At the 2018 Huawei Global Analyst Summit, Huawei launched the SoftCOM AI solution architecture. Huawei introduced AI technology based on the all-cloud network architecture to build "never faulty" autonomous networks and trigger a new round of network transformation.
Over the past decade, networks have experienced All IP transformation and All Cloud transformation. User experience is improved, network component division is more and more refined, and network management and O&M become increasingly complex. The OPEX is three times more than the CAPEX. Network complexity makes network management be beyond the human capability, and human factors cause 70% of faults. These problems are the structural problems faced by operators' networks. Han Yufa, president of Huawei SoftCOM AI Solution Dept, said that these structural problems cannot be solved by simply reducing expenditure or improving personnel skills and we need to solve structural problems with structural innovation.
Based on the original full-cloud network architecture, Huawei SoftCOM AI introduces the mature AI technology with the core of machine learning to enable networks to be intelligent. The entire architecture has two cores. One is the AI training platform, which is used to train data and provide models or algorithms. The other is the intelligent management and control center, which collects data and infers and executes network action instructions based on the model and algorithm provided by the training platform. The entire architecture also enables networks to change from automated service deployment and action execution to intelligent fault self-healing, network self-optimization, and self-management. In this way, autonomous networks that are never faulty will be eventually provided.
The value of the SoftCOM AI solution architecture for operators can be summarized as "three multiplications" and "one improvement". Three multiplications are O&M efficiency multiplication, energy consumption efficiency multiplication, and resource utilization efficiency multiplication. One improvement is user experience improvement. O&M efficiency multiplication means that fault analysis and locating requiring a great amount of manpower changes to self-optimization and self-healing. Energy efficiency multiplication means that idle carriers are shut down based on the traffic volume or the CPU dominant frequency in DCs is adjusted to reduce energy consumption. Resource utilization efficiency multiplication means that intelligent path selection and network load balancing are used to improve the resource utilization efficiency. User experience improvement means that network design, plan, and configuration are automatically generated and the service rollout time can be shortened to one tenth of the original time.
Han Yufa said that "Operators' network intelligence is a long-term practice and cannot be accomplished at one stroke." He said that Huawei will start with cases with significant improvement in operators' efficiency, increase cases, collect data, improve algorithms, accumulate experience, explore deployment modes, and gradually useAI on operators' networks.
He pointed out that the future is an intelligent era. Huawei has established the SoftCOM AI Solution Dept to streamline Huawei research, R&D, and market departments, attracts outstanding talents from the world, and strives to build a first-class AI solution in the telecom industry. SoftCOM AI is the implementation of Huawei's All Intelligence strategy in the telecom field. The All Intelligence strategy also covers the implementation of AI in the enterprise, cloud, and device fields. The most key AI capability of SoftCOM AI is developed based on both Huawei's long-term strategic investment and growth in All Intelligence and telecom scenarios. SoftCOM AI helps operators build "never faulty" autonomous networks and achieve digital transformation.