Exploring Long Short Term Memory Algorithms for Low Energy Data Aggregation
-
Published:2024-01-05
Issue:
Volume:
Page:71-82
-
ISSN:2788-7669
-
Container-title:Journal of Machine and Computing
-
language:en
-
Short-container-title:JMC
Affiliation:
1. Department of Architectural Design, Dong-Seo University, Sasang-gu, Busan, Republic of Korea.
Abstract
Long short-term memory methods are employed for data consolidation in intricate low-energy devices. It has enabled accurate and efficient aggregation of statistics in limited electricity settings, facilitating the review and retrieval of data while minimizing electricity wastage. The LSTM rules analyze, organize, and consolidate vast datasets inside weakly connected structures. It has employed a recurrent neural network to handle data processing, particularly nonlinear interactions. The machine's capabilities are subsequently examined and stored utilizing memory blocks. Memory blocks retain extended temporal connections within the data, facilitating adaptive and precise information aggregation. These blocks facilitate the system's ability to shop and utilize relevant capabilities for quick retrieval. The proposed algorithm offers realistic tuning capabilities such as learning rate scheduling and total regularization based on dropout like green information aggregation. These enable systems to reduce over fitting while permitting precise adjustment of the settings. It allows for optimizing the algorithm to provide highly dependable performance within weak structures, enhancing data aggregation techniques' energy efficiency. Standard algorithms provide an efficient, accurate solution for aggregating information in low-power systems. It facilitates evaluating, retrieving, and aggregating accurate and reliable information using memory blocks, adaptive tuning, and efficient learning rate scheduling.
Publisher
Anapub Publications
Subject
Electrical and Electronic Engineering,Computational Theory and Mathematics,Human-Computer Interaction,Computational Mechanics
Reference19 articles.
1. P. Ma, S. Cui, M. Chen, S. Zhou, and K. Wang, “Review of Family-Level Short-Term Load Forecasting and Its Application in Household Energy Management System,” Energies, vol. 16, no. 15, p. 5809, Aug. 2023, doi: 10.3390/en16155809. 2. J. Wang, H. Zhu, Y. Zhang, F. Cheng, and C. Zhou, “A novel prediction model for wind power based on improved long short-term memory neural network,” Energy, vol. 265, p. 126283, Feb. 2023, doi: 10.1016/j.energy.2022.126283. 3. B. Li, T. Wu, S. Bian, and J. W. Sutherland, “Predictive model for real-time energy disaggregation using long short-term memory,” CIRP Annals, vol. 72, no. 1, pp. 25–28, 2023, doi: 10.1016/j.cirp.2023.04.066. 4. C. Huang, H. R. Karimi, P. Mei, D. Yang, and Q. Shi, “Evolving long short-term memory neural network for wind speed forecasting,” Information Sciences, vol. 632, pp. 390–410, Jun. 2023, doi: 10.1016/j.ins.2023.03.031. 5. M. Stankovic, L. Jovanovic, M. Antonijevic, A. Bozovic, N. Bacanin, and M. Zivkovic, “Univariate Individual Household Energy Forecasting by Tuned Long Short-Term Memory Network,” Lecture Notes in Networks and Systems, pp. 403–417, 2023, doi: 10.1007/978-981-99-1624-5_30.
|
|