Non-Intrusive Similar Loads Identification

Citation Author(s):
Aloisio
Paixao
IFES
Wanderley
Celeste
DCEL/UFES
Luis
Rigo Jr.
DCEL/UFES
Daniel
Coura
DCEL/UFES
Helder
Rocha
DEL/UFES
Leonardo
Silvestre
DCEL/UFES
Silvia
Rissino
DCEL/UFES
Submitted by:
Luis Rigo Jr
Last updated:
Wed, 06/19/2019 - 15:21
DOI:
10.21227/mynq-a588
Data Format:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

This data set is composed by samples of load signature of electric devices acquired on a non-intrusively form. The test-bench was performed using four identical fluorescent lamps, four identical slots and four identical switches. Identical term means the same technical specifications (nominal voltage, power, isolation voltage, among others). The sensors are connected to the power supply in order to measure the electrical variations when appliances are turned on/off. We have 16 possible network configurations with 4 appliances, in which one, two, three or four appliances can be turned on. For each configuration, the acquisition of 150 samples was performed in four ways, i. e., 5, 10, 15 and 20 minutes after setting a new configuration, in order to increase the probability of obtaining a more heterogeneous set of samples.

Instructions: 

This database has 2400 samples. Each line is a feature vector represent a sample, composed by:
- Active power (P);
- Reactive power (Q);
- Apparent power (S);
- Power factor (FP);
- Effective current (Irms);
- 1st harmonic component;
- 3rd harmonics component;
- 5th harmonics component;
- 7th harmonics component;
- 9th harmonics component;
- 11th harmonics component;
- 13th harmonics component;
- 15th harmonics component;
- 17th harmonics component;
- Class;
- Sample weight.

Comments

Hi, 

could you help me to download the dataset?

Thank you 

Valentina

Submitted by Valentina Scarpa on Thu, 12/05/2019 - 03:25

sign up free and then click the link where size of file define

Submitted by Sami Ullah on Thu, 11/12/2020 - 02:36