direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Page Content

Fog4IoT: Fog Data Management for IoT Applications

Typically, IoT applications rely on data produced by sensors to trigger actions on smart devices. As an example, wind, temperature, and brightness sensors in a smart home could be used to control window blinds or a smart factory might use vibration and noise sensors to shut off CNC machines before permanent damage occurs as well as to enable preventive maintenance.

In both scenarios, data is processed and decisions are taken either locally on edge devices or in cloud-based services. Often, there are also secondary uses or improved decision processes when collecting and correlating sensor data from various sources in the cloud. For IoT applications, both cloud and edge computing have their own advantages and disadvantages: while edge computing primarily suffers from capacity constraints on local devices, cloud services have much higher latencies and a higher probability of not being available locally due to network outages. Furthermore, privacy concerns may further limit choices depending on the kind of data. For instance, personal data in EU smart home scenarios can be subject to the GDPR and manufacturers may be reluctant to expose data on sensitive production processes to outsiders. All these aspects need to be weighed carefully so as to alleviate weaknesses and fully utilize strengths when building data management systems for IoT applications in fog environments, i.e., using cloud and edge computing as well as possible intermediary nodes within the core network at the same time.

In this project, we research novel data management and data distribution techniques specifically tailored to the needs of IoT applications. Such techniques need to efficiently distribute and move data across edge and cloud nodes while hiding as much complexity as possible from applications. A particular challenge in this project is that IoT applications can use both streaming and event-driven functions (‘serverless’) as computation approaches depending on the respective use case. Additionally, there are scenarios where pub/sub-based data distribution provides much more flexibility than standard point-to-point communication. The goal of this project is to combine these different approaches and techniques into an integrated platform that offers a continuum choice between functions and streams.

The first four years of this project are funded by the Einstein Foundation; the project started in January 2018.

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions