Recent Applications of Federated Learning in Edge and IoT Environments: A Review

The Internet of Things has been raised as an alternative for implementing different data collection strategies. Because of the limited hardware, it is complemented with edge computing trying to bring the computing power as close to the data source as possible. Collected data have particular importance for building different kinds of artificial intelligence models. However, it requires that data are transported from the data source to some centralized processing place (e.g., cloud). Data ownership and data privacy associated emerge as essential concerns. Thus, federated learning is proposed as an alternative to train models in a distributed way and avoid unnecessary data transportation. So, a global model is built based on local parameters/weights computed in distributed nodes. This work describes a Systematic Mapping Study focused on recent applications of federated learning on the Internet of Things and Edge environments. Study cases and applications from 2021 onwards are queried and analyzed from the Scopus database. The study is limited to articles written in the English language and published in journals. From 32 articles, 28 are retained following the inclusion and exclusion criteria. Data Ownership emerges as the main challenge, while the model performance represents the main trend. China and United States concentrate 55 % of the involved articles on the subject.