Expression of Concern for: A DNN based LSTM Model for Predicting Future Energy Consumption
Due to the progressions of power subordinate hardware, the unnecessary development of energy utilization has expanded dramatically. In this manner, monitoring and prediction of the energy utilization framework will offer the future interest for energy utilization and further develop the power circul...
Saved in:
Published in | 2022 International Conference on Applied Artificial Intelligence and Computing (ICAAIC) p. 1 |
---|---|
Main Authors | , , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
09.05.2022
|
Online Access | Get full text |
Cover
Loading…
Summary: | Due to the progressions of power subordinate hardware, the unnecessary development of energy utilization has expanded dramatically. In this manner, monitoring and prediction of the energy utilization framework will offer the future interest for energy utilization and further develop the power circulation framework. By the virtue of a few difficulties of existing energy utilization, prediction models are restricting to anticipate the genuine energy utilization appropriately. Along these lines, to overcome the energy prediction technique, this paper dissects fourteen years of energy utilization information gathered on an hourly premise, from an open-source dataset from Kaggle. Also, the paper suggests a Long Short-Term Memory (LSTM) based way to deal with predicted energy utilization in light of the genuine dataset. The experimental outcomes show that the proposed LSTM engineering can effectively improve the prediction exactness of energy utilization. |
---|---|
DOI: | 10.1109/ICAAIC53929.2022.10703420 |