I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
14
,
No
.
6
,
Dec
em
b
er
20
24
,
p
p
.
7
0
6
7
~
7
0
7
9
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
14
i
6
.
pp
7
0
6
7
-
7
0
7
9
7067
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Lo
a
d f
o
recas
ting
using
f
uzzy
log
ic,
a
rtif
icia
l ne
ura
l n
etwork
,
a
nd
a
da
ptive neu
ro
-
fuzzy in
fere
nc
e sy
stem
a
ppro
a
c
hes:
a
pplica
tion to So
uth
-
W
estern
Mo
r
o
cco
H
icha
m
Stit
o
u,
M
o
ha
m
ed
A
m
ine
At
illa
h,
Abdelg
ha
ni B
o
ud
a
o
ud
,
M
o
un
a
im
Aqil
En
g
i
n
e
e
r
i
n
g
a
n
d
A
p
p
l
i
e
d
P
h
y
s
i
c
s
Te
a
m,
S
u
p
e
r
i
o
r
S
c
h
o
o
l
o
f
Te
c
h
n
o
l
o
g
y
,
S
u
l
t
a
n
M
o
u
l
a
y
S
l
i
ma
n
e
U
n
i
v
e
r
si
t
y
,
B
e
n
i
M
e
l
l
a
l
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
9
,
2
0
2
4
R
ev
is
ed
J
u
l 1
5
,
2
0
2
4
Acc
ep
ted
Au
g
6
,
2
0
2
4
Th
e
d
e
m
a
n
d
fo
r
e
n
e
rg
y
o
n
a
g
l
o
b
a
l
sc
a
le
is
c
o
n
ti
n
u
o
u
sly
risin
g
d
u
e
t
o
t
h
e
e
x
p
a
n
sio
n
o
f
e
n
e
rg
y
i
n
fra
stru
c
t
u
re
a
n
d
t
h
e
i
n
c
re
a
sin
g
n
u
m
b
e
r
o
f
n
e
w
a
p
p
li
a
n
c
e
s.
To
a
d
d
re
ss
th
is
g
r
o
win
g
n
e
e
d
,
a
n
e
fficie
n
t
e
n
e
rg
y
m
a
n
a
g
e
m
e
n
t
sy
ste
m
(EM
S
)
h
a
s
b
e
c
o
m
e
in
d
isp
e
n
sa
b
le.
B
y
imp
lem
e
n
ti
n
g
E
M
S
,
b
o
t
h
re
sid
e
n
ti
a
l
a
n
d
c
o
m
m
e
rc
ial
b
u
il
d
i
n
g
s
c
a
n
sig
n
ifi
c
a
n
tl
y
imp
r
o
v
e
th
e
ir
e
n
e
rg
y
e
fficie
n
c
y
a
n
d
c
o
n
s
u
m
p
ti
o
n
.
On
e
c
ru
c
ial
a
sp
e
c
t
o
f
e
n
a
b
li
n
g
EM
S
to
o
p
e
ra
te
e
fficie
n
tl
y
is
l
o
a
d
f
o
re
c
a
stin
g
.
T
h
e
a
c
c
u
ra
c
y
o
f
lo
a
d
f
o
re
c
a
stin
g
d
e
p
e
n
d
s
o
n
n
u
m
e
r
o
u
s
fa
c
to
rs.
A
re
li
a
b
le
l
o
a
d
f
o
re
c
a
st
m
o
d
e
l
s
h
o
u
ld
c
o
n
sid
e
r
t
h
e
re
g
io
n
’s
we
a
th
e
r
fo
re
c
a
st,
a
s
it
p
l
a
y
s
a
c
ru
c
ial
ro
le
i
n
d
e
v
e
lo
p
in
g
a
n
a
c
c
u
ra
te
p
re
d
ictio
n
.
T
h
is
st
u
d
y
is
a
b
o
u
t
t
h
e
m
e
d
iu
m
-
term
lo
a
d
f
o
re
c
a
stin
g
(M
TL
F
)
fo
r
t
h
e
P
ro
v
in
c
e
o
f
Taro
u
d
a
n
t,
M
o
ro
c
c
o
,
u
sin
g
h
ist
o
rica
l
m
o
n
th
l
y
l
o
a
d
a
n
d
we
a
th
e
r
d
a
ta
fo
r
fiv
e
y
e
a
rs
(2
0
1
8
t
o
2
0
2
2
).
To
fo
re
c
a
st
c
o
n
su
m
e
d
e
n
e
rg
y
th
re
e
m
e
th
o
d
s
a
re
u
se
d
n
a
m
e
ly
a
rti
ficia
l
n
e
u
ra
l
n
e
two
r
k
(AN
N),
f
u
z
z
y
lo
g
ic
(F
L)
a
n
d
a
d
a
p
t
iv
e
n
e
u
r
o
-
fu
z
z
y
i
n
fe
re
n
c
e
sy
ste
m
(A
NFIS
).
Th
is
p
a
p
e
r
se
lec
ts
a
b
so
lu
te
p
e
rc
e
n
tag
e
e
rro
r
(APE
)
,
m
e
a
n
a
b
so
lu
te
p
e
rc
e
n
tag
e
e
rro
r
(M
APE
),
c
o
rre
latio
n
c
o
e
fficie
n
t
(R)
a
n
d
r
o
o
t
m
e
a
n
sq
u
a
re
e
rro
r
(RM
S
E)
t
o
c
o
m
p
a
re
a
n
d
e
v
a
lu
a
te t
h
e
p
re
d
ictio
n
a
c
c
u
r
a
c
y
o
f
m
o
d
e
ls.
It
h
a
s b
e
e
n
o
b
se
rv
e
d
th
r
o
u
g
h
re
su
lt
s
a
n
a
ly
sis
th
a
t
th
e
AN
F
I
S
m
o
d
e
l
p
ro
d
u
c
e
s
v
e
ry
a
c
c
u
ra
te
f
o
re
c
a
stin
g
p
re
d
ictio
n
with
M
APE
o
f
4
.
7
5
%
wh
il
e
AN
N
a
n
d
F
L
m
o
d
e
ls
g
i
v
e
re
sp
e
c
ti
v
e
ly
M
AP
E
o
f
7
.
3
6
%
a
n
d
8
.
4
2
%
.
K
ey
w
o
r
d
s
:
Ad
ap
tiv
e
n
eu
r
o
-
f
u
zz
y
in
f
er
en
ce
s
y
s
tem
Ar
tific
ial
n
eu
r
al
n
etwo
r
k
E
n
er
g
y
ef
f
icien
cy
E
n
er
g
y
m
an
ag
e
m
en
t sy
s
tem
Fu
zz
y
lo
g
ic
L
o
ad
f
o
r
ec
asti
n
g
Po
wer
s
y
s
tem
s
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Hich
am
Sti
to
u
E
n
g
i
n
e
e
r
i
n
g
a
n
d
A
p
p
l
i
e
d
P
h
y
s
ic
s
T
e
a
m
,
S
u
p
e
r
i
o
r
S
c
h
o
o
l
o
f
T
e
c
h
n
o
l
o
g
y
,
S
u
l
t
a
n
M
o
u
l
a
y
Sl
im
a
n
e
U
n
i
v
e
r
s
it
y
B
en
i M
ellal,
Mo
r
o
cc
o
E
m
ail: h
ich
am
.
s
tito
u
@
u
s
m
s
.
m
a
1.
I
NT
RO
D
UCT
I
O
N
T
o
en
h
a
n
ce
th
e
ef
f
icien
cy
o
f
o
p
er
atio
n
al
m
a
n
ag
em
e
n
t
an
d
s
tr
ateg
ic
p
lan
n
i
n
g
in
b
o
th
th
e
p
r
o
cu
r
em
en
t
an
d
g
e
n
er
atio
n
o
f
elec
tr
ic
p
o
wer
,
u
tili
ties
ar
e
r
eq
u
ir
ed
to
m
ak
e
c
r
u
c
ial
d
ec
is
io
n
s
.
L
o
ad
f
o
r
ec
asti
n
g
s
tan
d
s
o
u
t
as
a
p
i
v
o
tal
task
f
o
r
u
tili
ties
,
s
er
v
in
g
as
a
p
o
te
n
t
to
o
l
f
o
r
p
o
wer
s
y
s
tem
o
p
er
ato
r
s
t
o
elev
ate
s
er
v
ice
q
u
ality
an
d
to
im
p
r
o
v
e
g
r
id
s
ec
u
r
ity
.
L
o
ad
f
o
r
ec
asti
n
g
ca
n
b
e
ca
teg
o
r
ized
in
to
f
o
u
r
d
is
tin
ct
ty
p
es
b
ased
o
n
t
h
e
tim
e
h
o
r
izo
n
an
d
s
p
ec
if
ic
tar
g
ets
[
1
]
–
[
3
]
:
L
T
L
F
k
n
o
w
n
as
lo
n
g
ter
m
lo
a
d
f
o
r
ec
asti
n
g
:
T
h
is
m
eth
o
d
d
ea
ls
with
f
o
r
ec
asti
n
g
lo
ad
s
f
o
r
a
p
er
i
o
d
lo
n
g
er
th
an
o
n
e
y
ea
r
.
I
ts
p
r
i
m
ar
y
u
s
e
is
in
s
tr
ateg
ic
p
lan
n
i
n
g
f
o
r
th
e
d
e
v
elo
p
m
e
n
t
o
f
elec
tr
ic
p
o
wer
s
y
s
tem
s
,
p
r
o
v
id
in
g
in
s
ig
h
ts
f
o
r
f
u
tu
r
e
r
eq
u
i
r
em
e
n
ts
an
d
f
ac
ilit
atin
g
p
r
o
ac
tiv
e
d
ec
is
io
n
-
m
ak
in
g
.
M
ed
iu
m
-
ter
m
l
o
ad
f
o
r
ec
asti
n
g
(
MT
L
F)
k
n
o
wn
as
m
e
d
iu
m
ter
m
lo
ad
f
o
r
ec
asti
n
g
:
f
o
cu
s
ed
o
n
th
e
f
o
r
ec
asti
n
g
o
f
lo
ad
o
v
er
a
p
er
io
d
r
a
n
g
in
g
f
r
o
m
o
n
e
wee
k
to
o
n
e
y
ea
r
.
I
ts
a
p
p
licatio
n
s
in
clu
d
e
th
e
p
lan
n
in
g
o
f
f
u
el
s
u
p
p
lies
an
d
th
e
ef
f
ec
ti
v
e
m
a
n
ag
em
en
t
o
f
u
n
its
.
STL
F
as
s
h
o
r
t
-
ter
m
lo
ad
f
o
r
ec
asti
n
g
:
u
s
ed
to
f
o
r
ec
ast
lo
ad
f
o
r
d
u
r
a
tio
n
r
a
n
g
in
g
f
r
o
m
o
n
e
h
o
u
r
to
o
n
e
wee
k
,
STL
F
ass
is
ts
in
esti
m
atin
g
lo
ad
f
lo
w
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
7
0
6
7
-
7
0
7
9
7068
an
d
m
ak
i
n
g
d
ec
is
io
n
s
to
p
r
e
v
e
n
t
o
v
er
l
o
ad
in
g
.
VSTL
F
as
v
er
y
s
h
o
r
t
-
ter
m
lo
ad
f
o
r
ec
asti
n
g
p
lay
s
a
cr
itical
r
o
le
in
r
ed
u
ci
n
g
o
p
er
atin
g
co
s
ts
,
m
ain
tain
in
g
e
f
f
icien
cy
in
en
e
r
g
y
m
a
r
k
ets,
an
d
im
p
r
o
v
i
n
g
u
n
d
er
s
tan
d
in
g
o
f
th
e
d
y
n
am
ics
with
in
th
e
m
o
n
ito
r
e
d
s
y
s
tem
wh
e
n
u
s
ed
to
f
o
r
ec
a
s
t
lo
ad
with
in
a
p
er
io
d
o
f
a
f
e
w
m
in
u
tes
to
a
f
ew
h
o
u
r
s
.
Mu
ltip
le
v
ar
iab
les,
in
clu
d
in
g
tem
p
o
r
al
f
ac
to
r
s
an
d
wea
th
er
d
ata,
ar
e
co
n
s
id
er
e
d
b
y
S
T
L
F.
T
h
e
m
ed
iu
m
an
d
l
o
n
g
-
ter
m
f
o
r
ec
a
s
ts
tak
e
in
to
ac
co
u
n
t
th
e
ca
teg
o
r
ies
an
d
th
e
n
u
m
b
er
o
f
cu
s
to
m
er
s
,
d
em
o
g
r
ap
h
ic
an
d
ec
o
n
o
m
ic
d
ata,
h
is
to
r
ical
lo
ad
p
r
o
f
iles
,
wea
th
er
d
ata,
a
s
well
a
s
o
th
er
r
elev
an
t
f
ac
to
r
s
.
I
t
is
n
o
tewo
r
th
y
th
at
wea
th
er
co
n
d
itio
n
s
s
ig
n
if
ican
tly
in
f
lu
en
ce
t
h
e
lo
ad
f
o
r
ec
ast,
p
ar
ticu
lar
ly
in
s
h
o
r
t
an
d
m
ed
iu
m
-
ter
m
p
r
ed
ictio
n
s
.
L
o
ad
f
o
r
ec
asti
n
g
co
n
s
id
er
s
m
u
ltip
le
m
eteo
r
o
l
o
g
ical
v
ar
ia
b
les,
with
h
u
m
id
i
ty
,
win
d
s
p
ee
d
a
n
d
tem
p
er
atu
r
e
em
er
g
i
n
g
as
th
e
m
ain
f
ac
to
r
s
th
at
a
r
e
o
f
ten
u
s
ed
to
p
r
e
d
ict
th
e
lo
ad
d
em
a
n
d
[
4
]
–
[
6
]
.
Giv
e
n
th
e
n
ee
d
s
an
d
g
o
als,
it is
p
o
s
s
ib
le
to
ch
o
o
s
e
an
y
o
f
th
e
ty
p
es p
r
e
v
io
u
s
ly
m
en
tio
n
ed
.
T
h
is
s
tu
d
y
s
p
ec
if
ically
co
n
ce
n
tr
ates
o
n
MT
L
F
f
o
r
p
r
ed
icti
n
g
f
u
tu
r
e
lo
ad
i
n
T
ar
o
u
d
an
n
t
P
r
o
v
in
ce
.
A
lar
g
e
n
u
m
b
er
o
f
f
o
r
ec
as
tin
g
m
eth
o
d
s
h
av
e
b
ee
n
th
e
s
u
b
ject
o
f
liter
atu
r
e
s
tu
d
ies,
in
clu
d
in
g
th
e
au
to
r
eg
r
ess
iv
e
in
teg
r
ated
m
o
v
in
g
av
er
a
g
e
(
AR
I
MA
)
m
o
d
e
l
[
7
]
,
lin
ea
r
r
eg
r
ess
io
n
[
8
]
–
[
1
0
]
,
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
[
1
1
]
–
[
1
3
]
,
f
u
zz
y
lo
g
ic
(
FL)
[
1
4
]
,
[
1
5
]
,
an
d
ad
ap
tiv
e
n
eu
r
o
-
f
u
zz
y
i
n
f
er
en
ce
s
y
s
tem
(
ANFI
S)
[
1
6
]
–
[
1
9
]
.
B
ased
o
n
th
is
liter
atu
r
e
r
ev
iew,
th
e
ANFI
S
ap
p
r
o
ac
h
a
p
p
ea
r
s
to
o
f
f
er
m
o
r
e
b
en
ef
its
d
u
e
to
its
u
n
iq
u
e
c
h
ar
ac
ter
is
tics
.
T
h
e
r
ea
s
o
n
b
eh
in
d
th
is
ca
n
b
e
el
u
cid
ated
b
y
th
e
f
ac
t
th
at
A
NFI
S
r
ep
r
esen
ts
a
s
o
p
h
is
ticated
h
y
b
r
i
d
s
y
s
tem
s
ea
m
less
ly
in
teg
r
atin
g
th
e
lear
n
in
g
a
p
p
r
o
ac
h
o
f
ANN
with
t
h
e
lo
g
ic
r
em
in
is
ce
n
t
o
f
h
u
m
an
r
ea
s
o
n
in
g
in
th
e
f
u
z
zy
lo
g
ic
(
FL)
.
I
n
th
is
s
tu
d
y
,
f
u
zz
y
lo
g
ic,
ANN,
an
d
ANFI
S
ap
p
r
o
ac
h
es
ar
e
p
r
o
p
o
s
ed
f
o
r
m
e
d
iu
m
-
ter
m
lo
ad
f
o
r
ec
asti
n
g
b
ased
o
n
a
r
e
al
ca
s
e
s
tu
d
y
.
Usi
n
g
h
is
to
r
ical
lo
ad
s
an
d
m
ete
o
r
o
lo
g
ical
d
ata
,
th
r
ee
m
o
d
els
ar
e
cr
ea
ted
to
p
r
ed
ict
m
o
n
th
l
y
l
o
ad
s
f
o
r
th
e
P
r
o
v
in
ce
o
f
T
ar
o
u
d
an
n
t,
lo
ca
ted
in
t
h
e
So
u
s
s
-
Ma
s
s
a
R
eg
io
n
o
f
Mo
r
o
cc
o
,
f
o
r
t
h
e
f
iv
e
y
ea
r
s
2
0
1
8
-
2
0
2
2
.
I
n
p
u
ts
f
o
r
all
m
o
d
els
ar
e
m
o
n
th
in
d
e
x
(
MI
)
,
m
o
n
th
ly
m
ea
n
tem
p
er
atu
r
e
(
T
)
an
d
m
o
n
th
ly
win
d
s
p
ee
d
(
W
S).
T
h
e
p
r
e
d
ictio
n
v
alu
es
u
s
in
g
FL
ar
e
c
o
m
p
ar
ed
with
th
e
ac
t
u
al
lo
ad
an
d
t
h
e
r
esu
lts
o
f
b
o
th
t
h
e
ANN
an
d
ANFI
S
m
eth
o
d
.
T
h
is
p
a
p
er
is
s
tr
u
ctu
r
ed
as
f
o
llo
ws;
we
s
tar
t
b
y
b
r
ief
ly
r
ev
iewin
g
th
e
lo
a
d
f
o
r
e
ca
s
tin
g
tech
n
iq
u
es.
T
h
e
s
ec
o
n
d
s
ec
tio
n
is
a
d
escr
ip
tio
n
o
f
th
e
m
eth
o
d
o
lo
g
y
a
n
d
m
ater
ials
u
s
ed
in
th
is
wo
r
k
.
Sectio
n
3
d
ea
ls
with
th
e
p
r
esen
tatio
n
an
d
d
is
cu
s
s
io
n
o
f
th
e
r
esu
lts
.
W
h
ile
s
ec
tio
n
4
s
er
v
es a
s
th
e
co
n
clu
s
io
n
.
2.
M
AT
E
R
I
AL
S AN
D
M
E
T
H
O
D
2
.
1
.
Da
t
a
co
llect
io
n descript
io
n
I
n
th
is
s
tu
d
y
,
t
h
e
f
o
c
u
s
ar
ea
is
th
e
T
ar
o
u
d
an
n
t
P
r
o
v
in
ce
,
s
itu
ated
with
in
th
e
So
u
s
s
-
Ma
s
s
a
R
eg
io
n
o
f
Mo
r
o
cc
o
.
L
o
ca
ted
in
th
e
s
o
u
th
wester
n
p
ar
t o
f
th
e
co
u
n
tr
y
.
T
ar
o
u
d
a
n
n
t sh
ar
es b
o
r
d
er
s
with
s
p
ec
if
ic
p
r
o
v
in
ce
s
,
as
illu
s
tr
ated
in
Fig
u
r
e
1
.
T
o
t
h
e
west
o
f
T
a
r
o
u
d
an
n
t
lies
th
e
Ag
ad
ir
-
I
d
a
Ou
T
a
n
an
e
Pr
o
v
i
n
ce
,
wh
ile
m
o
v
in
g
n
o
r
th
war
d
b
r
in
g
s
u
s
to
th
e
C
h
ich
ao
u
a
an
d
E
l
Hao
u
z
P
r
o
v
in
c
e,
b
o
th
in
teg
r
al
p
ar
ts
o
f
th
e
So
u
s
s
-
Ma
s
s
a
R
eg
io
n
.
