Version 1
: Received: 29 June 2023 / Approved: 3 July 2023 / Online: 3 July 2023 (08:12:17 CEST)
Version 2
: Received: 12 July 2023 / Approved: 13 July 2023 / Online: 13 July 2023 (07:31:00 CEST)
How to cite:
Tylor, M.; Banik, D. An Approach Towards Load Pattern Clustering on Smart Meter Data. Preprints2023, 2023070011. https://doi.org/10.20944/preprints202307.0011.v1
Tylor, M.; Banik, D. An Approach Towards Load Pattern Clustering on Smart Meter Data. Preprints 2023, 2023070011. https://doi.org/10.20944/preprints202307.0011.v1
Tylor, M.; Banik, D. An Approach Towards Load Pattern Clustering on Smart Meter Data. Preprints2023, 2023070011. https://doi.org/10.20944/preprints202307.0011.v1
APA Style
Tylor, M., & Banik, D. (2023). An Approach Towards Load Pattern Clustering on Smart Meter Data. Preprints. https://doi.org/10.20944/preprints202307.0011.v1
Chicago/Turabian Style
Tylor, M. and Dipti Banik. 2023 "An Approach Towards Load Pattern Clustering on Smart Meter Data" Preprints. https://doi.org/10.20944/preprints202307.0011.v1
Abstract
Life in the modern century is heavily reliant on an enormous amount of electricity consumption as technology has become the most integral part of daily life. In this context, smart grid systems play a pivotal role to maintain the uninterrupted power supply which needs to be monitored in a timely fashion to keep track of the electric consumers’ usage pattern. The smart meter is the one of smart applications of the smart grid that collects huge amounts of consumer load data on a daily basis which has become a focus for various researchers and analyzers to study load characterization. In this paper, an approach has been proposed to recognize the energy consumption patterns among diverse types of consumers ranging from residential to industrial levels. This approach is worth considering not only for load pattern recognition but also for involving customers in different events such as demand response or peak shaving. In such a way, this analytical mechanism certainly assists in reducing power wastage and saving costs. The proposed methodology is based on a two-fold clustering algorithm with the use of state-of-the-art technology, machine learning. The primary goal is to classify electric customers' data collected from smart meters. Then, analyzing the classified results with an aim to predict power consumption patterns for the customers in the future and making the right energy policy that will benefit both the grid operator and consumers as well.
Computer Science and Mathematics, Computer Science
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.