Since virtualization technology enables the abstraction and sharing of resources in a flexible management way, the overall expenses of network deployment can be significantly reduced. Therefore, the technology has bee...Since virtualization technology enables the abstraction and sharing of resources in a flexible management way, the overall expenses of network deployment can be significantly reduced. Therefore, the technology has been widely applied in the core network. With the tremendous growth in mobile traffic and services, it is natural to extend virtualization technology to the cloud computing based radio access networks(CCRANs) for achieving high spectral efficiency with low cost.In this paper, the virtualization technologies in CC-RANs are surveyed, including the system architecture, key enabling techniques, challenges, and open issues. The enabling key technologies for virtualization in CC-RANs mainly including virtual resource allocation, radio access network(RAN) slicing, mobility management, and social-awareness have been comprehensively surveyed to satisfy the isolation, customization and high-efficiency utilization of radio resources. The challenges and open issues mainly focus on virtualization levels for CC-RANs, signaling design for CC-RAN virtualization, performance analysis for CC-RAN virtualization, and network security for virtualized CC-RANs.展开更多
Network slicing is one of the most important concepts in 5G networks. It is enabled by the Network Function Virtualization (NFV) technology to allow a set of Virtual Network Functions (VNFs) to be interconnected to fo...Network slicing is one of the most important concepts in 5G networks. It is enabled by the Network Function Virtualization (NFV) technology to allow a set of Virtual Network Functions (VNFs) to be interconnected to form a Network Service (NS). When network slices are created in 5G, some are shared among different 5G services while the others are dedicated to specific 5G services. The latter are called dedicated slices. Dedicated slices can be constructed with different configurations. In this research, dedicated slices of different configurations in 5G Core were evaluated in order to discover which one would perform better than the others. The performance of three systems would be compared: 1) Free5GC Stage 2 with each dedicated slice consisting of only UPF;2) Free5GC Stage 3 with each dedicated slice consisting of only UPF;3) Free5GC Stage 3 with each dedicated slice consisting of both SMF and UPF in terms of their registration time, response time, throughput, resource cost, and CPU utilization. It is shown that not one of the above systems will always be the best choice;based on the requirements, a specific system may be the best under a specific situation.展开更多
为了满足5G垂直用户对于网络切片部署时细粒度安全隔离需求,同时兼顾用户的隔离需求和提高资源利用率,提出了一种基于改进BN模型的网络切片安全部署方法。首先提出了一种双层BN模型的网络切片部署架构,基于SBA(service based architectu...为了满足5G垂直用户对于网络切片部署时细粒度安全隔离需求,同时兼顾用户的隔离需求和提高资源利用率,提出了一种基于改进BN模型的网络切片安全部署方法。首先提出了一种双层BN模型的网络切片部署架构,基于SBA(service based architecture)设计了虚拟机容器的双层虚拟化架构,将网络切片根据其所属用户的隔离需求分配利益冲突类标签,基于改进的BN模型部署规则确定网络切片的隔离部署策略;然后将该部署方法建立为整数线性规划模型,并将部署成本作为目标函数,通过最小化目标函数实现低成本部署网络切片;最后使用遗传算法对该问题仿真求解。实验结果表明,该安全部署方法在满足网络切片安全隔离需求的前提下降低了部署成本。展开更多
为降低化工智能园区虚拟网络功能部署成本问题,以最小化虚拟网络功能部署代价为目标函数,考虑容量、延迟等约束条件,提出化工智能园区虚拟网络功能部署方案。采用长短期记忆神经网络(LSTM)预测化工园中网络用户未来可能的位置,并利用基...为降低化工智能园区虚拟网络功能部署成本问题,以最小化虚拟网络功能部署代价为目标函数,考虑容量、延迟等约束条件,提出化工智能园区虚拟网络功能部署方案。采用长短期记忆神经网络(LSTM)预测化工园中网络用户未来可能的位置,并利用基于模型预测控制(MPC)的算法求解最小部署总代价,以使得虚拟网络功能部署成本最小。仿真结果表明:相对于Heuristic和Heuristic With Predict的求解方法,迁移部署虚拟网络功能的总代价最小,为13628。所提方案具有一定的有效性,可节约化工智能工业园区的虚拟网络功能部署成本。展开更多
文摘Since virtualization technology enables the abstraction and sharing of resources in a flexible management way, the overall expenses of network deployment can be significantly reduced. Therefore, the technology has been widely applied in the core network. With the tremendous growth in mobile traffic and services, it is natural to extend virtualization technology to the cloud computing based radio access networks(CCRANs) for achieving high spectral efficiency with low cost.In this paper, the virtualization technologies in CC-RANs are surveyed, including the system architecture, key enabling techniques, challenges, and open issues. The enabling key technologies for virtualization in CC-RANs mainly including virtual resource allocation, radio access network(RAN) slicing, mobility management, and social-awareness have been comprehensively surveyed to satisfy the isolation, customization and high-efficiency utilization of radio resources. The challenges and open issues mainly focus on virtualization levels for CC-RANs, signaling design for CC-RAN virtualization, performance analysis for CC-RAN virtualization, and network security for virtualized CC-RANs.
文摘Network slicing is one of the most important concepts in 5G networks. It is enabled by the Network Function Virtualization (NFV) technology to allow a set of Virtual Network Functions (VNFs) to be interconnected to form a Network Service (NS). When network slices are created in 5G, some are shared among different 5G services while the others are dedicated to specific 5G services. The latter are called dedicated slices. Dedicated slices can be constructed with different configurations. In this research, dedicated slices of different configurations in 5G Core were evaluated in order to discover which one would perform better than the others. The performance of three systems would be compared: 1) Free5GC Stage 2 with each dedicated slice consisting of only UPF;2) Free5GC Stage 3 with each dedicated slice consisting of only UPF;3) Free5GC Stage 3 with each dedicated slice consisting of both SMF and UPF in terms of their registration time, response time, throughput, resource cost, and CPU utilization. It is shown that not one of the above systems will always be the best choice;based on the requirements, a specific system may be the best under a specific situation.
文摘为了满足5G垂直用户对于网络切片部署时细粒度安全隔离需求,同时兼顾用户的隔离需求和提高资源利用率,提出了一种基于改进BN模型的网络切片安全部署方法。首先提出了一种双层BN模型的网络切片部署架构,基于SBA(service based architecture)设计了虚拟机容器的双层虚拟化架构,将网络切片根据其所属用户的隔离需求分配利益冲突类标签,基于改进的BN模型部署规则确定网络切片的隔离部署策略;然后将该部署方法建立为整数线性规划模型,并将部署成本作为目标函数,通过最小化目标函数实现低成本部署网络切片;最后使用遗传算法对该问题仿真求解。实验结果表明,该安全部署方法在满足网络切片安全隔离需求的前提下降低了部署成本。
文摘为降低化工智能园区虚拟网络功能部署成本问题,以最小化虚拟网络功能部署代价为目标函数,考虑容量、延迟等约束条件,提出化工智能园区虚拟网络功能部署方案。采用长短期记忆神经网络(LSTM)预测化工园中网络用户未来可能的位置,并利用基于模型预测控制(MPC)的算法求解最小部署总代价,以使得虚拟网络功能部署成本最小。仿真结果表明:相对于Heuristic和Heuristic With Predict的求解方法,迁移部署虚拟网络功能的总代价最小,为13628。所提方案具有一定的有效性,可节约化工智能工业园区的虚拟网络功能部署成本。