Hea
d
in
g
s
o
u
th
war
d
,
o
n
e
co
m
es
ac
r
o
s
s
T
ata
an
d
T
izn
it
Pro
v
in
ce
,
an
d
to
war
d
s
th
e
west
ar
e
th
e
P
r
o
v
in
c
e
o
f
C
h
to
u
k
a
Ait Bah
a
an
d
I
n
ze
g
a
n
e
Ait M
ello
l.
Fig
u
r
e
1
.
L
o
ca
tio
n
o
f
T
ar
o
u
d
a
n
n
t
P
r
o
v
in
ce
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Lo
a
d
fo
r
ec
a
s
tin
g
u
s
in
g
fu
z
z
y
lo
g
ic,
a
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
k,
a
n
d
a
d
a
p
tive
…
(
Hich
a
m
S
tito
u
)
7069
E
lectr
icity
d
em
an
d
d
ata
f
o
r
th
e
P
r
o
v
in
ce
o
f
T
ar
o
u
d
an
n
t
a
r
e
u
s
ed
to
b
u
ild
th
e
p
r
ed
ictio
n
m
o
d
el.
T
h
e
2
0
2
2
d
ata
is
s
elec
ted
to
d
em
o
n
s
tr
ate
th
e
ac
cu
r
ac
y
o
f
t
h
e
p
r
o
p
o
s
ed
f
o
r
ec
asti
n
g
m
o
d
els.
T
h
e
h
is
to
r
ical
lo
a
d
d
atab
ase
h
as
b
ee
n
o
b
tain
ed
f
r
o
m
th
e
Natio
n
al
Of
f
ice
o
f
E
lectr
icity
,
b
ased
in
th
e
city
o
f
T
ar
o
u
d
an
t.
T
h
e
m
o
n
th
ly
lo
a
d
d
em
an
d
p
r
o
f
iles
f
o
r
th
e
P
r
o
v
in
ce
o
f
T
ar
o
u
d
an
n
t
o
v
er
th
e
y
ea
r
s
2
0
1
8
-
2
0
2
2
ar
e
s
h
o
w
n
in
Fig
u
r
e
2
(
a)
.
T
h
e
p
lo
t
h
as
b
ee
n
g
en
er
ated
b
ased
o
n
th
e
co
ll
ec
ted
h
is
to
r
ic
d
ata.
T
h
e
wea
t
h
er
d
ata,
in
clu
d
in
g
win
d
s
p
ee
d
an
d
tem
p
er
at
u
r
e,
as
in
p
u
ts
wer
e
co
llected
u
s
in
g
th
e
h
is
to
r
ical
wea
th
er
d
ata
b
ase
o
f
Mo
r
o
cc
o
[
2
0
]
.
T
h
e
v
ar
iatio
n
o
f
th
ese
in
p
u
ts
in
co
r
r
elatio
n
with
th
e
lo
a
d
as o
u
tp
u
t is sh
o
wn
in
Fig
u
r
e
2
(
b
)
.
Du
e
to
wea
th
er
c
h
ar
ac
ter
is
tics
in
T
ar
o
u
d
a
n
t
P
r
o
v
in
ce
,
th
e
co
n
s
u
m
e
d
e
n
er
g
y
v
ar
ies
b
etwe
en
th
e
win
ter
p
er
io
d
an
d
th
e
s
u
m
m
er
p
er
io
d
.
I
t
is
p
o
s
s
ib
le
to
ex
tr
ac
t
ea
ch
o
f
th
e
f
o
llo
win
g
o
b
s
er
v
atio
n
s
f
r
o
m
Fig
u
r
e
2
(
a)
:
th
e
co
n
s
u
m
ed
en
er
g
y
in
cr
ea
s
es
to
its
p
ea
k
s
d
u
r
in
g
s
u
m
m
er
an
d
d
ec
r
ea
s
es
s
ig
n
if
ican
tly
d
u
r
in
g
non
-
s
u
m
m
e
r
.
Fo
r
ea
ch
y
ea
r
,
e
n
er
g
y
co
n
s
u
m
p
tio
n
is
m
in
im
al
in
win
ter
.
T
h
e
r
is
e
an
d
f
all
o
f
th
e
lo
ad
cu
r
v
es a
r
e
n
o
ted
i
n
th
e
au
t
u
m
n
an
d
s
p
r
in
g
s
ea
s
o
n
s
,
r
esp
ec
tiv
el
y
.
E
lectr
icity
co
n
s
u
m
p
tio
n
s
ee
s
a
g
r
ad
u
al
y
ea
r
l
y
in
c
r
ea
s
e,
n
o
tab
ly
b
etwe
en
th
e
m
o
n
th
s
o
f
Ma
y
an
d
Sep
tem
b
er
.
I
n
2
0
2
0
,
a
n
o
tewo
r
th
y
s
u
r
g
e
in
th
e
p
r
o
v
in
ce
’
s
en
er
g
y
co
n
s
u
m
p
tio
n
was
d
etec
ted
,
p
o
s
s
ib
ly
lin
k
ed
to
th
e
p
er
io
d
o
f
lo
ck
d
o
wn
im
p
o
s
ed
in
Mo
r
o
cc
o
d
u
e
to
th
e
co
r
o
n
a
v
ir
u
s
d
is
ea
s
e
2
0
1
9
(
C
OVI
D
-
19
)
p
an
d
e
m
ic.
Ob
s
er
v
atio
n
s
f
r
o
m
Fig
u
r
e
2
(
b
)
lea
d
to
th
e
f
o
llo
win
g
co
n
clu
s
io
n
s
:
d
u
r
in
g
win
ter
,
lo
ad
co
n
s
u
m
p
tio
n
d
ec
r
ea
s
es
with
d
ec
r
ea
s
in
g
tem
p
e
r
atu
r
es.
I
n
s
u
m
m
er
,
a
d
i
r
ec
t
r
elatio
n
s
h
ip
is
ev
id
en
t
b
etwe
en
lo
ad
co
n
s
u
m
p
tio
n
an
d
te
m
p
er
atu
r
e.
Sp
r
in
g
is
ch
ar
ac
ter
ized
b
y
a
tr
an
s
itio
n
f
r
o
m
co
l
d
to
war
m
clim
ates,
with
a
co
r
r
esp
o
n
d
in
g
r
elatio
n
s
h
ip
b
etwe
en
lo
ad
a
n
d
tem
p
er
atu
r
e
d
u
r
in
g
th
e
win
ter
-
s
u
m
m
er
tr
an
s
itio
n
.
I
n
au
tu
m
n
,
t
h
e
lo
ad
c
o
n
s
u
m
p
tio
n
p
atter
n
s
r
esem
b
le
th
at
o
f
t
h
e
s
p
r
in
g
m
o
n
th
s
.
E
x
ce
p
t f
o
r
2
0
1
8
,
win
d
s
p
ee
d
a
n
d
tem
p
er
at
u
r
e
cu
r
v
es g
en
e
r
ally
ex
h
ib
it si
m
ilar
ity
.
(
a)
(
b
)
Fig
u
r
e
2
.
Var
iatio
n
o
f
e
n
er
g
y
d
em
an
d
a
n
d
wea
th
er
v
ar
iab
les
in
T
ar
o
u
d
an
t (
a
)
p
r
o
f
ile
o
f
lo
a
d
en
er
g
y
d
em
a
n
d
an
d
(
b
)
in
p
u
ts
v
ar
iatio
n
in
co
r
r
elatio
n
with
th
e
lo
ad
2
.
2
.
M
T
L
F
us
i
ng
f
uzzy
lo
g
ic
Fu
zz
y
lo
g
ic
-
b
ased
lo
ad
f
o
r
e
ca
s
tin
g
m
o
d
els
h
av
e
b
ee
n
u
s
ed
f
o
r
s
h
o
r
t,
m
e
d
iu
m
,
a
n
d
lo
n
g
-
ter
m
f
o
r
ec
asts
,
co
n
s
id
er
in
g
f
ac
to
r
s
s
u
ch
as
m
eteo
r
o
lo
g
ical
p
ar
a
m
eter
s
an
d
en
er
g
y
c
o
n
s
u
m
p
tio
n
p
atter
n
s
[
1
5
]
.
T
h
is
ap
p
r
o
ac
h
h
as
s
h
o
wn
p
r
o
m
is
in
g
r
esu
lts
in
h
an
d
lin
g
th
e
in
h
er
en
t
u
n
ce
r
tain
t
y
in
lo
a
d
f
o
r
ec
asti
n
g
,
esp
ec
ially
wh
en
d
ea
lin
g
with
r
ea
l
-
wo
r
l
d
d
ata
t
h
at
m
ay
n
o
t
ad
h
er
e
to
s
tr
ict
m
ath
em
atica
l
r
elatio
n
s
h
ip
s
[
2
1
]
.
T
h
e
ar
ch
itectu
r
e
o
f
th
e
f
u
zz
y
in
f
er
en
ce
s
y
s
tem
(
FIS)
is
s
h
o
wn
in
Fig
u
r
e
3
.
Fig
u
r
e
3
.
Fu
zz
y
in
f
er
e
n
ce
s
y
s
tem
s
tr
u
ctu
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
7
0
6
7
-
7
0
7
9
7070
2
.
2
.
1
.
I
m
plem
ent
a
t
i
o
n o
f
f
uz
zy
lo
g
ic
m
o
del us
ing
f
uzzy
lo
g
ic
des
ig
ner
t
o
o
l
T
o
im
p
lem
e
n
t
th
e
f
u
zz
y
lo
g
ic
m
o
d
el,
th
e
f
u
zz
y
lo
g
ic
d
esig
n
er
to
o
l
is
u
s
ed
in
th
e
MA
T
L
A
B
en
v
ir
o
n
m
en
t,
as
s
h
o
wn
in
Fi
g
u
r
e
4
.
T
h
is
to
o
l
allo
ws
th
e
d
esig
n
an
d
test
in
g
o
f
f
u
zz
y
i
n
f
er
en
ce
s
y
s
tem
s
f
o
r
m
o
d
ellin
g
th
e
s
y
s
tem
b
eh
av
io
r
.
