Hadis Dalkani

Work place: Department of Computer Engineering, Liyan Institute of Education, Bushehr, Iran

E-mail: hadis.dalkani76@yahoo.com


Research Interests: Data Science


Hadis Dalkani received his B.E. degree in computer software engineering from Kherad Institute of Higher Education Bushehr, Iran, and Department of Computer Engineering in 2018, and has received his M.Sc. degree in computer software engineering from of Lian Bushehr Institute, Iran, in 2021. His hobbies are Data Visualization, Data Science, Data Analysis, Web Development and Object-Oriented Programming.

Author Articles
Modelling Electricity Consumption Forecasting Using the Markov Process and Hybrid Features Selection

By Hadis Dalkani Musa Mojarad Hassan Arfaeinia

DOI: https://doi.org/10.5815/ijisa.2021.05.02, Pub. Date: 8 Oct. 2021

Given the problem of electrical energy storage, it is critical to predict the amount of load required in order to have a reliable and stable power distribution network. Predicting electricity consumption of subscribers and analyzing their consumption behavior under the influence of various factors and time variables is important. Given the large volume of subscriber consumption data and the effective factors, it is only possible to analyze the data using new information technology tools such as data mining. In this paper, feature selection, clustering and Markov process techniques are used to model and predict the power consumption data of subscribers. First, the selection of a subset of effective features is based on the combined PCA approach and the Firefly algorithm. Subscribers are then clustered based on the features selected by the K-means. Finally, subscriber behavior patterns are modeled to predict consumption using the Markov process on high-risk clusters. This study is simulated based on the data of electricity subscribers in Bushehr-Iran Power Distribution Company. The simulation results show the superiority of the proposed model over other similar algorithms such as LASSO-QRNN and HyFIS. The accuracy of power consumption prediction in the proposed method is about 1% compared to LASSO-QRNN and about 0.5% compared to HyFIS.

[...] Read more.
Other Articles