55
Internet of Things and Artificial Intelligence
3.7.3 Experiment 3: Prediction and forecasting using Deep
Convolutional Neural Network with REDD Dataset
Finally, the third experiment is conducted in the REDD dataset for more knowledge on IoT
scenario with an understanding of the energy consumption in an hourly to yearly basis for
smart applications. The results obtained are presented in Figures 3.9 and 3.10.
From all the results obtained above, one can envisage the behavior of the consumer
in using energy for their daily life at a suitable hour, daily, monthly and yearly basis for
making effective decision-making process.
70
60
50
40
30
20
10
0
1
2
3
4
5
6
7
8
9 10 11
Future forecast for: energy_cons_total, energy_exp_total, energy_exp_persqft
12 13 14 15 16 17 18 19 20 21 22 23 24
energy_cons_total
energy_exp_total
energy_exp_persqft
energy_cons_total-predicted
energy_exp_total-predicted
energy_exp_persqft-predicted
FIGURE 3.7
RECS data future prediction for some attributes.
30
25
20
15
10
5
0
2 5 0
0
5 0 0
1 , 0 0 0
7 5 0
1 , 2 5 0
1 , 5 0 0
1 , 7 5 0
2 , 2 5 0
2 , 5 0 0
2 , 7 5 0
Future forecast for: UsageKW [95% conf.intervals]
2 , 0 0 0
3 , 2 5 0
3 , 5 0 0
3 , 7 5 0
3 , 0 0 0
4 , 2 5 0
4 , 5 0 0
4 , 7 5 0
4 , 0 0 0
5 , 2 5 0
5 , 5 0 0
5 , 7 5 0
5 , 0 0 0
6 , 2 5 0
6 , 5 0 0
6 , 7 5 0
6 , 0 0 0
7 , 2 5 0
7 , 5 0 0
7 , 0 0 0
UsageKW
UsageKW-predicted
FIGURE 3.8
Future predictions for microgrid data.