Predicting Quality of Service (QoS) for mobile Communication

Many applications in the field of cooperative autonomous driving or mobile robotics due to the highly dynamic nature of their environment will necessitate the deployment of ultra-reliable wireless links that can provide real-time, low-latency control for such autonomous systems. An important challenge is therefore to guarantee the end-to-end quality of service (QoS) required by the respective application. Integrating fundamental notions of artificial intelligence (AI) across the wireless infrastructure and end-user devices has gained a tremendous interest not only in the improvement of road safety but also in the industry4.0 domain by reducing quality control eff orts and operational costs on exponential levels. One major gain of exploiting AI to optimize the operation of wireless-based use cases is the prediction of future network performance indicators also known as predictive Quality of Service (pQoS). Intelligent AI-based PQoS methods must be able to adaptively exploit the wireless system resources and generated data, in order to optimize network operation and guarantee, in real-time, the QoS needs of highly mobile use cases.