• English
  • Deutsch
  • Log In
    Password Login
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Generative Machine Learning for Resource-Aware 5G and IoT Systems
 
  • Details
  • Full
Options
2021
Conference Paper
Titel

Generative Machine Learning for Resource-Aware 5G and IoT Systems

Abstract
Extrapolations predict that the sheer number of Internet-of-Things (IoT) devices will exceed 40 billion in the next five years. Hand-crafting specialized energy models and monitoring sub-systems for each type of device is error prone, costly, and sometimes infeasible. In order to detect abnormal or faulty behavior as well as inefficient resource usage autonomously, it is of tremendous importance to endow upcoming IoT and 5G devices with sufficient intelligence to deduce an energy model from their own resource usage data. Such models can in-turn be applied to predict upcoming resource consumption and to detect system behavior that deviates from normal states. To this end, we investigate a special class of undirected probabilistic graphical model, the so-called integer Markov random fields (IntMRF). On the one hand, this model learns a full generative probability distribution over all possible states of the system-allowing us to predict system states and to measure the probability of observed states. On the other hand, IntMRFs are themselves designed to consume as less resources as possible-e.g., faithful modelling of systems with an exponentially large number of states, by using only 8-bit unsigned integer arithmetic and less than 16KB memory. We explain how IntMRFs can be applied to model the resource consumption and the system behavior of an IoT device and a 5G core network component, both under various workloads. Our results suggest, that the machine learning model can represent important characteristics of our two test systems and deliver reasonable predictions of the power consumption.
Author(s)
Piatkowski, Nico
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS
Müller-Römer, Johannes
Fraunhofer-Institut für Graphische Datenverarbeitung IGD
Hasse, Peter
Fraunhofer-Institut für Offene Kommunikationssysteme FOKUS
Bachorek, Adam
Fraunhofer-Institut für Experimentelles Software Engineering IESE
Werner, Tim
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Birnstill, Pascal
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Morgenstern, Andreas
Fraunhofer-Institut für Experimentelles Software Engineering IESE
Stobbe, Lutz
Fraunhofer-Institut für Zuverlässigkeit und Mikrointegration IZM
Hauptwerk
IEEE International Conference on Communications Workshops (ICC Workshops) 2021. Proceedings
Project(s)
TRAICT
Funder
Bundesministerium für Bildung und Forschung BMBF (Deutschland)
Konferenz
International Conference on Communications (ICC) 2021
DOI
10.1109/ICCWorkshops50388.2021.9473625
File(s)
N-638015.pdf (4.23 MB)
Language
English
google-scholar
Fraunhofer-Institut für Offene Kommunikationssysteme FOKUS
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS
Fraunhofer-Institut für Experimentelles Software Engineering IESE
Fraunhofer-Institut für Graphische Datenverarbeitung IGD
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Fraunhofer-Institut für Zuverlässigkeit und Mikrointegration IZM
Tags
  • Lead Topic: Digitized Work

  • Research Line: Machine Learning (ML)

  • Machine learning

  • Energy efficiency

  • Communication services and networks

  • generative model

  • probabilistic graphical model

  • Internet of Things

  • 5G core

  • energy model

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022