T
h
e
p
r
o
ce
s
s
o
f
lo
ad
f
o
r
ec
ast
in
g
u
s
in
g
th
is
to
o
l c
an
b
e
s
u
m
m
ar
ized
as f
o
llo
ws:
th
e
f
ir
s
t
s
tep
i
s
to
d
esig
n
M
am
d
an
i
f
u
zz
y
in
f
er
en
ce
s
y
s
tem
s
.
I
n
p
u
t
an
d
o
u
tp
u
t
v
ar
ia
b
les
ar
e
th
en
ad
d
ed
.
Me
m
b
er
s
h
ip
f
u
n
ctio
n
s
o
f
all
in
p
u
ts
an
d
o
u
t
p
u
ts
ar
e
th
en
s
p
ec
if
ied
.
Def
in
e
f
u
zz
y
if
-
th
e
n
r
u
les.
Select
f
u
zz
y
in
f
er
en
ce
f
u
n
ctio
n
s
f
o
r
:
a
n
d
o
p
er
atio
n
s
,
o
r
o
p
e
r
atio
n
s
,
im
p
licatio
n
,
a
g
g
r
eg
atio
n
a
n
d
d
e
f
u
zz
if
icatio
n
.
Nex
t,
ad
ju
s
t
in
p
u
t
v
al
u
es
an
d
v
iew
ass
o
ciate
d
f
u
zz
y
in
f
e
r
en
ce
g
r
ap
h
s
.
T
h
e
f
in
al
s
tep
is
to
v
iew
o
u
tp
u
t
s
u
r
f
ac
e
m
ap
s
f
o
r
f
u
zz
y
in
f
er
en
ce
s
y
s
tem
s
.
Fig
u
r
e
4
.
Fu
zz
y
lo
g
ic
m
o
d
el
u
s
in
g
f
u
zz
y
l
o
g
ic
d
esig
n
e
r
to
o
l
T
h
e
FIS
d
esig
n
is
co
n
d
u
cte
d
th
r
o
u
g
h
a
s
eq
u
en
tial
p
r
o
ce
s
s
[
2
2
]
,
wh
ich
i
n
v
o
lv
es
id
e
n
tify
in
g
an
d
f
u
zz
if
y
in
g
in
p
u
ts
an
d
o
u
tp
u
ts
,
estab
li
s
h
in
g
r
u
le
s
tr
en
g
th
,
d
er
iv
in
g
r
u
le
co
n
s
eq
u
e
n
ts
,
in
teg
r
atin
g
r
u
le
co
n
s
eq
u
en
ts
,
a
n
d
a
p
p
ly
in
g
th
e
d
ef
u
zz
if
icatio
n
p
r
o
ce
s
s
.
T
o
s
elec
t
th
e
b
est
m
o
d
el,
a
s
er
ies
o
f
test
s
ar
e
ca
r
r
ied
o
u
t
u
s
in
g
d
if
f
er
e
n
t
d
ef
u
zz
if
ic
atio
n
m
eth
o
d
s
[
1
4
]
.
T
h
e
m
o
d
el
u
s
es
m
o
n
th
ly
av
er
ag
e
tem
p
er
atu
r
e
(
T
)
,
Mo
n
t
h
I
n
d
ex
(
M
I
)
an
d
win
d
s
p
ee
d
(
W
S)
as
in
p
u
ts
an
d
lo
ad
as o
u
t
p
u
t.
I
n
p
u
ts
an
d
o
u
t
p
u
t a
r
e
s
o
r
t
ed
in
to
lo
w,
m
ed
iu
m
,
an
d
h
ig
h
,
an
d
s
er
v
e
as
class
es
o
f
f
u
zz
y
s
ets.
T
o
d
eter
m
in
e
t
h
e
m
em
b
er
s
h
ip
f
u
n
ctio
n
s
(
M
Fs
)
f
o
r
th
e
d
if
f
er
e
n
t
class
es
o
f
th
e
f
u
zz
y
s
ets,
th
e
ex
am
in
atio
n
o
f
th
e
d
ata
co
ll
ec
ted
s
h
o
ws
th
at
in
p
u
ts
an
d
o
u
tp
u
ts
ca
n
b
e
b
est
class
if
ied
ac
co
r
d
in
g
to
t
h
e
d
is
tr
ib
u
tio
n
s
h
o
w
n
in
T
a
b
le
1
.
T
ab
le
1
.
C
lass
es o
f
f
u
zz
y
s
ets
I
n
p
u
t
s
a
n
d
o
u
t
p
u
t
D
i
sco
u
r
se
u
n
i
v
.
C
l
a
s
ses
T
i
n
°
C
1
3
t
o
3
5
LT
:
1
3
t
o
2
4
;
HT
:
2
2
t
o
3
5
a
n
d
LS
:
1
0
t
o
1
9
WS
i
n
K
m
/
h
1
0
t
o
3
4
MS
:
1
8
t
o
2
7
a
n
d
HS
:
2
4
t
o
3
4
M
o
n
t
h
i
n
d
e
x
{1
,
2
,
3
,
…
,
1
2
}
W
I
N
TER
,
S
P
R
I
N
G
,
S
U
M
M
E
R
,
a
n
d
F
A
LL
L
o
a
d
i
n
M
W
h
4
0
t
o
1
0
0
LL
:
4
0
t
o
7
0
;
ML
:
6
5
t
o
8
1
a
n
d
HL
:
7
8
t
o
1
0
0
I
n
th
is
wo
r
k
tr
ian
g
u
lar
MFs
is
s
elec
ted
.
I
n
f
ac
t,
a
f
ter
a
s
er
ies
o
f
test
s
u
s
in
g
th
r
ee
ty
p
es
o
f
m
em
b
er
s
h
ip
f
u
n
ctio
n
s
,
it
was
f
o
u
n
d
th
at
th
e
m
o
d
el
u
s
in
g
t
r
ian
g
u
lar
MFs
h
ad
th
e
h
ig
h
est
lev
el
o
f
ac
cu
r
ac
y
.
Fig
u
r
e
5
s
h
o
ws
th
e
MFs
o
f
in
p
u
ts
an
d
o
u
tp
u
t.
T
h
e
in
p
u
t
T
h
as
two
MF
s
wh
ich
ar
e
lo
w
te
m
p
er
atu
r
e
(
L
T
)
an
d
h
ig
h
tem
p
er
atu
r
e
(
HT
)
in
Fig
u
r
e
5
(
a
)
.
SP
R
I
NG,
W
I
NT
E
R
,
FALL
,
an
d
SUMM
E
R
ar
e
th
e
MFs
o
f
MI
in
Fig
u
r
e
5
(
b
)
.
Hig
h
s
p
ee
d
(
HS)
,
m
ed
iu
m
s
p
ee
d
(
MS)
an
d
lo
w
s
p
ee
d
(
L
S)
ar
e
th
e
th
r
ee
MFs
o
f
th
e
in
p
u
t
W
S
in
Fig
u
r
e
5
(
c)
.
T
h
e
f
o
r
ec
asted
lo
ad
h
as
th
r
ee
MFs
in
Fig
u
r
e
5
(
d
)
.
W
h
er
e
L
L
is
lo
w
lo
ad
,
ML
is
m
ed
iu
m
lo
ad
an
d
HL
is
h
ig
h
lo
a
d
.
A
c
o
llectio
n
o
f
f
u
zz
y
r
u
les
th
at
estab
lis
h
co
n
n
ec
tio
n
s
b
etwe
en
th
e
in
p
u
t
v
a
r
iab
les
an
d
th
e
o
u
tp
u
t v
ar
iab
le
is
g
e
n
er
ate
d
,
as d
ep
icted
b
y
th
e
r
u
le
ed
ito
r
d
is
p
lay
ed
in
Fig
u
r
e
6
2
.
3
.
ANN
a
pp
ro
a
ch
f
o
r
M
T
L
F
T
h
e
p
r
o
ce
s
s
o
f
c
o
n
d
u
ctin
g
lo
a
d
f
o
r
ec
asti
n
g
u
s
in
g
th
e
ANN
tech
n
iq
u
e
ca
n
b
e
s
u
m
m
a
r
ized
as
f
o
llo
ws
[
2
3
]
–
[
2
6
]
:
th
e
f
ir
s
t
s
tep
i
s
d
a
ta
co
llectio
n
an
d
p
r
e
-
p
r
o
ce
s
s
in
g
.
T
h
is
in
clu
d
es
r
etr
iev
in
g
h
is
to
r
ical
lo
ad
d
ata
with
tim
estam
p
s
an
d
n
o
r
m
al
izin
g
to
im
p
r
o
v
e
tr
ain
in
g
p
e
r
f
o
r
m
a
n
ce
.
T
h
e
d
ataset
is
th
en
p
ar
titi
o
n
e
d
in
to
tr
ain
in
g
,
v
alid
atio
n
,
an
d
test
s
ets.
T
h
e
ANN
ar
ch
itectu
r
e
is
th
en
s
elec
ted
,
in
p
u
t
lay
er
s
an
d
h
id
d
en
lay
er
s
ar
e
d
ef
in
ed
,
an
d
a
n
a
p
p
r
o
p
r
iate
r
eg
r
ess
io
n
lo
s
s
f
u
n
ctio
n
is
u
s
ed
.
T
h
e
m
o
d
el
is
tr
ain
e
d
u
s
in
g
o
p
tim
izatio
n
alg
o
r
ith
m
s
,
with
c
o
n
tin
u
o
u
s
m
o
n
ito
r
in
g
o
n
th
e
v
alid
atio
n
s
et
to
av
o
id
o
v
e
r
f
itti
n
g
.
T
h
is
is
f
o
llo
wed
b
y
ev
alu
atio
n
o
n
th
e
test
d
ataset
to
ass
ess
p
r
ed
ictio
n
ac
cu
r
ac
y
.
On
ce
s
atis
f
ac
to
r
y
p
er
f
o
r
m
a
n
ce
is
ac
h
iev
ed
,
th
e
m
o
d
el
is
d
ep
lo
y
ed
f
o
r
lo
ad
f
o
r
ec
asti
n
g
in
a
p
r
o
d
u
ctio
n
en
v
ir
o
n
m
en
t.
