Multi-State Energy Classifier to Evaluate the Performance of the NILM Algorithm

. 2019 Nov 28;19(23):5236. doi: 10.3390/s19235236

Algorithm 1 Multi-state energy classifier (MEC).

Input:

G_{T} = {g_{1}, g_{2} \dots g_{t}}

is the ground truth of appliance m

P_{T} = {p_{1}, p_{2} \dots p_{t}}

is the predicted values of appliance m

ε

= Accuracy weightage for event classification

(1 - ε)

= Accuracy weightage for energy estimation
Output:

M E C

= MEC accuracy for appliance m

1:
$C_{S t a t e}$ = $A p p l i a n c e S t a t e C l u s t e r i n g (G_{T})$
2:
$P e n a l t y_{E C}^{(m)}$ = $E C P e n a l t y$ ( $G_{T}$ , $P_{T}$ , $C_{S t a t e}$ )
3:
$P e n a l t y_{E E}^{(m)}$ = $E E P e n a l y$ ( $G_{T}$ , $P_{T}$ , $C_{S t a t e}$ )
4:
$T o t a l P e n a l t y_{m}$ = $(ε \cdot P e n a l t y_{E C}^{(m)})$ + $((1 - ε) \cdot P e n a l t y_{E E}^{(m)})$
5:
return $T o t a l P e n a l t y_{m}$