio Resource Management(RRM) processes. This contributes to the on-demand user-centric serving-set associations with cell-edge effect elimination. The Control Plane(CP) and User Plane(UP) separation and adaptation are introduced for energy efficiency improvements. The centralized RRM and different optimization goals are discussed for fully exploring the merits from the centralized computing of C-RAN. Considering the complexity, near-optimal approaches for specific users' Quality-of-Service(Qo S) requirements are addressed. Finally, based on the research highlighted above, the way forward of C-RAN evolution is discussed.展开更多
Three recent breakthroughs due to AI in arts and science serve as motivation:An award winning digital image,protein folding,fast matrix multiplication.Many recent developments in artificial neural networks,particularl...Three recent breakthroughs due to AI in arts and science serve as motivation:An award winning digital image,protein folding,fast matrix multiplication.Many recent developments in artificial neural networks,particularly deep learning(DL),applied and relevant to computational mechanics(solid,fluids,finite-element technology)are reviewed in detail.Both hybrid and pure machine learning(ML)methods are discussed.Hybrid methods combine traditional PDE discretizations with ML methods either(1)to help model complex nonlinear constitutive relations,(2)to nonlinearly reduce the model order for efficient simulation(turbulence),or(3)to accelerate the simulation by predicting certain components in the traditional integration methods.Here,methods(1)and(2)relied on Long-Short-Term Memory(LSTM)architecture,with method(3)relying on convolutional neural networks.Pure ML methods to solve(nonlinear)PDEs are represented by Physics-Informed Neural network(PINN)methods,which could be combined with attention mechanism to address discontinuous solutions.Both LSTM and attention architectures,together with modern and generalized classic optimizers to include stochasticity for DL networks,are extensively reviewed.Kernel machines,including Gaussian processes,are provided to sufficient depth for more advanced works such as shallow networks with infinite width.Not only addressing experts,readers are assumed familiar with computational mechanics,but not with DL,whose concepts and applications are built up from the basics,aiming at bringing first-time learners quickly to the forefront of research.History and limitations of AI are recounted and discussed,with particular attention at pointing out misstatements or misconceptions of the classics,even in well-known references.Positioning and pointing control of a large-deformable beam is given as an example.展开更多
基于复杂网络的拓扑结构优化理论与禁忌搜索算法，结合指挥控制系统的特点，建立了优化最优指挥与控制系统网络结构（Command and Control Architecture Network，C2AN）模型，并以复杂网络的网络效率和网络成本分别描述C2AN中的信息传...基于复杂网络的拓扑结构优化理论与禁忌搜索算法，结合指挥控制系统的特点，建立了优化最优指挥与控制系统网络结构（Command and Control Architecture Network，C2AN）模型，并以复杂网络的网络效率和网络成本分别描述C2AN中的信息传播效率及构建C2AN的资源消耗，建立优化的目标函数，通过禁忌搜索算法获得了最优的C2AN。最后通过仿真实例，分析了最优C2AN生成过程及其基本统计特征。展开更多
基金supported by the National High Technology Research and Development Program of China No.2014AA01A701Nature and Science Foundation of China under Grants No.61471068,61421061+2 种基金Beijing Nova Programme No.Z131101000413030International Collaboration Project No.2015DFT10160National Major Project No.2016ZX03001009-003
文摘The key technologies involved in the evolution of the Cloud-based Radio Access Network(C-RAN) are discussed in this paper. Taking the Frameless Network Architecture(FNA) as a starting point, a cell-lessbased network topology for a multi-tier Heterogeneous Network(Het Net) and ultra-dense network is proposed. The FNA network topology modeling is researched with centralized processing and distributed antenna deployments. The Antenna Element(AE) is released as a new dimensional radio resource that is included in the centralized Radio Resource Management(RRM) processes. This contributes to the on-demand user-centric serving-set associations with cell-edge effect elimination. The Control Plane(CP) and User Plane(UP) separation and adaptation are introduced for energy efficiency improvements. The centralized RRM and different optimization goals are discussed for fully exploring the merits from the centralized computing of C-RAN. Considering the complexity, near-optimal approaches for specific users' Quality-of-Service(Qo S) requirements are addressed. Finally, based on the research highlighted above, the way forward of C-RAN evolution is discussed.
文摘Three recent breakthroughs due to AI in arts and science serve as motivation:An award winning digital image,protein folding,fast matrix multiplication.Many recent developments in artificial neural networks,particularly deep learning(DL),applied and relevant to computational mechanics(solid,fluids,finite-element technology)are reviewed in detail.Both hybrid and pure machine learning(ML)methods are discussed.Hybrid methods combine traditional PDE discretizations with ML methods either(1)to help model complex nonlinear constitutive relations,(2)to nonlinearly reduce the model order for efficient simulation(turbulence),or(3)to accelerate the simulation by predicting certain components in the traditional integration methods.Here,methods(1)and(2)relied on Long-Short-Term Memory(LSTM)architecture,with method(3)relying on convolutional neural networks.Pure ML methods to solve(nonlinear)PDEs are represented by Physics-Informed Neural network(PINN)methods,which could be combined with attention mechanism to address discontinuous solutions.Both LSTM and attention architectures,together with modern and generalized classic optimizers to include stochasticity for DL networks,are extensively reviewed.Kernel machines,including Gaussian processes,are provided to sufficient depth for more advanced works such as shallow networks with infinite width.Not only addressing experts,readers are assumed familiar with computational mechanics,but not with DL,whose concepts and applications are built up from the basics,aiming at bringing first-time learners quickly to the forefront of research.History and limitations of AI are recounted and discussed,with particular attention at pointing out misstatements or misconceptions of the classics,even in well-known references.Positioning and pointing control of a large-deformable beam is given as an example.
文摘基于复杂网络的拓扑结构优化理论与禁忌搜索算法，结合指挥控制系统的特点，建立了优化最优指挥与控制系统网络结构（Command and Control Architecture Network，C2AN）模型，并以复杂网络的网络效率和网络成本分别描述C2AN中的信息传播效率及构建C2AN的资源消耗，建立优化的目标函数，通过禁忌搜索算法获得了最优的C2AN。最后通过仿真实例，分析了最优C2AN生成过程及其基本统计特征。
