Machine learning Technique for improving the stability of Thermal Energy storage

In deep learning, it is possible that training efficiency will suffer as a result of redundant data. A lower amount of training data, on the other hand, may result in a model that is unable to capture the necessary features hidden within the dataset. In this paper, we use machine-deep-statistical model to analyse the stability of thermal storage systems i.e., battery in terms of managing the energy storage. These three models offer a prominent success across various applications and in this study, it uses life prediction, state estimation, defect diagnosis, fault detection, behaviour and property analysis via proper modelling and optimization. The validation is conducted in terms of various metrics to estimate the proposed model against various methods. The results of simulation shows that the proposed method achieves higher degree of accuracy with reduced prediction errors than other methods.(c) 2022 Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Automated summary

The paper discusses how redundant data in deep learning can reduce training efficiency, while too little data can hinder capturing essential features. Using a machine-deep-statistical model, it analyzes the stability of thermal storage systems, demonstrating higher accuracy through simulation results.