C
o
n
tin
u
o
u
s
m
o
n
ito
r
in
g
co
n
tin
u
es,
allo
win
g
u
p
d
ates
b
ased
o
n
n
e
w
d
ata
o
r
ch
a
n
g
es
in
lo
ad
p
at
ter
n
s
.
Fig
u
r
e
7
s
h
o
ws
th
e
f
lo
wch
ar
t
f
o
r
th
e
ANN
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Lo
a
d
fo
r
ec
a
s
tin
g
u
s
in
g
fu
z
z
y
lo
g
ic,
a
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
k,
a
n
d
a
d
a
p
tive
…
(
Hich
a
m
S
tito
u
)
7071
m
o
d
el
[
2
7
]
.
T
h
e
p
r
im
ar
y
o
b
je
ctiv
e
o
f
th
e
lea
r
n
in
g
alg
o
r
ith
m
(
L
A)
is
t
o
m
o
d
if
y
th
e
co
n
n
ec
t
io
n
weig
h
ts
with
in
th
e
n
etwo
r
k
t
o
attain
th
e
in
te
n
d
ed
o
u
tc
o
m
e.
Fig
u
r
e
5
.
Me
m
b
er
s
h
ip
f
u
n
ctio
n
s
u
s
ed
in
FL
m
o
d
el
(
a)
MFs
o
f
in
p
u
t T
(
b
)
MFs o
f
in
p
u
t WS
(
c)
MFs o
f
in
p
u
t
MI
an
d
(
d
)
MFs o
f
o
u
tp
u
t l
o
ad
Fig
u
r
e
6
.
So
m
e
f
u
zz
y
r
u
les u
s
ed
to
b
u
ild
FL
m
o
d
el
Fig
u
r
e
7
.
Flo
wch
ar
t
o
f
ANN
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
7
0
6
7
-
7
0
7
9
7072
2
.
3
.
1
.
I
m
plem
ent
a
t
i
o
n o
f
AN
N
us
ing
M
AT
L
A
B
T
o
im
p
lem
en
t
ANN
m
o
d
el
t
h
e
co
llected
d
ata
p
lo
tted
in
Fig
u
r
e
2
an
d
s
av
ed
in
an
E
x
ce
l
s
p
r
ea
d
s
h
ee
t
ar
e
u
s
ed
.
Fig
u
r
e
8
s
h
o
ws
th
e
o
p
en
to
o
l
u
s
ed
to
g
e
n
er
ate
A
NN
m
o
d
el.
Dif
f
er
en
t
c
h
ar
ac
te
r
is
tics
o
f
p
ar
am
eter
s
ar
e
u
s
ed
to
ac
h
iev
e
th
e
b
est
ar
ch
itectu
r
e
with
th
e
f
ewe
s
t
er
r
o
r
s
,
s
u
ch
as
h
id
d
en
lay
er
s
ize,
an
d
tr
ain
in
g
alg
o
r
ith
m
.
h
as
b
ee
n
e
x
am
in
ed
.
T
h
e
ar
ch
itectu
r
e
o
f
ANN
co
n
s
is
ts
o
f
th
r
ee
i
n
p
u
ts
an
d
o
n
e
o
u
tp
u
t,
o
r
g
an
ized
in
th
r
ee
d
is
tin
ct
lay
er
s
:
th
e
i
n
p
u
t
lay
er
,
a
h
id
d
e
n
lay
e
r
with
5
n
eu
r
o
n
s
,
an
d
th
e
o
u
tp
u
t
lay
er
.
T
h
e
tr
ain
i
n
g
s
tag
e
em
p
lo
y
ed
th
e
L
e
v
en
b
e
r
g
-
Ma
r
q
u
ar
d
t
al
g
o
r
ith
m
(
L
MA
)
.
T
h
e
d
ataset
was
p
ar
titi
o
n
ed
i
n
to
t
h
r
ee
s
ep
ar
ate
s
ets,
with
7
0
%
ass
ig
n
ed
to
tr
ain
in
g
d
ata,
1
5
%
to
v
alid
atio
n
d
at
a,
an
d
an
o
t
h
er
1
5
%
to
test
d
ata
as
also
s
h
o
wn
in
Fig
u
r
e
8
.
Fig
u
r
e
8
.
ANN
o
p
en
to
o
l in
M
AT
L
AB
en
v
ir
o
n
m
en
t
2
.
4
.
ANF
I
S t
ec
hn
iqu
e
f
o
r
M
T
L
F
2
.
4
.
1
.
ANF
I
S a
rc
hite
ct
ure
T
h
e
ANFI
S
wa
s
in
tr
o
d
u
ce
d
in
[
2
8
]
.
ANFI
S
is
a
h
y
b
r
id
in
tellig
en
t
m
o
d
el,
it
co
m
b
in
es
th
e
s
tr
en
g
th
s
o
f
ANNs,
an
d
f
u
zz
y
lo
g
ic
s
y
s
tem
.
I
t
is
a
p
o
wer
f
u
l
to
o
l
f
o
r
m
o
d
elin
g
c
o
m
p
lex
n
o
n
lin
ea
r
s
y
s
tem
s
,
r
ain
f
all
p
r
ed
ictin
g
[
2
9
]
.
Pre
d
ictin
g
th
e
o
u
tp
u
t
p
o
wer
o
f
a
p
h
o
to
v
o
ltaic
s
y
s
tem
[
3
0
]
.
T
h
e
esti
m
atio
n
o
f
L
i
-
I
o
n
b
atter
y
s
tate
o
f
ch
ar
g
e
f
o
r
h
y
b
r
id
v
e
h
icle
[
3
1
]
,
an
d
l
o
ad
f
o
r
ec
asti
n
g
.
Fig
u
r
e
9
s
h
o
ws
th
e
ANFI
S
ar
c
h
itectu
r
e
with
two
in
p
u
ts
,
1
an
d
2
,
an
d
s
in
g
le
o
u
t
p
u
t
,
̂
.
T
h
e
f
u
zz
y
r
u
les f
o
r
t
h
e
co
n
s
i
d
er
ed
ANFI
S m
o
d
el
a
r
e
ex
p
r
e
s
s
ed
as:
−
R
u
le
I
: if
1
is
1
an
d
2
is
1
th
en
:
1
=
1
1
+
1
2
+
1
−
R
u
le
I
I
: if
1
is
2
an
d
2
is
2
th
en
:
2
=
2
1
+
2
2
+
2
w
h
er
e
an
d
r
ep
r
esen
t
th
e
lin
g
u
is
tic
v
alu
es
d
ef
in
ed
b
y
th
e
f
u
zz
y
s
ets,
an
d
,
,
an
d
ar
e
k
n
o
wn
as
co
n
s
eq
u
en
t
p
ar
am
eter
s
.
T
h
e
la
y
er
s
in
ANFI
S
ca
n
b
e
b
r
o
ad
ly
ca
teg
o
r
ized
in
to
f
iv
e
m
ain
ty
p
es,
ea
ch
s
er
v
in
g
a
s
p
ec
if
ic
p
u
r
p
o
s
e
in
th
e
o
v
er
all
s
y
s
tem
[
3
2
]
.
Fig
u
r
e
9
.
Simp
le
ANFI
S
ar
ch
i
tectu
r
e
with
2
in
p
u
ts
an
d
o
n
e
o
u
tp
u
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Lo
a
d
fo
r
ec
a
s
tin
g
u
s
in
g
fu
z
z
y
lo
g
ic,
a
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
k,
a
n
d
a
d
a
p
tive
…
(
Hich
a
m
S
tito
u
)
7073
−
L
ay
er
1
(
Fu
zz
if
icatio
n
lay
er
)
:
On
ce
th
e
in
p
u
t
d
ata
is
r
ec
ei
v
ed
,
it
n
ee
d
s
to
b
e
c
o
n
v
er
te
d
in
to
lin
g
u
is
tic
ter
m
s
to
en
ab
le
f
u
zz
y
in
f
e
r
en
ce
.
T
h
e
f
u
zz
if
icatio
n
lay
er
a
p
p
lies
m
em
b
er
s
h
ip
f
u
n
ctio
n
s
to
th
e
in
p
u
t
d
ata,
tr
an
s
f
o
r
m
in
g
cr
is
p
n
u
m
er
ical
v
alu
es in
to
f
u
zz
y
lin
g
u
is
tic
ter
m
s
.
1
,
=
(
1
)
=
1
,
2
(
1
.
a)
1
,
=
−
2
(
2
)
=
3
,
4
(
1
.
b
)
wh
er
e
an
d
ar
e
th
e
m
em
b
er
s
h
ip
g
r
ad
e
o
f
th
e
in
p
u
ts
1
an
d
2
in
th
e
an
d
f
u
zz
y
s
ets,
r
esp
ec
tiv
ely
.
T
h
e
r
e
ar
e
s
ev
e
r
a
l
s
u
itab
le
p
ar
am
eter
ized
m
em
b
er
s
h
ip
f
u
n
ctio
n
s
th
at
ca
n
b
e
u
s
ed
,
s
u
ch
as
th
e
g
au
s
s
ian
MF
(
g
a
u
s
s
mf
)
,
g
en
er
alize
d
b
ell
MF
(
g
b
ellmf
)
,
tr
ian
g
u
lar
MF
(
tr
imf
)
[
3
3
]
.
−
L
ay
er
2
(
R
u
le
ev
alu
atio
n
eq
u
atio
n
s
)
:
T
h
is
lay
er
in
a
f
u
zz
y
lo
g
ic
s
y
s
tem
ca
lcu
lates
th
e
f
ir
in
g
s
tr
en
g
th
o
f
th
e
r
u
les
b
ased
o
n
th
e
co
m
b
i
n
ed
ef
f
ec
t
o
f
a
n
tece
d
en
t
m
e
m
b
er
s
h
ip
g
r
ad
es.
T
h
is
is
ca
lc
u
lated
u
s
in
g
th
e
p
r
o
d
u
ct
o
p
e
r
ato
r
:
2
,
=
=
(
1
)
∗
(
2
)
=
1
,
2
(
2
)
wh
er
e
is
th
e
f
ir
in
g
s
tr
en
g
th
o
f
r
u
le
i
.
