Artificial Intelligence-enabled Massive Multiple-input multiple-output (AIMM)

第五代移动的网络（5G）旨在通过提供无处不在的连接和许多其他改进来改变无线技术在社会中的角色。在5G的初始阶段，仅在全球一些大城市的某些地区提供覆盖。增加5G覆盖范围需要运营商进行额外投资，以部署新天线，增加频谱并升级现有基础设施。因此，电信公司需要寻找效率和货币化机会，而不仅仅是提供连接。5G通过其固有的属性，预计将为许多新的服务，用例，业务和收入模式创造潜力。为了实现完全货币化，5G网络必须嵌入新的新兴技术，包括边缘缓存、云计算和人工智能（AI），目标是生成可操作的见解并最大限度地提高关键性能指标（KPI）。AIMM是一个合作研发项目，参与者包括英国最大的固定和移动的运营商BT、专注于无线连接解决方案的中小企业Vilicom，以及布里斯托大学和拉夫堡大学的领先研究机构。AIMM的目标是通过利用AI技术来提高移动的无线电网络的性能。有关分配、无线电信道条件和用户服务要求的数据将从网络中获得。AI技术将用于通过实现更好的无线接入网络（RAN）管理和优化来提高现有天线结构和无线网络架构的性能。还将评估可从现有架构和新技术中收集的新数据项的价值。网络数据集还将使人工智能能够释放部署在中心位置或分布在某个区域的大规模天线阵列（称为大规模MIMO）的真正潜力，作为5G RAN及其他领域的重要商业解决方案。AIMM将始终密切关注网络功能之间数据的适当使用和共享。因此，AIMM解决了5G RAN及以后的人工智能的两个方面：（1）使用人工智能优化空中接口的性能，并实现先进天线结构的切实可行的实施，以及（2）使用人工智能管理和优化系统级的网络参数。AIMM旨在确保英国引领5G电信网络和服务下一阶段的创新。

The fifth-generation of mobile network (5G) aims at transforming the role of wireless technology in society through providing ubiquitous connectivity and many other improvements. In the initial phase of 5G, coverage will only be available in certain areas in a number of large cities worldwide. Increasing the 5G footprint requires additional investments from the operators to deploy new antennas, add spectrum, and upgrade their existing infrastructure. Telcos hence need to look for efficiency and monetization opportunities, beyond simply providing connectivity. 5G through its inherent attributes is anticipated to create the potential for a host of new services, use-cases, business and revenue models. To achieve full monetization, 5G networks must embed new emerging technologies including edge caching, cloud computing, and artificial intelligence (AI) -- with the goal of generating actionable insights and maximizing key performance indicators (KPIs). Creating strong partnerships between telcos, vertical industries, and public agencies is the way forward to realise this.AIMM is a collaborative research and development project involving BT, the largest fixed and mobile operator in the country, Vilicom, an SME specialising in wireless connectivity solutions, and leading research institutions in University of Bristol and Loughborough University. The objective of AIMM is to enhance the performance of mobile radio networks through utilization of AI techniques. Data regarding the distribution, radio channel conditions and service requirements of users will be accessed from the network. AI techniques will be employed to improve performance with existing antenna structures and radio network architectures by enabling better radio access network (RAN) management and optimisation. The value of new items of data that could be collected from both existing architectures and new techniques will also be assessed. The network data sets will also enable AI to unlock the true potential of large-scale antenna arrays (known as massive MIMO), deployed at a central location or distributed over an area, as an important commercial solution for 5G RAN and beyond. At all times, close attention will be paid to the appropriate use and sharing of data between network functions.AIMM therefore addresses two aspects of AI for the 5G RAN and beyond: (1) using AI to optimise the performance of the air-interface and enable the practicable implementation of advanced antenna structures and (2) using AI to manage and optimise network parameters at the system level. AIMM intends to ensure that UK leads the innovation of the next phases of 5G telecoms networks and services.