Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Short-Term Electricity Demand Forecasting of Dhaka City Using CNN with Stacked BiLSTM

Kazi Fuad Bin Akhter, Sadia Mobasshira, Saief Nowaz Haque, Mahjub Alam Khan Hesham, Tanvir Ahmed

TL;DR

The paper tackles short-term electricity load forecasting for Dhaka, Bangladesh, addressing the nonlinear and time-dependent nature of urban electricity demand. It proposes a CNN with stacked BiLSTM architecture to capture local features and bidirectional temporal dependencies in daily consumption data from 2016–2021. The model achieves state-of-the-art accuracy, reporting a MAPE of 1.64% and outperforming several benchmark models and prior studies, highlighting its potential for improved power-system planning. The work demonstrates the viability of hybrid deep-learning approaches for reliable, data-driven daily demand forecasts in developing urban grids, with future directions including additional data sources and holiday effects.

Abstract

The precise forecasting of electricity demand also referred to as load forecasting, is essential for both planning and managing a power system. It is crucial for many tasks, including choosing which power units to commit to, making plans for future power generation capacity, enhancing the power network, and controlling electricity consumption. As Bangladesh is a developing country, the electricity infrastructure is critical for economic growth and employment in this country. Accurate forecasting of electricity demand is crucial for ensuring that this country has a reliable and sustainable electricity supply to meet the needs of its growing population and economy. The complex and nonlinear behavior of such energy systems inhibits the creation of precise algorithms. Within this context, this paper aims to propose a hybrid model of Convolutional Neural Network (CNN) and stacked Bidirectional Long-short Term Memory (BiLSTM) architecture to perform an accurate short-term forecast of the electricity demand of Dhaka city. Short-term forecasting is ordinarily done to anticipate load for the following few hours to a few weeks. Normalization techniques have been also investigated because of the sensitivity of these models towards the input range. The proposed approach produced the best prediction results in comparison to the other benchmark models (LSTM, CNN- BiLSTM and CNN-LSTM) used in the study, with MAPE 1.64%, MSE 0.015, RMSE 0.122 and MAE 0.092. The result of the proposed model also outperformed some of the existing works on load-forecasting.

Short-Term Electricity Demand Forecasting of Dhaka City Using CNN with Stacked BiLSTM

TL;DR

The paper tackles short-term electricity load forecasting for Dhaka, Bangladesh, addressing the nonlinear and time-dependent nature of urban electricity demand. It proposes a CNN with stacked BiLSTM architecture to capture local features and bidirectional temporal dependencies in daily consumption data from 2016–2021. The model achieves state-of-the-art accuracy, reporting a MAPE of 1.64% and outperforming several benchmark models and prior studies, highlighting its potential for improved power-system planning. The work demonstrates the viability of hybrid deep-learning approaches for reliable, data-driven daily demand forecasts in developing urban grids, with future directions including additional data sources and holiday effects.

Abstract

The precise forecasting of electricity demand also referred to as load forecasting, is essential for both planning and managing a power system. It is crucial for many tasks, including choosing which power units to commit to, making plans for future power generation capacity, enhancing the power network, and controlling electricity consumption. As Bangladesh is a developing country, the electricity infrastructure is critical for economic growth and employment in this country. Accurate forecasting of electricity demand is crucial for ensuring that this country has a reliable and sustainable electricity supply to meet the needs of its growing population and economy. The complex and nonlinear behavior of such energy systems inhibits the creation of precise algorithms. Within this context, this paper aims to propose a hybrid model of Convolutional Neural Network (CNN) and stacked Bidirectional Long-short Term Memory (BiLSTM) architecture to perform an accurate short-term forecast of the electricity demand of Dhaka city. Short-term forecasting is ordinarily done to anticipate load for the following few hours to a few weeks. Normalization techniques have been also investigated because of the sensitivity of these models towards the input range. The proposed approach produced the best prediction results in comparison to the other benchmark models (LSTM, CNN- BiLSTM and CNN-LSTM) used in the study, with MAPE 1.64%, MSE 0.015, RMSE 0.122 and MAE 0.092. The result of the proposed model also outperformed some of the existing works on load-forecasting.
Paper Structure (16 sections, 14 equations, 1 figure, 3 tables)

This paper contains 16 sections, 14 equations, 1 figure, 3 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Background Study
  4. Convolutional Neural Network
  5. Long Short-Term Memory
  6. Bidirectional Long Short-Term Memory
  7. Methodology
  8. Dataset Collection
  9. Data Preprocessing
  10. Splitting Input Data
  11. Normalization
  12. Proposed Model
  13. Evaluation Metrices
  14. Experimental Setup
  15. Results and Analysis
  16. ...and 1 more sections

Figures (1)

  • Figure 1: Proposed Methodolgy.