Open AccessAnalysis and Development Potential of Predictive Models for Energy Flows of Autonomous Hybrid Energy Systems
Author(s) -
Victor D. Berdonosov,
G. V. Vasilev,
Alena A. Zhivotova
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2096/1/012024
Subject(s) - computer science , energy (signal processing) , energy system , hybrid system , wind power , autonomous system (mathematics) , architecture , artificial intelligence , machine learning , engineering , mathematics , visual arts , art , statistics , electrical engineering
The article is devoted to the analysis and development potential for predictive models of energy flows of autonomous hybrid energy systems. The article considers the results of the analysis in the form of a morphological table and TRIZ–evolutionary map. The research defined the most promising in predicting energy flows are hybrid models that include more than one architecture. For example, DCNN + LSTM or MLP + LS–SVR. The authors intend to continue research in the direction of creating predictive models of wind energy flows for autonomous hybrid energy systems.