| Related citation: | K.Rama Devi,V.Srinivasan,G. Clara Barathi Priyadharshini,J. Gokulapriya.Intelligent Energy Utilization Analysis Using IUA-SMD Model Based Optimization Technique for Smart Metering Data[J].Journal of Harbin Institute Of Technology(New Series),2024,31(1):90-98.DOI:10.11916/j.issn.1005-9113.2023014. |
|
| Author Name | Affiliation | | K.Rama Devi | Department of Information Technology, Panimalar Engineering College, Chennai, Tamil Nadu 600029, India | | V.Srinivasan | Department of Computer Applications, Dayananda Sagar College of Engineering, Bengaluru 560078, Karnataka, India | | G. Clara Barathi Priyadharshini | Department of Computer Appliations, Karpagam Academy of Higher Education, Coimbatore, Tamil Nadu 641021, India | | J. Gokulapriya | Department of Computer Science, Rathinam College of Arts and Science, Coimbatore, Tamil Nadu 641021, India |
|
| Abstract: |
| Smart metering has gained considerable attention as a research focus due to its reliability and energy-efficient nature compared to traditional electromechanical metering systems. Existing methods primarily focus on data management, rather than emphasizing efficiency. Accurate prediction of electricity consumption is crucial for enabling intelligent grid operations, including resource planning and demand-supply balancing. Smart metering solutions offer users the benefits of effectively interpreting their energy utilization and optimizing costs. Motivated by this, this paper presents an Intelligent Energy Utilization Analysis using Smart Metering Data (IUA-SMD) model to determine energy consumption patterns. The proposed IUA-SMD model comprises three major processes: data Pre-processing, feature extraction, and classification, with parameter optimization. We employ the extreme learning machine (ELM) based classification approach within the IUA-SMD model to derive optimal energy utilization labels. Additionally, we apply the shell game optimization (SGO) algorithm to enhance the classification efficiency of the ELM by optimizing its parameters. The effectiveness of the IUA-SMD model is evaluated using an extensive dataset of smart metering data, and the results are analyzed in terms of accuracy and mean square error (MSE). The proposed model demonstrates superior performance, achieving a maximum accuracy of 65.917% and a minimum MSE of 0.096. These results highlight the potential of the IUA-SMD model for enabling efficient energy utilization through intelligent analysis of smart metering data. |
| Key words: electricity consumption predictive model data analytics smart metering machine learning |
| DOI：10.11916/j.issn.1005-9113.2023014 |
| Clc Number:TM933 |
| Fund: |
