February 21, 2024
Abdolkarim Hosseinpoor

Abdolkarim Hosseinpoor

Academic Rank: Assistant professor
Degree: Ph.D in Economics
Phone: 07731222772
Faculty: School of Business and Economics


Comparison of Arima and Hidden markov Methods in Forecasting Residential Electricity Demand in Bushehr Province
Type Thesis
تقاضاي برق، بخش مسكوني، ماركوف پنهان، خودرگرسيون ميانگين متحرك انباشته، استان بوشهر
Researchers simin rasti (Student) , Abdolkarim Hosseinpoor (Primary advisor) , Fazlollah Lak (Advisor) , Ebrahim Heidari (Advisor)


Background: Energy consumption in the residential sector has increased significantly in the past years. Electricity demand forecasting is beneficial for both consumers and suppliers, as it allows improving energy efficiency policies and the rational use of resources. Aim: The main goal of this study is to compare the prediction accuracy of the models used in this research using different evaluation criteria. Methodology: The data of this study is the monthly electricity consumption of Bushehr province from 1390:01 to 1401:05. We have used data from 1390:01 to 2019:06 for training and data from 1399:07 to 1401:05 to test the model and obtain prediction accuracy. In this research, forecasting has been done using ARIMA and HMM models and with Eviews and R software. Conclusions: The main goal of this research was to compare two methods, HMM and ARIMA, in forecasting electricity demand in the residential sector. In this study, different evaluation criteria including RMSE and MAE were used. The results of the study show that the performance of the seasonal ARIMA model is better than the HMM model.