A two-phase data-driven approach for detection of solar PV and EV infrastructure in smart grid

Rajesh K. Ahir, Viral Biyawala and Shivam Sikotra

Applied Energy, 2025, vol. 391, issue C, No S0306261925006427

Abstract: With the rapid transition towards more flexible, interactive, and intelligent power systems by higher penetration of renewables, electric vehicles (EV), and smart meter data analytics, it is essential for electric utilities to identify such infrastructure in customer premises for efficient grid operation. The study introduces a comprehensive two-phase approach for discerning residences equipped with solar Photovoltaic (PV) installations, EV charging infrastructure, or a combination of both. The first phase deals with detection of above mentioned scenarios/changes in the consumption patterns by employing support vector classifier (SVC). The second phase introduces personalized Long Short-Term Memory (LSTM) and novel dynamic threshold calculation technique for identifying the date on which the change occurred. The Error Profile (EP) for each customer is generated to exhibit the identification of the scenarios on the specific date. The proposed approach yields promising results with an overall F1-score of more than 90 % for various scenarios.

Keywords: Change-type detection; Electric vehicles; Error profile; Smart grid; Smart meter; Solar PV; Dynamic threshold (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261925006427
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:391:y:2025:i:c:s0306261925006427

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2025.125912

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().