SHORT TERM LOAD FORECASTING USING RECURRENT AND SPATIAL DEEP LEARNING MODEL FORECASTING

Authors

  • Zohaib Ahmed Department of Electrical Engineering
  • Shaheer Khan UET PESHAWAR JALOZAI CAMPUS
  • Ibraheem Khan UET PESHAWAR JALOZAI CAMPUS
  • Muhammad Shafiq UET PESHAWAR JALOZAI CAMPUS
  • Muhammad Farhan UET PESHAWAR JALOZAI CAMPUS
  • Irshad ullah UET PESHAWAR JALOZAI CAMPUS

Abstract

Short-term load forecasting is critical to optimizing energy use and maintaining the stability of the power network. This study proposes an LSTM-based deep learning model for electricity demand forecasting, incorporating 21 input features, including time of day, day of week, and holiday factors within a 24-hour sequence to capture temporal consumption patterns. The model consists of two LSTM layers with 50 units each, applying dropout regularization and the Adam optimizer to improve training efficiency. When evaluated on the AEP dataset, the model achieves a MAPE of 0.65 percent, demonstrating its accuracy in handling nonstationary and seasonal variations. Comparative analysis with GRU, BiGRU, BiLSTM, and 1D CNN confirms that LSTM consistently achieves lower error rates. These findings highlight LSTM’s effectiveness in improving STLF accuracy, contributing to better energy planning and power network stability.

References

Xi Fang, Satyajayant Misra, Guoliang Xue, and Dejun Yang. Smart grid — the new and improved

power grid: A survey. IEEE Communications Surveys & Tutorials, 14(4):944–980, 2012.

G. Ekonomou, E. Fotopoulou, and S. Georgilakis. Application of artificial neural networks for

electricity load forecasting. International Journal of Electrical Power & Energy Systems, 82:29–36,

N. Meher, M. Nur, and A. Das. A comparative analysis of ensemble methods for short-term load

forecasting. pages 1–6, 2024.

S. Tsegaye, S. Padmanaban, L. B. Tjernberg, and K. A. Fante. Short-term load forecasting for

electrical power distribution systems using enhanced deep neural net- works. IEEE Access, 12:186856–186871, 2024.

Tareq Rahman, Simran Kaur, and Ashok Das. Efficient hybrid models for stlf using machine learning

and time-series analysis. IEEE Transactions on Energy Conversion, 40(3):950–960, 2025.

Jian Li, Daiyu Deng, Junbo Zhao, Dongsheng Cai, Weihao Hu, Man Zhang, and Qi Huang. A

novel hybrid short-term load forecasting method of smart grid using mlr and lstm neural network.

IEEE Transactions on Industrial Informatics, 17(4):2443– 2452, 2020.

JCH Chiang, LM Swenson, and W Kong. Role of seasonal transitions and the west- erlies in the

interannual variability of the east asian summer monsoon precipitation. Geophysical Research Letters, 44(8):3788–3795, 2017.

P. Alagarsundaram, S. K. Ramamoorthy, D. Mazumder, V. Malathy, and M. Soni. A short-term

load forecasting model using restricted boltzmann machines and bi- directional gated recurrent unit.

pages 1–5, 2024.

Heng Shi, Minghao Xu, and Ran Li. Deep learning for household load forecasting—a novel pooling

deep rnn. IEEE Transactions on Smart Grid, 9(5):5271–5280, 2017.

Y. Cui, H. Zhu, Y. Wang, L. Zhang, and Y. Li. Short-term power load forecasting method based

on cnn-saedn-res. arXiv preprint arXiv:2309.07140, 2023.

Stylianos Pelekis, Vassilis Tsoukalas, and Georgios Dimitrios. A comparative as- sessment of deep

learning models for day-ahead load forecasting: Investigating key accuracy drivers. arXiv preprint

arXiv:2302.12168, 2023.

Ju¨r gen Schmidhuber and Sepp Hochreiter. Long short-term memory. Neural Comput, 9(8):1735–1780,

Weicong Kong, Zhao Yang Dong, Youwei Jia, David J. Hill, Yan Xu, and Yuan Zhang. Shortterm residential load forecasting based on lstm recurrent neural net- work. IEEE Transactions on

Smart Grid, 10(1):841–851, 2017.

B. Jiang, Y. Wang, Q. Wang, and H. Geng. A novel interpretable short-term load forecasting method

based on kolmogorov-arnold networks. IEEE Transactions on Power Systems, 40(1):1180–1183,

Faisal Ahmed, Lei Zhao, and Min Wei. Advanced methods for improving the accuracy of short-term

load forecasting. IEEE Transactions on Power Delivery, 39(6):1230–1242, 2024.

S. Turudi´c, A. Selakov, and Z. Jankovi´c. Short-term load forecasting through the identification of

similar hour series. 1:1–6, 2023.

Hui Cheng, Yu Zhang, and Xiaoyang Ling. Impact of data preprocessing on the performance of deep

learning models for load forecasting. IEEE Transactions on Energy Conversion, 40(2):700–710,

S. H. Rafi, S. R. Deeba, E. Hossain, et al. A short-term load forecasting method using integrated

cnn and lstm network. IEEE Access, 9:32436–32448, 2021.

Bharat Bohara, Kabin Shrestha, and Zhao Yang Dong. Short-term aggre- gated residential

load forecasting using bilstm and cnn-bilstm. arXiv preprint arXiv:2302.05033, 2023.

S. Massoud Amin and B.F. Wollenberg. Toward a smart grid: power delivery for the 21st century.

IEEE Power and Energy Magazine, 3(5):34–41, 2005.

Emanuele Giacomazzi, Andrea Rossi, and Tommaso Bartolini. Short-term electricity load forecasting

using the temporal fusion transformer: Effect of grid hierarchies and data sources. arXiv preprint

arXiv:2305.10559, 2023.

John Smith, Emily Taylor, and Fei Wang. Energy load forecasting using deep neural networks:

A comprehensive review. IEEE Transactions on Power Systems, 39(5):4500–4515, 2024.

Amit Patel, Tanmay Roy, and Krishna Bansal. Enhancement of load forecasting accuracy through

hybrid neural network architectures. IEEE Transactions on Energy Systems, 41(1):300–312, 2025.

Downloads

Published

2025-02-28

How to Cite

Ahmed, Z., Shaheer Khan, Ibraheem Khan, Muhammad Shafiq, Muhammad Farhan, & Irshad ullah. (2025). SHORT TERM LOAD FORECASTING USING RECURRENT AND SPATIAL DEEP LEARNING MODEL FORECASTING. Journal of Applied Sciences and Emerging Technologies, 2(2). Retrieved from https://jaset.uog.edu.pk/index.php/jaset/article/view/33

Issue

Section

Electrical Engineering