Detection of Irregular Consumption to Load Monitoring in Smart Grids Environment

Bogdan C. Neagu, Gheorghe Grigoraș

Abstract

Today, power distribution operators are concerned about irregular behavior of electricity consumption in their decision-making process. In the load data, abnormal consumptions may happen due to measurement error, undetected consumption, illegal electricity connection, improperly installed equipment etc. The paper presents a statistical approach which acquires the basic concept of knowledge discovery on databases (KDD)with data mining, focuses on the identification of outliers (irregular consumption) from load curves recorded by Smart Meters on the substation of the power distribution networks. In order to validate the proposed approach, a real database with 300 substations from rural area was used. The results demonstrate that by detection and elimination of irregular consumption, the load curves can be efficiently used by modern distribution operators for a better operation and planning of actually “smart” networks.

Keywords

data mining, load monitoring, irregular consumption, Smart Grids

Download

IMEKO-TC4-2017-035.pdf

DOI

-

IMEKO TC

TC4 - Measurement of Electrical Quantities

Back to the proceedings