The use of IoT systems is increasing day by day. However, these systems due to their heterogeneity and inherently dynamic nature, face different uncertainties from the context, environment, etc. Such uncertainties can have a big impact on the overall system QoS, especially on energy efficiency and data traffic. This calls for better ways of architecting IoT systems that may self-adapt to keep the desired QoS. This paper presents an approach that leverages the use of machine learning (ML) techniques to perform a proactive adaptation of IoT architectures using self-adaptation patterns. It i) continuously monitors the QoS parameters; ii) forecasts possible deviations from the acceptable QoS parameters; iii) selects the best adaptation pattern based on forecasts using reinforcement learning (RL) techniques; iv) checks the quality of the selected decision using feedback mechanisms; and v) continuously performs the loop of the forecast, adaptation, and feedback. The results of our evaluations show that our approach can provide accurate QoS forecasts and further improve the energy efficiency of the system while maintaining the required data traffic.

Leveraging Machine Learning Techniques for Architecting Self-Adaptive IoT Systems

Muccini H.;
2020-01-01

Abstract

The use of IoT systems is increasing day by day. However, these systems due to their heterogeneity and inherently dynamic nature, face different uncertainties from the context, environment, etc. Such uncertainties can have a big impact on the overall system QoS, especially on energy efficiency and data traffic. This calls for better ways of architecting IoT systems that may self-adapt to keep the desired QoS. This paper presents an approach that leverages the use of machine learning (ML) techniques to perform a proactive adaptation of IoT architectures using self-adaptation patterns. It i) continuously monitors the QoS parameters; ii) forecasts possible deviations from the acceptable QoS parameters; iii) selects the best adaptation pattern based on forecasts using reinforcement learning (RL) techniques; iv) checks the quality of the selected decision using feedback mechanisms; and v) continuously performs the loop of the forecast, adaptation, and feedback. The results of our evaluations show that our approach can provide accurate QoS forecasts and further improve the energy efficiency of the system while maintaining the required data traffic.
2020
978-1-7281-6997-2
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11697/153811
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 8
  • ???jsp.display-item.citation.isi??? 4
social impact