English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Online output prediction is an indispensable part of any model predictivecontrol implementation, especially when simplifications of the underlyingphysical model have been considered and/or the operating conditions changequite often. Furthermore, the selection of an output prediction model isstrongly related to the data available, while designing/altering the datacollection process may not be an option. Thus, in several scenarios, selectingthe most appropriate prediction model needs to be performed during runtime. Tothis end, this paper introduces a supervisory output prediction scheme,tailored specifically for input-output stable bilinear systems, that intends onautomating the process of selecting the most appropriate prediction modelduring runtime. The selection process is based upon a reinforcement-learningscheme, where prediction models are selected according to their priorprediction performance. An additional selection process is concerned withappropriately partitioning the control-inputs' domain in order to also allowfor switched-system approximations of the original bilinear dynamics. We showanalytically that the proposed scheme converges (in probability) to the bestmodel and partition. We finally demonstrate these properties throughsimulations of temperature prediction in residential buildings.

Supervisory Output Prediction for Bilinear Systems by Reinforcement Learning