Rule‐based classification of energy theft and anomalies in consumers load demand profile. Issue 4 (13th September 2019)

• Record Type: Journal Article
• Authors: Jain, Sonal; Choksi, Kushan A.; Pindoriya, Naran M.
• Is Part Of: IET smart grid. Volume 2:Issue 4(2019)
• Page Start: 612
• Page End: 624
• Publication Date: 2019-09-13
• Subjects: pattern classification -- power consumption -- data mining -- security of data -- learning (artificial intelligence) -- fraud -- power system management -- power engineering computing -- data privacy -- metering -- power meters -- knowledge based systems -- meta data; classification block -- rule‐based classification -- energy theft -- consumers load demand profile -- advanced metering infrastructure -- AMI -- consumers consumption patterns -- power utilities -- fraud detection methodology -- data mining techniques -- consumer consumption patterns -- rule‐base learning -- validation technique -- energy anomalies -- abnormality type classification -- validation block -- privacy preservation -- metadata; B8110B Power system management, operation and economics -- B8150 Power system measurement and metering -- C6130S Data security -- C6160 Database management systems (DBMS) -- C6170K Knowledge engineering techniques -- C7410B Power engineering computing; Smart power grids -- Periodicals; Computer science -- Periodicals; Energy industries -- Periodicals; Broadcasting -- Periodicals; 333.79110285
• DOI: 10.1049/iet-stg.2019.0081
• Languages: English
• ISSNs: 2515-2947

Abstract

Abstract : The invent of advanced metering infrastructure (AMI) opens the door for a comprehensive analysis of consumers consumption patterns including energy theft studies, which were not possible beforehand. This study proposes a fraud detection methodology using data mining techniques such as hierarchical clustering and decision tree classification to identify abnormalities in consumer consumption patterns and further classify the abnormality type into the anomaly, fraud, high or low power consumption based on rule‐based learning. The proposed algorithm uses real‐time dataset of Nana Kajaliyala village, Gujarat, India. The focus has been on generalizing the algorithm for varied practical cases to make it adaptive towards non‐malicious changes in consumer profile. Simultaneously, this study proposes a novel validation technique used for validation, which utilizes predicted profiles to ensure accurate bifurcation between anomaly and theft targets. The result exhibits high detection ratio and low false‐positive ratio due to the application of appropriate validation block. The proposed methodology is also investigated from point of view of privacy preservation and is found to be relatively secure owing to low‐sampling rates, minimal usage of metadata and communication layer. The proposed algorithm has an edge over state‐of‐the‐art theft detection algorithms in detection accuracy and robustness towards outliers.