−
L
ay
er
3
(
No
r
m
aliza
tio
n
eq
u
at
io
n
s
)
:
T
h
is
lay
er
n
o
r
m
alize
s
th
e
f
ir
in
g
s
tr
en
g
th
s
o
f
all
r
u
le
s
to
en
s
u
r
e
th
at
th
ey
s
u
m
u
p
to
1
.
T
h
is
is
ac
h
ie
v
ed
b
y
th
e
g
i
v
en
(
3
)
:
3
,
=
̅
=
1
+
2
(
3
)
wh
er
e
̅
is
th
e
n
o
r
m
alize
d
f
ir
in
g
s
tr
en
g
th
o
f
r
u
le
i
.
−
L
ay
er
4
(
Def
u
zz
if
icatio
n
eq
u
atio
n
s
)
:
T
h
e
n
o
d
es
o
f
t
h
is
lay
er
ar
e
an
ad
ap
tiv
e
n
o
d
e
with
n
o
d
e
f
u
n
ctio
n
s
g
iv
en
b
y
(
4
)
:
4
,
=
̅
.
=
̅
.
(
1
+
2
+
)
=
1
,
2
(
4
)
wh
er
e
an
d
,
,
an
d
ar
e
th
e
co
n
s
eq
u
en
t p
a
r
am
eter
s
.
−
L
ay
er
5
(
Ag
g
r
e
g
atio
n
eq
u
ati
o
n
)
:
T
h
is
lay
er
ag
g
r
eg
ates
th
e
o
u
tp
u
ts
o
f
all
r
u
les
to
o
b
tain
th
e
f
in
al
f
o
r
ec
asted
lo
ad
v
alu
e:
5
=
̂
=
∑
̅
.
=
∑
∑
=
1
,
2
(
5
)
wh
er
e
̂
is
th
e
d
ef
u
zz
if
ied
o
u
tp
u
t.
I
n
ad
d
itio
n
to
t
h
ese
f
iv
e
m
ai
n
lay
er
s
,
ANFI
S
also
in
co
r
p
o
r
ates
a
lear
n
in
g
alg
o
r
ith
m
,
s
u
ch
as
t
h
e
b
ac
k
p
r
o
p
ag
atio
n
o
r
th
e
h
y
b
r
id
alg
o
r
ith
m
,
to
ad
ap
t
its
p
ar
a
m
eter
s
in
tr
ain
in
g
p
h
ase.
I
n
t
h
e
h
y
b
r
id
al
g
o
r
ith
m
,
th
e
p
ar
am
eter
s
ar
e
u
p
d
ate
d
u
s
i
n
g
two
d
if
f
er
en
t m
eth
o
d
s
[
3
4
]
,
p
r
em
is
e
p
ar
a
m
eter
s
an
d
c
o
n
s
eq
u
en
t
p
a
r
am
eter
s
.
T
h
e
p
r
em
is
e
p
ar
a
m
eter
s
,
,
an
d
,
ar
e
o
p
tim
ized
u
s
in
g
a
g
r
ad
ien
t
d
escen
t
alg
o
r
ith
m
.
W
h
er
e
th
e
co
n
s
eq
u
en
t
p
a
r
am
eter
s
,
,
an
d
wh
ich
r
ep
r
esen
t
th
e
m
o
d
el'
s
o
u
tp
u
t,
ar
e
u
p
d
ate
d
u
s
in
g
a
l
ea
s
t
-
s
q
u
ar
es
alg
o
r
ith
m
.
2
.
4
.
2
.
T
he
pro
po
s
ed
ANF
I
S
m
o
del
T
o
im
p
lem
en
t
th
e
ANFI
S
m
et
h
o
d
,
n
e
u
r
o
-
f
u
zz
y
d
esig
n
e
r
o
f
MA
T
L
AB
en
v
ir
o
n
m
en
t is u
s
e
d
as sh
o
wn
in
Fig
u
r
e
1
0
.
Fig
u
r
e
1
1
p
r
esen
ts
th
e
f
lo
wch
a
r
t
o
f
ANFI
S
m
o
d
el
[
2
7
]
.
T
h
e
p
er
f
o
r
m
a
n
ce
s
o
f
th
e
ANFI
S
m
o
d
el
ar
e
also
co
m
p
ar
e
d
with
th
e
f
u
zz
y
lo
g
ic
a
n
d
ANN
m
o
d
el
u
s
in
g
th
e
s
am
e
d
ataset.
ANFI
S
m
o
d
el
tak
es
th
e
m
o
n
th
ly
av
er
ag
e
tem
p
er
at
u
r
e
(
T
)
,
m
o
n
th
i
n
d
ex
(
MI
)
,
an
d
w
in
d
s
p
ee
d
(
W
S)
as
in
p
u
ts
,
p
r
o
d
u
cin
g
th
e
m
o
n
th
ly
lo
ad
as o
u
tp
u
t.
T
h
e
d
ata
f
o
r
2
0
1
8
to
2
0
2
1
ar
e
s
elec
ted
f
o
r
tr
ai
n
in
g
,
a
n
d
th
e
d
ata
f
o
r
2
0
2
2
ar
e
u
s
ed
f
o
r
test
in
g
.
T
o
ac
h
iev
e
th
e
b
est
ar
ch
itectu
r
e
with
th
e
f
ewe
s
t
er
r
o
r
s
,
v
a
r
i
o
u
s
p
ar
am
eter
s
,
s
u
ch
as
MFs
ty
p
es,
th
e
n
u
m
b
er
o
f
MFs,
an
d
tr
ain
in
g
m
eth
o
d
s
,
h
a
v
e
b
ee
n
in
v
esti
g
at
ed
.
T
h
e
b
est
o
b
tain
ed
f
ea
tu
r
e
o
f
ANFI
S
af
ter
th
e
tu
n
in
g
p
r
o
ce
s
s
is
d
escr
ib
ed
as f
o
llo
ws:
th
e
ty
p
e
o
f
MFs
is
tr
a
p
ez
o
id
al,
n
u
m
b
e
r
o
f
MFs
is
4
,
2
,
an
d
3
f
o
r
MI
,
T
an
d
W
S
r
esp
ec
tiv
ely
an
d
n
u
m
b
er
o
f
ep
o
ch
s
is
5
0
0
.
Fig
u
r
e
1
2
p
r
esen
ts
th
e
s
tr
u
ctu
r
e
o
f
m
o
n
th
ly
m
o
d
el
wh
ich
co
n
s
is
ts
o
f
s
ix
lay
er
s
,
L
1
to
L
6
.
L
1
s
h
o
ws
th
e
m
o
d
el
i
n
p
u
ts
.
L
2
r
ep
r
esen
ts
th
e
in
p
u
t
MF
wh
ich
ar
e
T
r
ap
ez
o
id
al.
L
3
is
r
u
les
an
d
L
4
is
th
e
o
u
tp
u
t
MFs.
L
5
r
ep
r
esen
ts
th
e
o
u
tp
u
t
as
th
e
r
esu
lt
o
f
a
weig
h
ted
s
u
m
an
d
L
6
is
o
u
tp
u
t
o
f
ANFI
S m
o
d
el.
T
h
e
g
e
n
er
ated
r
u
les f
o
r
ANFI
S m
o
d
el
ar
e
g
iv
e
n
in
Fig
u
r
e
1
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
7
0
6
7
-
7
0
7
9
7074
Fig
u
r
e
1
0
.
Data
p
r
ep
a
r
atio
n
an
d
m
o
d
el
p
ar
am
eter
izatio
n
in
n
eu
r
o
f
u
zz
y
d
esig
n
er
Fig
u
r
e
1
1
.
Flo
wch
ar
t o
f
ANFI
S
Fig
u
r
e
1
2
.
Fra
m
ewo
r
k
o
f
AN
FIS
Fig
u
r
e
1
3
.
R
u
les v
iewe
r
o
f
th
e
p
r
o
p
o
s
ed
ANFI
S
m
o
d
el
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
E
v
a
lua
t
io
n m
et
rics
I
n
th
e
liter
atu
r
e,
v
a
r
io
u
s
s
tatis
tical
m
eth
o
d
s
ar
e
em
p
l
o
y
ed
to
ca
lc
u
late
f
o
r
ec
asti
n
g
e
r
r
o
r
s
.
I
n
th
is
wo
r
k
,
ab
s
o
lu
te
p
er
ce
n
ta
g
e
er
r
o
r
(
APE)
,
m
ea
n
ab
s
o
l
u
te
p
e
r
ce
n
tag
e
er
r
o
r
(
MA
PE)
,
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
an
d
co
r
r
elatio
n
c
o
ef
f
icien
t
(
R
)
cr
iter
io
n
,
ar
e
s
elec
ted
to
ev
al
u
ate
th
e
ac
cu
r
ac
y
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
els.
APE,
MA
PE,
R
MSE
an
d
R
f
o
r
m
u
las ar
e
g
iv
e
n
b
y
(
6
)
-
(
8
)
.
(
%
)
=
|
(
)
−
(
)
|
(
)
an
d
(
%
)
=
1
∑
(
)
=
=
1
(
6
)
(
%
)
=
√
∑
(
(
)
−
(
)
)
2
=
1
(
7
)
2
=
1
−
(
)
(
)
(
8
)
w
h
er
e
A
Lo
a
d
an
d
F
Lo
a
d
ar
e
r
esp
ec
tiv
ely
th
e
ac
tu
al
an
d
f
o
r
ec
ast
lo
ad
,
an
d
n
is
th
e
n
u
m
b
er
o
f
f
o
r
ec
asts
.
SSR
is
th
e
s
u
m
o
f
s
q
u
ar
ed
d
if
f
er
en
ce
s
b
etwe
en
th
e
o
b
s
er
v
ed
v
alu
es
an
d
th
e
v
alu
es
p
r
ed
icted
b
y
th
e
r
eg
r
ess
io
n
m
o
d
el.
S
S
T
is
th
e
to
tal
s
u
m
o
f
s
q
u
ar
ed
d
if
f
er
en
ce
s
b
etwe
en
th
e
o
b
s
er
v
e
d
v
alu
es a
n
d
th
eir
m
ea
n
.
