Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 18, 2026Integrated Computer-Aided Engineering

An adaptive multi-agent system for dynamic detection and prediction of daily energy profiles in buildings

View Full Paper
Ask AI
Bookmark
Share

Authors

YKYoussef El KouchSCStéphanie CombettesIAIrina Andriamandimbihasina

Discussion

Loading...

Member takes

Overview

Randomized trial evaluates daily energy profiles in buildings, suggesting improved HVAC control methods.

Key Points

  • The study aims to develop a system for dynamic detection and prediction of energy consumption profiles in buildings.
  • Introduced the AMA-PDP framework utilizing a multi-agent system for energy profile detection and prediction.
  • Applied Dynamic Time Warping for daily profile detection based on streaming data.
  • Employed an Incremental One-vs-Rest Neural Network ensemble for predicting energy consumption based on various features.
  • The AMA-PDP method achieved higher average accuracy compared to batch neural models, with fewer cluster misclassifications.
  • Dynamic adaptation of clusters led to improved representation of varying operational configurations over time.

Cite This Study

Kouch et al. (2026) studied this question.

synapsesocial.com/papers/6a5b18d718557b26c203a89ahttps://doi.org/10.1177/10692509261464046
View Full Paper
Ask AI
Bookmark
Share