Predicting Electricity Usage of Houses Incorporating Smart Meters

Abstract

The need for smart grid user-side management is becoming more critical as smart power distribution networks evolve. This study suggests a short-term power load forecasting model based on K-means and Clustering to increase the precision of short-term electric load forecasting for individual customers. Local comparable daily data are used as characteristics for users with poor correlation at adjacent times. Based on the -means cluster analysis technique, a clustering module was created. The clustering module was validated using home load profiles based on smart meters. Utilizing daily and segmented load profiles from individual and collective smart meter data, many case studies were put into practice. The smallest segmentation time window yields the lowest clustering ratio, according to simulation findings described in terms of the correlation between the clustering ratio and the time window. Results also indicate that for strongly coupled load profiles, a limited number of clusters is advised. Last but not least, the feather vectors are sent into the BP Neural Network, which forecasts the short-term load. According to experimental findings, the suggested clustering algorithm matches the features of customers' power consumption pattern. The accuracy of clustering-based load forecasting is higher than that of non-clustering load forecasting when using the same forecasting methodology. This model offers superior predicting accuracy when compared to conventional BP, RBF, and GRNN Neural Network.

Authors and Affiliations

Musaib Amin, Dharminder Kumar, and Dr. Satish Saini

Keywords

Related Articles

Exploring The World Of Collaborative Sharing Over The Internet Through The Use Of A PeerTo-Peer Network Protocol

Abstract-P2P downloads represent a large portion of today’s Internet traffic. Millions of users operate BitTorrent and generate more than 30% of the total Internet traffic. This paper mainly examines the working of the B...

Low Power Implementation of QRS Detection System

This paper proposes a modification of the pre-processing stage of the Pan-Tompkins algorithm. In this paper, the fractional order differentiator now stands in for the integer order differentiator. Since the gain of the f...

Design and Topology Optimization on Car Wheel Rim Using FEA

Since their beginnings, automotive wheels have evolved over decades. Wood and stone were used to make the antique wheel rims. The wheel rim, as an essential and crucial portion of the vehicle, was concentrated on with ex...

INDPLAY-A Software Solution for Uncovering India's Sporting Talent

In an era where the pursuit of sporting dreams often encounters formidable challenges, INDPLAY emerges as a beacon of hope and opportunity for aspiring youth and children passionate about forging a career in sports. Reco...

A Machine Learning Model for Clinical Decision Support for Drug Recommendation

Modern machine learning techniques play a very crucial role in dealing with very complex unstructured data that is available in the medical domain. The wide range of applications in this area is capable of changing the...

Download PDF file
  • EP ID EP746036
  • DOI 10.55524/ijircst.2022.10.5.10
  • Views 1
  • Downloads 0

How To Cite

Musaib Amin, Dharminder Kumar, and Dr. Satish Saini (2022). Predicting Electricity Usage of Houses Incorporating Smart Meters. International Journal of Innovative Research in Computer Science and Technology, 10(5), -. https://europub.co.uk/articles/-A-746036