Name
Title | ||
|---|---|---|
Analysis And Prediction Of Hourly Energy Consumption Based On Long Short-Term Memory Neural Network |
Abstract | ||
|---|---|---|
Due to the advancements of electricity dependent machinery, the excessive growth of power consumption has increased exponentially. Therefore, analysis and prediction of the energy consumption system will offer the future demand for electricity consumption and improve the power distribution system. On account of several challenges of existing energy consumption prediction models that are limiting to predict the actual energy consumption properly. Thus, to conquer the energy prediction method, this paper analyzes fourteen years of energy consumption data collected on an hourly basis, an open source dataset from kaggle. Moreover, the paper initiates a Long Short Term Memory (LSTM) based approach to predict the energy consumption based on the actual dataset. The empirical results demonstrate that the proposed LSTM architecture can efficiently enhance the prediction accuracy of energy consumption. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/ICOIN50884.2021.9333968 | 35TH INTERNATIONAL CONFERENCE ON INFORMATION NETWORKING (ICOIN 2021) |
Keywords | DocType | Citations |
Energy consumption, LSTM neural network, prediction analysis | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Rubina Akter | 1 | 3 | 2.17 |
| Jae Min Lee | 2 | 124 | 37.53 |
| Dong Seong Kim | 3 | 866 | 93.34 |