Millimeter waves is one of 5G networks strategies to achieve high bit rates. Measurement campaigns with these signals are difficult and require expensive equipment. In order to generate realistic data this paper refines a methodology for "virtual" measurements of 5G channels, which combines a simulation of urban mobility with a ray-tracing simulator. The urban mobility simulator is responsible for controlling mobility, positioning pedestrians and vehicles throughout each scene while the ray-tracing simulator is repeatedly invoked, simulating the interactions between receivers and transmitters. The orchestration among both simulators is done using a Python software. To check how the realism can influence the computational cost, it was made a numerical analyse between the number of faces and the simulation time.

No abstract

Gathering channel data to test telecommunication systems is an essential step to guarantee the quality of the product. However, it can be a slow process and demand a considerable amount of effort and investment since it is costly to make field measurements of mmWaves. Having a ready dataset at disposal make things way faster and cheaper, allowing a developer to focus on more specific tasks. This paper presents an entire multimodal dataset with different kinds of information like channel communication, urban traffic and obstacles position, got from two realistic computer simulations made in two different city models: Beijing and Rosslyn. It also includes detailed information on how each data is stored.

The fifth generation of mobile networks evolved to serve applications with distinct requirements, which results in a high management complexity due to simultaneous real-time tasks. In the physical layer, code words that allow proper data exchange between the Base Station (BS) and the served users must be chosen. While, in higher layers, the BS must choose users to be served in a given transmission opportunity. There are approaches based on Machine Learning (ML) to solve these combined tasks. However, due to the high amount of possible inputs, a challenge is the availability of data to train the models. In some cases, there may not even exist a predefined optimal answer to use as a "label" for supervised approaches. In this paper, we evaluate solutions for the combined problems of beam selection and user scheduling with Reinforcement Learning (RL), which does not need labels, as a solution for problems without a predefined answer. The algorithms were proposed for Problem Statement 6 of the challenge organized by the International Telecommunication Union (ITU) in 2021, which ranked as the finalists. We compare the approaches in relation to the cumulative reward received by the agents and show a performance comparison of different RL approaches by comparing them with baselines developed for the challenge. The paper also shows how the action taken by the trained agents affect network operation by comparing the number of packets transmitted, which is highly related to the proper selection of users and code words.

No abstract