Forecasting Monthly Electricity Consumption Using Machine Learning and Statistical-Based Models: A Case Study

Authors

  • ABDUL JALIL NIAZAI Author
  • MOHAMMAD AKBAR SHAHPOOR Author
  • ABDULLAH ZAHIRZADA Author
  • ABDUL RAHMAN SAFI Author
  • NOOR AHMAD NOORI Author

DOI:

https://doi.org/10.68924/6hnqap90

Keywords:

ARIMA, Forecasting, Electricity Consumption Demand, Kunduz Province, MLP

Abstract

Forecasting electricity consumption demand plays a vital role in short-term load balancing and long-term planning for having secure power systems, new energy generation, and transmission infrastructures. Knowing the consumption demand is also essential in preparing the power system according to the anticipated load status. In this research paper, we conducted a time series forecasting analysis on the monthly electricity consumption data of Kunduz province gathered from April 2011 to July 2022 to predict the consumption demand in this province. For this purpose, we employed two well-known forecasting methods: Multilayer perceptron (MLP) from machine learning and ARIMA from statistics. The MAPE and MAE metrics were used to measure and compare the predictive performance of developed MLP and ARIMA models. The comparison result found that MLP outperforms ARIMA in model forecasting accuracy. We believe that the outcomes of this research work significantly help Kunduz’s regional electricity authorities in better energy management and allow them to make effective decisions regarding electrical energy cost and efficiency.

Author Biographies

  • ABDUL JALIL NIAZAI

    Abdul Jalil Niazai is an assistant professor at Kunduz University’s software engineering department. He got a master’s degree in information management from the Asian Institute of Technology (AIT), Thailand, in 2019, and BSc in computer science from Peshawar University in 2015. His research interest lies in data science, machine learning, and computer vision. Abdul Jalil Niazai has been acting as leader of the research committee of the software engineering department since 2020 at Kunduz University.

  • MOHAMMAD AKBAR SHAHPOOR

    Mohammad Akbar Shahpoor received a BCS degree in computer science from Nangarhar university in 2012 and an MSC degree in computer science from the Indian Academy Degree College of Bangalore, India, in 2018. Presently, he is working as an assistant professor in the department of software engineering at Kunduz university. His research areas include software engineering, data science, and machine learning.

  • ABDULLAH ZAHIRZADA

    Abdullah Zahirzada received a B.Sc. degree in computer science from Kunduz University, Afghanistan, in 2016 and an M.Sc. in Information Technology at the School of Information Technology (SIT) from King Mongkut’s University of Technology Thonburi, Thailand, in 2022. Presently, he is working as an assistant professor in the department of Information Systems at Kunduz university. His research interests are Data Science, Data Mining, Image Processing, Machine Learning, and Cognitive Computing.

  • ABDUL RAHMAN SAFI

    Abdul Rahman Safi received a BCS degree in Information Systems from Kabul University in 2013 and an MS degree in Information Management from the Asian Institute of Technology, Thailand, in 2019. His research areas include software engineering, data science, and artificial intelligence. Presently, he is working as an assistant professor in the department of Information Systems at Kabul University.

  • NOOR AHMAD NOORI

    Noor Ahmad Noori is currently a Ph.D. scholar at the National University of Science & Technology, Pakistan. He received an MS in Information Management from the Asian Institute of Technology, Thailand, in 2018 and a BSc degree in Computer Science from Peshawar University, Pakistan, in 2014. His research interests include Data Science, Big Data Analysis, Machine Learning, and Computer Networking. Noor Ahmad has eight years of administrative, teaching, and research experience.

Downloads

Published

2026-08-22

Issue

Section

Articles

How to Cite

Forecasting Monthly Electricity Consumption Using Machine Learning and Statistical-Based Models: A Case Study. (2026). Kabul Polytechnic University International Journal of Engineering & Technology, 2(2), 75-92. https://doi.org/10.68924/6hnqap90