Traffic recognition and long-term traffic forecasting based on AI algorithms and metadata for 5G/IMT-2020 and beyond
5G/IMT-2020 and beyond networks will require robust smart algorithms to adapt network protocols and resource management for different services in different scenarios. Artificial intelligence (AI), which is defined as any process or device that realizes its environment and takes actions that maximize the opportunities of success for some predefined goal, is a practical solution for the design of an emerging complex communications system. The recent developments in deep learning, convolutional neural networks, and reinforcement learning hold important promise for the solution of very complex problems considered intractable until now. This talk will present AI algorithms and metadata-based approach for traffic recognition and classification with very high precision and following forecasting, to ensure ultra-reliable and ultra-low latency systems. This process should behold intelligently and include the flexible scaling methods according to the changing traffic, the geographic network position, and requirements. One key features to use the metadata of flows on the data plane at the same time with the analytical application of AI/ML algorithms is located on the service level and working with the SDN/NFV network via northbound API.