I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
,
p
p
.
2
2
5
6
~2
2
6
3
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v9
i
4
.
p
p
2
2
5
6
-
2263
2256
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
Da
ily
peak lo
a
d f
o
recas
t
using
arti
ficial neura
l
netw
o
rk
Ra
m
e
s
h K
u
m
a
r
V
1
,
P
ra
dip
k
u
m
a
r
D
ix
it
2
1
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
En
g
i
n
e
e
rin
g
,
JA
IN (De
e
m
e
d
-
to
-
be
-
Un
iv
e
rsity
)
,
In
d
ia
2
De
p
a
rt
m
e
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
En
g
i
n
e
e
rin
g
,
M
.
S
.
Ra
m
a
iah
In
stit
u
te
o
f
T
e
c
h
n
o
l
o
g
y
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
5
,
2
0
1
8
R
ev
i
s
ed
Dec
2
7
,
2
0
1
8
A
cc
ep
ted
J
an
1
0
,
2
0
1
9
T
h
e
p
a
p
e
r
p
re
se
n
ts an
A
rti
f
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
(
A
NN
)
m
o
d
e
l
f
o
r
sh
o
rt
-
term
lo
a
d
f
o
re
c
a
stin
g
o
f
d
a
il
y
p
e
a
k
lo
a
d
.
A
m
u
lt
i
-
lay
e
re
d
f
e
e
d
f
o
r
wa
rd
n
e
u
ra
l
n
e
tw
o
rk
w
it
h
L
e
v
e
n
b
e
rg
-
M
a
rq
u
a
rd
t
lea
rn
i
n
g
a
lg
o
rit
h
m
is
u
se
d
b
e
c
a
u
se
o
f
it
s
g
o
o
d
g
e
n
e
ra
li
z
in
g
p
ro
p
e
rty
a
n
d
ro
b
u
stn
e
ss
in
p
re
d
ictio
n
.
T
h
e
in
p
u
t
t
o
th
e
n
e
tw
o
rk
is
in
term
s
o
f
h
isto
rica
l
d
a
il
y
p
e
a
k
lo
a
d
d
a
ta
a
n
d
c
o
rre
sp
o
n
d
in
g
d
a
il
y
p
e
a
k
te
m
p
e
ra
tu
re
d
a
ta.
T
h
e
n
e
tw
o
rk
is
train
e
d
to
p
re
d
ict
th
e
l
o
a
d
re
q
u
irem
e
n
t
a
h
e
a
d
.
T
h
e
e
ff
e
c
ti
v
e
n
e
ss
o
f
th
e
p
ro
p
o
se
d
A
NN
a
p
p
ro
a
c
h
to
th
e
sh
o
rt
-
term
lo
a
d
f
o
re
c
a
stin
g
p
r
o
b
lem
s
is
d
e
m
o
n
stra
ted
b
y
p
ra
c
ti
c
a
l
d
a
ta
f
ro
m
th
e
Ba
n
g
a
lo
re
El
e
c
tri
c
it
y
S
u
p
p
ly
Co
m
p
a
n
y
L
i
m
it
e
d
(BES
C
OM).
T
h
e
c
o
m
p
a
riso
n
b
e
tw
e
e
n
th
e
p
ro
p
o
se
d
a
n
d
th
e
c
o
n
v
e
n
ti
o
n
a
l
m
e
th
o
d
s
is
m
a
d
e
in
term
s
o
f
p
e
rc
e
n
tag
e
e
rro
r
a
n
d
it
i
s
f
o
u
n
d
t
h
a
t
t
h
e
p
r
o
p
o
se
d
A
NN
m
o
d
e
l
g
iv
e
s
m
o
re
a
c
c
u
ra
te
p
re
d
ictio
n
s
w
it
h
o
p
ti
m
a
l
n
u
m
b
e
r
o
f
n
e
u
ro
n
s
in
th
e
h
id
d
e
n
lay
e
r.
K
ey
w
o
r
d
s
:
A
r
ti
f
icial
Ne
u
r
al
Net
w
o
r
k
Dail
y
p
ea
k
lo
ad
Fo
r
ec
asti
n
g
L
i
n
ea
r
f
it
P
o
ly
n
o
m
ial
f
it
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
R
a
m
e
s
h
Ku
m
ar
V
,
R
esear
ch
Sch
o
lar
,
J
A
I
N
(
Dee
m
ed
-
to
-
be
-
U
n
i
v
er
s
it
y
)
,
Dep
ar
t
m
en
t o
f
E
lectr
ical
an
d
E
lectr
o
n
ics E
n
g
i
n
ee
r
in
g
,
J
GI
Glo
b
al
C
am
p
u
s
,
B
en
g
alu
r
u
-
5
6
2
1
1
2
,
Kar
n
atak
a
State,
I
n
d
ia.
E
m
ail:
r
a
m
es
h
_
u
v
ce
@
r
ed
i
f
f
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
E
lectr
ical
en
er
g
y
p
la
y
s
a
v
ital
r
o
le
in
d
a
y
to
d
a
y
li
f
e.
