Open Access

ARTICLE

Energy Demand Forecasting Using Fused Machine Learning Approaches

by Taher M. Ghazal^1,2, Sajida Noreen³, Raed A. Said⁴, Muhammad Adnan Khan^5,*, Shahan Yamin Siddiqui^3,6, Sagheer Abbas³, Shabib Aftab³, Munir Ahmad³

1 Center for Cyber Security, Faculty of Information Science and Technology, Universiti Kebansaan Malaysia (UKM), Bangi, 43600, Selangor, Malaysia
2 School of Information Technology, Skyline University College, University City Sharjah, Sharjah, 1797, UAE
3 School of Computer Science, NCBA&E, Lahore, 54000, Pakistan
4 Canadian University Dubai, Dubai, UAE
5 Pattern Recognition and Machine Learning Lab, Department of Software, Gachon University, Seongnam, 13557, Korea
6 School of Computer Science, Minhaj University Lahore, Lahore, 54000, Pakistan

* Corresponding Author: Muhammad Adnan Khan. Email:

Intelligent Automation & Soft Computing 2022, 31(1), 539-553. https://doi.org/10.32604/iasc.2022.019658

Received 21 April 2021; Accepted 04 June 2021; Issue published 03 September 2021

Abstract

The usage of IoT-based smart meter in electric power consumption shows a significant role in helping the users to manage and control their electric power consumption. It produces smooth communication to build equitable electric power distribution for users and improved management of the entire electric system for providers. Machine learning predicting algorithms have been worked to apply the electric efficiency and response of progressive energy creation, transmission, and consumption. In the proposed model, an IoT-based smart meter uses a support vector machine and deep extreme machine learning techniques for professional energy management. A deep extreme machine learning approach applied to feature-based data provided a better result. Lastly, decision-based fusion applied to both datasets to predict power consumption through smart meters and get better results than previous techniques. The established model smart meter with automatic load control increases the effectiveness of energy management. The proposed EDF-FMLA model achieved 90.70 accuracy for predicting energy consumption with a smart meter which is better than the existing approaches.

---

Keywords

---