3
.
2
.
O
bt
a
ined
re
s
ults
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
o
b
t
ain
ed
r
esu
lts
.
T
h
e
f
ir
s
t
s
u
b
s
ec
tio
n
ex
am
in
es
th
e
R
,
MSE
,
an
d
R
MSE
m
etr
ics
to
ev
alu
ate
an
d
co
m
p
ar
e
th
e
ac
c
u
r
ac
y
o
f
th
e
th
r
ee
m
o
d
els.
T
h
e
s
ec
o
n
d
s
u
b
s
ec
tio
n
an
aly
ze
s
APE
a
n
d
MA
PE
v
alu
es,
d
is
cu
s
s
in
g
th
e
tr
ad
e
-
o
f
f
s
b
etwe
en
m
o
d
el
co
m
p
lex
ity
a
n
d
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
f
o
r
ea
ch
ap
p
r
o
ac
h
,
wh
ile
also
h
i
g
h
lig
h
tin
g
th
e
ch
allen
g
es
ass
o
ciate
d
with
ea
ch
m
o
d
el.
T
h
is
an
aly
s
is
aim
s
to
ass
ess
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Lo
a
d
fo
r
ec
a
s
tin
g
u
s
in
g
fu
z
z
y
lo
g
ic,
a
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
k,
a
n
d
a
d
a
p
tive
…
(
Hich
a
m
S
tito
u
)
7075
h
o
w
ef
f
ec
tiv
ely
ea
ch
m
o
d
el
ca
p
tu
r
es
th
e
u
n
d
er
ly
i
n
g
p
atte
r
n
s
an
d
v
ar
iatio
n
s
with
in
th
e
d
ata,
en
ab
lin
g
a
co
m
p
r
eh
e
n
s
iv
e
co
m
p
a
r
is
o
n
o
f
th
eir
p
r
ed
ictiv
e
ca
p
a
b
ilit
ies.
T
h
e
th
ir
d
s
u
b
s
ec
tio
n
h
ig
h
lig
h
ts
th
e
p
r
ac
tical
im
p
licatio
n
s
o
f
th
ese
r
esu
lts
f
o
r
en
er
g
y
m
an
a
g
em
en
t in
s
o
u
th
west M
o
r
o
cc
o
.
3
.
2
.
1
.
R,
M
SE
a
nd
R
M
S
E
v
a
lues
a
na
ly
s
is
Fig
u
r
e
1
4
(
a)
s
h
o
ws
th
e
ev
o
l
u
tio
n
o
f
th
e
co
s
t
f
u
n
ctio
n
(
MSE
)
v
s
ep
o
ch
s
.
I
t
ca
n
b
e
s
ee
n
th
at
th
e
b
est
v
alid
atio
n
p
er
f
o
r
m
an
ce
is
3
3
.
2
5
4
at
ep
o
c
h
3
.
W
h
ile
F
ig
u
r
e
1
4
(
b
)
co
n
s
is
ts
o
f
f
o
u
r
d
if
f
er
en
t
g
r
a
p
h
s
r
ep
r
esen
tin
g
r
eg
r
ess
io
n
p
lo
ts
f
o
r
test
in
g
,
tr
ain
i
n
g
,
a
n
d
v
alid
a
tio
n
.
T
h
e
tr
ain
in
g
p
lo
t
s
h
o
ws
a
g
o
o
d
co
r
r
elatio
n
b
etwe
en
th
e
o
u
tp
u
t
an
d
th
e
t
ar
g
et
with
th
e
R
-
v
al
u
e
o
f
0
.
9
3
2
.
Ad
d
itio
n
ally
,
it
is
o
b
s
er
v
ed
th
at
th
e
test
in
g
r
eg
r
ess
io
n
p
lo
t
y
ield
s
a
n
R
-
v
alu
e
o
f
0
.
9
5
1
,
a
n
d
t
h
e
v
ali
d
atio
n
p
lo
t
ex
h
ib
its
a
h
i
g
h
r
elatio
n
s
h
ip
with
an
R
-
v
alu
e
o
f
0
.
9
4
8
.
T
h
e
R
-
v
alu
e
ac
r
o
s
s
all
an
aly
s
es is
0
.
9
3
5
.
Fro
m
T
ab
le
2
,
th
e
m
in
im
al
an
d
m
ax
im
al
R
-
v
alu
e
o
f
th
e
f
u
zz
y
l
o
g
ic
an
d
ANFI
S
m
o
d
els
ar
e,
r
esp
ec
tiv
ely
,
0
.
8
an
d
0
.
9
2
.
I
n
ter
m
s
o
f
r
o
o
t
m
ea
n
s
q
u
a
r
e
er
r
o
r
(
R
MSE
)
,
th
e
ANFI
S
d
em
o
n
s
tr
ates
a
m
in
im
u
m
o
f
4
.
3
2
,
wh
ile
th
e
FL
m
o
d
el
e
x
h
ib
its
a
m
ax
im
u
m
v
al
u
e
o
f
6
.
8
6
.
All
th
ese
a
n
aly
s
es
in
d
icate
a
h
ig
h
er
ac
cu
r
ac
y
o
f
th
e
ANFI
S in
lo
ad
p
r
ed
ictio
n
co
m
p
a
r
ed
to
t
h
e
o
th
e
r
two
m
o
d
els.
(
a)
(
b
)
Fig
u
r
e
14
.
Per
f
o
r
m
a
n
ce
s
o
f
A
NN
m
o
d
el
(
a)
ANN
p
e
r
f
o
r
m
a
n
ce
p
lo
t a
n
d
(
b
)
ANN
r
eg
r
ess
io
n
p
lo
t
T
ab
le
2
.
R
,
R
MSE
an
d
MA
PE
v
alu
es o
f
FL,
ANN
,
an
d
ANFI
S f
o
r
2
0
2
2
R
e
g
r
e
ssi
o
n
R
M
S
E
M
A
P
E
F
u
z
z
y
l
o
g
i
c
0
.
8
0
6
.
8
6
8
.
4
2
ANN
0
.
8
7
6
.
7
7
7
.
3
6
A
N
F
I
S
0
.
9
2
4
.
3
2
4
.
7
5
3
.
2
.
2
.
AP
E
a
nd
M
AP
E
v
a
lue
s
a
na
ly
s
is
Fig
u
r
e
1
5
(
a)
s
h
o
ws
th
e
m
o
n
t
h
ly
ac
tu
al
an
d
esti
m
ated
lo
ad
p
atter
n
f
o
r
y
ea
r
2
0
2
2
u
s
in
g
FL
m
o
d
el.
Fig
u
r
e
1
5
(
b
)
p
r
esen
ts
th
e
m
o
n
th
ly
ac
tu
al
an
d
p
r
e
d
icted
lo
ad
p
r
o
f
ile
f
o
r
y
ea
r
2
0
2
2
u
s
in
g
ANN
tech
n
iq
u
e
.
Fig
u
r
e
1
6
illu
s
tr
ates
th
e
m
o
n
th
ly
ac
tu
al
an
d
f
o
r
ec
asted
lo
ad
p
atter
n
f
o
r
y
ea
r
2
0
2
2
u
s
in
g
A
NFI
S
ap
p
r
o
ac
h
.
As
th
ese
f
ig
u
r
es
s
h
o
w,
th
e
p
r
o
f
il
es
o
f
ac
tu
al
an
d
p
r
ed
icted
l
o
ad
cu
r
v
es
ar
e
s
im
ilar
.
I
n
ad
d
itio
n
,
co
m
p
ar
ed
to
f
u
zz
y
lo
g
ic
an
d
ANN
m
o
d
els,
th
e
ANFI
S m
o
d
el
h
as v
er
y
lo
w
er
r
o
r
lev
el
a
n
d
p
r
o
d
u
ce
s
m
o
r
e
ac
cu
r
ate
r
esu
lts
.
T
h
e
APE
an
d
MA
PE
ar
e
ca
lcu
lated
u
s
in
g
(
6
)
.
Fro
m
Fig
u
r
e
1
5
an
d
1
6
th
ese
o
b
s
er
v
atio
n
s
ca
n
b
e
ex
tr
ac
ted
:
th
e
m
a
x
im
u
m
v
alu
e
o
f
th
e
APE
as
2
1
.
3
8
%
is
r
ec
o
r
d
ed
in
Dec
em
b
er
b
y
th
e
f
u
zz
y
lo
g
ic
m
o
d
el.
T
h
e
m
in
im
u
m
d
e
v
iatio
n
f
o
r
th
e
th
r
ee
m
o
d
els
is
o
b
s
er
v
ed
d
u
r
in
g
th
e
s
u
m
m
er
.
Fr
o
m
th
e
co
m
p
ar
is
o
n
o
f
t
h
e
2
0
2
2
r
esu
lts
f
o
r
FL,
ANN
an
d
AN
FIS
p
r
esen
ted
in
T
ab
le
2
,
th
e
MA
PE
v
alu
es
f
o
r
th
e
ANFI
S
m
eth
o
d
ar
e
b
etter
th
an
th
o
s
e
f
o
r
FL
an
d
ANN.
T
h
ese
v
alu
es f
o
r
t
h
e
FL
an
d
AN
N
m
o
d
els ar
e
ap
p
r
o
x
im
ately
th
e
s
am
e.
T
h
e
ch
o
ice
b
etwe
en
th
ese
ap
p
r
o
ac
h
es
d
ep
e
n
d
s
o
n
th
e
s
p
ec
if
i
c
ch
ar
ac
ter
is
tics
o
f
th
e
p
r
o
b
le
m
at
h
an
d
,
in
clu
d
in
g
t
h
e
av
ailab
le
d
ata,
th
e
d
esire
d
lev
el
o
f
in
ter
p
r
etab
ilit
y
,
an
d
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
.
Fin
d
in
g
th
e
r
ig
h
t
b
alan
ce
b
etwe
en
m
o
d
el
co
m
p
lex
ity
a
n
d
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
is
cr
u
cial
f
o
r
d
ev
el
o
p
in
g
ef
f
ec
tiv
e
an
d
r
eliab
le
p
r
e
d
ictiv
e
m
o
d
els.