I
t
is
r
eq
u
ir
ed
f
o
r
d
o
m
e
s
tic
p
u
r
p
o
s
e,
in
d
u
s
tr
ial
p
u
r
p
o
s
e
an
d
in
m
a
n
y
ar
ea
s
.
E
l
ec
tr
ical
en
er
g
y
i
s
in
g
r
ea
t
d
e
m
an
d
b
y
co
n
s
u
m
er
s
.
A
t
p
r
ese
n
t,
in
I
n
d
ia
ac
co
r
d
in
g
to
C
en
tr
al
E
lectr
icit
y
Au
t
h
o
r
it
y
,
Ne
w
Del
h
i
s
u
r
v
e
y
[
1
]
t
h
e
to
tal
in
s
talled
ca
p
ac
it
y
a
s
o
n
3
1
-
03
-
2
0
1
7
is
3
2
6
.
8
4
8
GW
an
d
h
as
en
er
g
y
s
h
o
r
tag
e
o
f
0
.
7
%
an
d
p
ea
k
s
h
o
r
tag
e
o
f
1
.
6
%
d
u
r
in
g
t
h
e
f
i
n
an
cial
y
ea
r
2
0
1
6
-
1
7
an
d
s
i
m
i
lar
l
y
in
Kar
n
a
tak
a
th
e
to
tal
i
n
s
ta
lled
ca
p
ac
it
y
i
s
2
1
.
3
1
6
GW
an
d
h
as
e
n
er
g
y
s
h
o
r
tag
e
o
f
0
.
5
%
an
d
p
ea
k
s
h
o
r
ta
g
e
o
f
0
.
2
%.
T
h
e
s
h
o
r
tag
e
o
f
p
o
w
er
is
b
ec
au
s
e
o
f
lack
o
f
g
e
n
er
atio
n
d
u
e
to
s
h
o
r
tag
e
o
f
r
eso
u
r
ce
s
,
u
n
s
ch
ed
u
led
m
ai
n
te
n
an
ce
s
,
o
u
tag
e
s
an
d
f
a
u
lt
s
.
T
h
is
d
ef
icit
ca
n
b
e
r
ed
u
ce
d
to
s
o
m
e
e
x
te
n
t
b
y
d
e
m
a
n
d
s
id
e
m
an
a
g
e
m
e
n
t
o
r
b
y
tr
a
n
s
m
it
ti
n
g
p
o
w
er
at
h
i
g
h
v
o
ltag
e
s
wh
ich
r
ed
u
ce
s
tr
an
s
m
i
s
s
io
n
lo
s
s
es,
b
u
t
t
h
e
b
asic
m
ea
n
s
o
f
m
ee
ti
n
g
t
h
e
d
e
m
a
n
d
is
b
y
in
cr
ea
s
in
g
t
h
e
g
en
er
a
tio
n
its
e
lf
.
Fo
r
t
h
is
p
u
r
p
o
s
e,
p
r
ed
ictio
n
o
f
f
u
t
u
r
e
lo
ad
r
eq
u
ir
em
e
n
t
is
es
s
en
t
ial.
Dete
r
m
in
in
g
an
es
ti
m
ate
o
f
lo
ad
r
e
q
u
ir
e
m
en
t
s
f
o
r
f
u
t
u
r
e
is
k
n
o
w
n
as
lo
ad
f
o
r
ec
asti
n
g
.
Dep
e
n
d
in
g
o
n
t
h
e
d
u
r
atio
n
,
lo
ad
f
o
r
ec
asti
n
g
i
s
g
en
er
all
y
cla
s
s
i
f
ied
i
n
to
s
h
o
r
t
-
ter
m
,
m
ed
i
u
m
-
ter
m
an
d
lo
n
g
-
ter
m
[
2
]
.
T
h
e
d
ev
elo
p
m
e
n
t
o
f
a
n
ac
c
u
r
ate,
f
ast
a
n
d
r
o
b
u
s
t
elec
tr
ic
al
lo
ad
f
o
r
ec
asti
n
g
m
et
h
o
d
o
lo
g
y
i
s
o
f
i
m
p
o
r
tan
ce
to
b
o
th
th
e
elec
tr
i
c
u
til
it
y
an
d
it
s
c
u
s
to
m
er
s
.
A
f
o
r
ec
ast
t
h
at
i
s
to
o
lo
w
o
r
to
o
h
i
g
h
ca
n
r
e
s
u
l
t
i
n
r
ev
en
u
e
lo
s
s
[
3
]
.
A
w
id
e
v
ar
i
et
y
o
f
f
o
r
ec
asti
n
g
m
o
d
el
s
h
a
v
e
b
ee
n
p
r
o
p
o
s
ed
in
th
e
liter
at
u
r
e
,
m
o
s
t
o
f
w
h
ic
h
ca
n
b
e
g
e
n
er
all
y
c
lass
if
ied
in
t
o
t
w
o
b
r
o
ad
ca
teg
o
r
ies:
1
)
S
ta
tis
tica
l
o
r
C
la
s
s
ica
l
ap
p
r
o
ac
h
es
s
u
ch
a
s
m
u
l
tip
le
r
eg
r
ess
io
n
,
ex
p
o
n
en
tial
s
m
o
o
t
h
in
g
,
m
in
i
m
u
m
m
ea
n
s
q
u
ar
e
esti
m
at
io
n
,
B
o
x
an
d
J
en
k
i
n
s
m
eth
o
d
s
,
Kal
m
a
n
f
ilter
a
n
d
s
tate
e
s
ti
m
atio
n
.
