Mid-term electricity load prediction using CNN and Bi-LSTM

M. Junaid Gul, Gul Malik Urfa, Anand Paul, Jihoon Moon, Seungmin Rho, Eenjun Hwang

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

Electricity is one of the critical role players to build an economy. Electricity consumption and generation can affect the overall policy of the country. Such importance opens an area for intelligent systems that can provide future insights. Intelligent management for electric power consumption requires future electricity power consumption prediction with less error. These predictions provide insights for making decisions to smooth line the policy and grow the country’s economy. Future prediction can be categorized into three categories, namely (1) Long-Term, (2) Short-Term, and (3) Mid-Term predictions. For our study, we consider the Mid-Term electricity consumption prediction. Dataset provided by Korea Electric power supply to get insights for a metropolitan city like Seoul. Dataset is in time-series, so statistical and machine learning models can be used. This study provides experimental results from the proposed ARIMA and CNN-Bi-LSTM. Hyperparameters are tuned for ARIMA and neural network models to increase the models’ accuracy, which looks promising as RMSE for training is 0.14 and 0.20 RMSE for testing.

Original languageEnglish
Pages (from-to)10942-10958
Number of pages17
JournalJournal of Supercomputing
Volume77
Issue number10
DOIs
Publication statusPublished - 2021 Oct

Keywords

  • ARIMA
  • BI-LSTM
  • CNN
  • Mid-term power consumption
  • Neural network

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Information Systems
  • Hardware and Architecture

Fingerprint

Dive into the research topics of 'Mid-term electricity load prediction using CNN and Bi-LSTM'. Together they form a unique fingerprint.

Cite this