T
a
b
le
3
d
is
cu
s
s
th
e
tr
a
d
e
-
o
f
f
b
et
wee
n
m
o
d
el
co
m
p
lex
ity
an
d
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
f
o
r
ea
ch
ap
p
r
o
ac
h
,
h
ig
h
lig
h
tin
g
s
o
m
e
ch
allen
g
es a
s
s
o
ciate
d
with
th
e
ch
o
s
en
m
o
d
el.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
7
0
6
7
-
7
0
7
9
7076
(
a)
(
b
)
Fig
u
r
e
1
5
.
C
o
m
p
ar
is
o
n
o
f
m
o
n
th
ly
ac
tu
al
an
d
p
r
e
d
icted
lo
a
d
p
r
o
f
iles
f
o
r
2
0
2
2
(
a)
m
o
n
th
l
y
ac
tu
al
v
s
esti
m
ated
lo
ad
p
atter
n
s
u
s
in
g
FL
m
o
d
el
an
d
(
b
)
m
o
n
t
h
ly
ac
t
u
al
v
s
esti
m
ated
lo
ad
p
r
o
f
iles
u
s
in
g
ANN
m
o
d
el
Fig
u
r
e
1
6
.
Mo
n
th
ly
ac
tu
al
an
d
esti
m
ated
lo
ad
p
atter
n
f
o
r
2
0
2
2
u
s
in
g
ANFI
S m
o
d
el
T
ab
le
3
.
T
h
e
tr
ad
e
-
o
f
f
b
etwe
en
m
o
d
el
c
o
m
p
lex
ity
an
d
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
with
s
o
m
e
lim
itatio
n
s
ass
o
ciate
d
with
th
e
p
r
o
p
o
s
ed
m
o
d
el
A
p
p
r
o
a
c
h
C
o
m
p
l
e
x
i
t
y
A
c
c
u
r
a
c
y
C
h
a
l
l
e
n
g
e
s a
n
d
l
i
m
i
t
a
t
i
o
n
s
F
u
z
z
y
l
o
g
i
c
Te
n
d
s
t
o
h
a
v
e
r
e
l
a
t
i
v
e
l
y
si
mp
l
e
st
r
u
c
t
u
r
e
s,
c
o
n
s
i
st
i
n
g
o
f
f
u
z
z
y
set
s,
mem
b
e
r
s
h
i
p
f
u
n
c
t
i
o
n
s
,
a
n
d
a
se
t
o
f
r
u
l
e
s
.
I
t
i
s
i
n
t
u
i
t
i
v
e
t
o
u
n
d
e
r
st
a
n
d
a
n
d
i
n
t
e
r
p
r
e
t
.
C
a
n
h
a
n
d
l
e
v
a
g
u
e
a
n
d
i
m
p
r
e
c
i
s
e
i
n
p
u
t
d
a
t
a
w
e
l
l
,
m
a
k
i
n
g
i
t
s
u
i
t
a
b
l
e
f
o
r
p
r
o
b
l
e
ms w
h
e
r
e
p
r
e
c
i
s
e
m
a
t
h
e
m
a
t
i
c
a
l
r
e
l
a
t
i
o
n
s
h
i
p
s
a
r
e
d
i
f
f
i
c
u
l
t
t
o
d
e
f
i
n
e
.
H
o
w
e
v
e
r
,
i
t
s
f
o
r
e
c
a
s
t
i
n
g
a
c
c
u
r
a
c
y
m
a
y
b
e
l
i
m
i
t
e
d
i
n
c
o
mp
l
e
x
a
n
d
h
i
g
h
l
y
n
o
n
l
i
n
e
a
r
sy
s
t
e
ms
d
u
e
t
o
i
t
s
si
m
p
l
i
c
i
t
y
.
Li
mi
t
e
d
a
b
i
l
i
t
y
t
o
c
a
p
t
u
r
e
c
o
m
p
l
e
x
n
o
n
l
i
n
e
a
r
r
e
l
a
t
i
o
n
sh
i
p
s,
sen
s
i
t
i
v
i
t
y
t
o
t
h
e
c
h
o
i
c
e
o
f
memb
e
r
sh
i
p
f
u
n
c
t
i
o
n
s a
n
d
r
u
l
e
s
,
a
n
d
d
i
f
f
i
c
u
l
t
i
e
s
i
n
s
c
a
l
i
n
g
t
o
l
a
r
g
e
d
a
t
a
se
t
s.
ANN
C
a
n
v
a
r
y
si
g
n
i
f
i
c
a
n
t
l
y
i
n
c
o
m
p
l
e
x
i
t
y
,
d
e
p
e
n
d
i
n
g
o
n
t
h
e
n
u
m
b
e
r
o
f
l
a
y
e
r
s
,
n
e
u
r
o
n
s,
a
n
d
c
o
n
n
e
c
t
i
o
n
s.
C
a
n
c
a
p
t
u
r
e
h
i
g
h
l
y
c
o
m
p
l
e
x
r
e
l
a
t
i
o
n
s
h
i
p
s
i
n
d
a
t
a
b
u
t
ma
y
s
u
f
f
e
r
f
r
o
m
o
v
e
r
f
i
t
t
i
n
g
i
f
n
o
t
p
r
o
p
e
r
l
y
r
e
g
u
l
a
r
i
z
e
d
.
A
N
N
e
x
c
e
l
s
i
n
c
a
p
t
u
r
i
n
g
n
o
n
l
i
n
e
a
r
r
e
l
a
t
i
o
n
s
h
i
p
s
a
n
d
c
a
n
a
c
h
i
e
v
e
h
i
g
h
f
o
r
e
c
a
st
i
n
g
a
c
c
u
r
a
c
y
,
e
s
p
e
c
i
a
l
l
y
i
n
h
i
g
h
-
d
i
m
e
n
s
i
o
n
a
l
a
n
d
c
o
mp
l
e
x
d
a
t
a
s
e
t
s
.
H
o
w
e
v
e
r
,
t
h
e
y
ma
y
r
e
q
u
i
r
e
l
a
r
g
e
a
mo
u
n
t
s
o
f
d
a
t
a
f
o
r
t
r
a
i
n
i
n
g
a
n
d
c
a
n
b
e
c
h
a
l
l
e
n
g
i
n
g
t
o
i
n
t
e
r
p
r
e
t
d
u
e
t
o
t
h
e
i
r
b
l
a
c
k
-
b
o
x
n
a
t
u
r
e
.
S
u
sce
p
t
i
b
i
l
i
t
y
t
o
o
v
e
r
f
i
t
t
i
n
g
,
d
e
p
e
n
d
e
n
c
e
o
n
l
a
r
g
e
a
m
o
u
n
t
s
o
f
d
a
t
a
f
o
r
t
r
a
i
n
i
n
g
,
b
l
a
c
k
-
b
o
x
n
a
t
u
r
e
l
e
a
d
i
n
g
t
o
r
e
d
u
c
e
d
i
n
t
e
r
p
r
e
t
a
b
i
l
i
t
y
,
a
n
d
c
h
a
l
l
e
n
g
e
s
i
n
sel
e
c
t
i
n
g
o
p
t
i
ma
l
a
r
c
h
i
t
e
c
t
u
r
e
s
a
n
d
h
y
p
e
r
p
a
r
a
me
t
e
r
s
A
N
F
I
S
A
N
F
I
S
c
o
m
b
i
n
e
s
t
h
e
s
i
m
p
l
i
c
i
t
y
o
f
f
u
z
z
y
l
o
g
i
c
w
i
t
h
t
h
e
l
e
a
r
n
i
n
g
c
a
p
a
b
i
l
i
t
i
e
s
o
f
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
r
e
su
l
t
i
n
g
i
n
a
h
y
b
r
i
d
mo
d
e
l
w
i
t
h
m
o
d
e
r
a
t
e
c
o
m
p
l
e
x
i
t
y
.
I
t
c
o
n
si
s
t
s
o
f
f
u
z
z
y
i
n
f
e
r
e
n
c
e
sy
st
e
ms
t
r
a
i
n
e
d
u
s
i
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
t
e
c
h
n
i
q
u
e
s.
I
t
c
a
n
h
a
n
d
l
e
n
o
n
l
i
n
e
a
r
i
t
i
e
s
a
n
d
u
n
c
e
r
t
a
i
n
t
i
e
s
i
n
d
a
t
a
w
h
i
l
e
p
r
o
v
i
d
i
n
g
so
me
l
e
v
e
l
o
f
i
n
t
e
r
p
r
e
t
a
b
i
l
i
t
y
c
o
mp
a
r
e
d
t
o
f
u
l
l
y
b
l
a
c
k
-
b
o
x
n
e
u
r
a
l
n
e
t
w
o
r
k
s.
H
o
w
e
v
e
r
,
t
r
a
i
n
i
n
g
A
N
F
I
S
mo
d
e
l
s
c
a
n
b
e
c
o
mp
u
t
a
t
i
o
n
a
l
l
y
i
n
t
e
n
s
i
v
e
,
a
n
d
sel
e
c
t
i
n
g
t
h
e
a
p
p
r
o
p
r
i
a
t
e
s
t
r
u
c
t
u
r
e
a
n
d
p
a
r
a
m
e
t
e
r
s c
a
n
b
e
c
h
a
l
l
e
n
g
i
n
g
.
C
o
m
p
u
t
a
t
i
o
n
a
l
c
o
m
p
l
e
x
i
t
y
d
u
r
i
n
g
t
r
a
i
n
i
n
g
,
p
o
t
e
n
t
i
a
l
o
v
e
r
f
i
t
t
i
n
g
i
f
n
o
t
p
r
o
p
e
r
l
y
r
e
g
u
l
a
r
i
z
e
d
,
d
i
f
f
i
c
u
l
t
y
i
n
se
l
e
c
t
i
n
g
a
p
p
r
o
p
r
i
a
t
e
f
u
z
z
y
s
e
t
s
a
n
d
r
u
l
e
s,
a
n
d
l
i
m
i
t
a
t
i
o
n
s
i
n
h
a
n
d
l
i
n
g
e
x
t
r
e
mel
y
h
i
g
h
-
d
i
me
n
si
o
n
a
l
d
a
t
a
Evaluation Warning : The document was created with Spire.PDF for Python.