2
)
A
r
tifi
cia
l
I
n
tellig
en
ce
(
A
I
)
b
ased
m
et
h
o
d
s
s
u
c
h
a
s
E
x
p
er
t
s
y
s
te
m
,
Ne
u
r
al
Net
w
o
r
k
s
,
F
u
zz
y
L
o
g
ic,
P
ar
ticle
S
w
ar
m
Op
ti
m
izer
(
P
SO)
,
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
(
SVM)
an
d
Gen
et
ic
A
l
g
o
r
ith
m
(
G
A
)
.
Ot
h
er
ca
te
g
o
r
y
s
u
ch
a
s
h
yb
r
id
tech
n
iq
u
e
s
is
a
co
m
b
i
n
atio
n
o
f
m
o
r
e
t
h
an
o
n
e
tech
n
iq
u
e
i.e
.
,
eith
er
t
h
e
co
m
b
in
atio
n
o
f
clas
s
ical
an
d
A
I
tec
h
n
iq
u
es o
r
th
e
c
o
m
b
i
n
atio
n
o
f
d
if
f
er
en
t
A
I
tech
n
iq
u
es [
4
]
.
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:
2
0
8
8
-
8708
Da
ily
p
ea
k
lo
a
d
fo
r
ec
a
s
t u
s
in
g
a
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
k
(
R
a
mesh
K
u
ma
r
V
.
)
2257
T
o
m
o
n
o
b
u
Se
n
j
y
u
et
al.
[
5
]
,
e
m
p
lo
y
ed
A
NN
w
it
h
b
ac
k
p
r
o
p
ag
atio
n
al
g
o
r
ith
m
to
f
o
r
ec
ast
t
h
e
lo
ad
b
y
ad
d
in
g
a
co
r
r
ec
tio
n
to
t
h
e
s
elec
ted
s
i
m
i
lar
d
a
y
d
ata.
L
o
ad
d
ev
iatio
n
a
n
d
te
m
p
er
at
u
r
e
d
ev
iatio
n
d
ata
i
s
u
s
ed
as
th
e
co
r
r
ec
tio
n
f
o
r
f
o
r
ec
ast
in
g
lo
ad
.
I
f
th
e
te
m
p
er
at
u
r
e
cu
r
v
e
s
ch
a
n
g
e
r
ap
id
l
y
o
n
th
e
f
o
r
ec
ast
d
a
y
,
lo
ad
p
o
w
er
ch
an
g
es
g
r
ea
tl
y
a
n
d
f
o
r
ec
ast
er
r
o
r
w
o
u
ld
in
cr
ea
s
e.
Vito
r
Hu
g
o
Fer
r
eir
a
et
al.
[
6
]
,
p
r
o
p
o
s
ed
A
NN
m
o
d
el
w
it
h
B
a
y
esia
n
tr
ai
n
i
n
g
an
d
SVM
lear
n
i
n
g
alg
o
r
it
h
m
to
co
n
tr
o
l
t
h
e
ANN
co
m
p
lex
it
y
.
T
h
e
t
h
r
ee
i
n
p
u
t
d
atasets
u
s
ed
w
er
e
h
o
u
r
l
y
lo
ad
an
d
te
m
p
er
at
u
r
e,
d
ail
y
p
e
ak
lo
ad
a
n
d
te
m
p
er
at
u
r
e,
a
n
d
h
al
f
-
h
o
u
r
l
y
lo
ad
te
m
p
er
atu
r
e
a
n
d
p
r
ice.
Z
.
A
.
B
ash
ir
et
al.
[
7
]
,
i
m
p
l
e
m
e
n
te
d
ad
ap
tiv
e
ar
tif
ic
ial
n
eu
r
al
n
e
t
w
o
r
k
s
to
p
r
ed
icted
h
o
u
r
l
y
lo
ad
d
e
m
a
n
d
a
n
d
tr
ai
n
ed
th
e
ANNs
w
it
h
P
SO
alg
o
r
i
th
m
w
i
th
lo
ad
,
te
m
p
er
at
u
r
e,
win
d
s
p
ee
d
,
h
u
m
id
it
y
as
in
p
u
t
d
ata.
Yi
n
g
C
h
en
et
al.
[
8
]
,
d
ev
elo
p
ed
w
av
e
let
b
ased
n
eu
r
al
n
et
w
o
r
k
m
e
th
o
d
t
o
f
o
r
ec
ast
n
e
x
t
d
a
y
d
em
a
n
d
,
w
it
h
s
i
m
ilar
d
a
y
lo
ad
an
d
w
ea
th
er
in
f
o
r
m
at
io
n
s
u
c
h
as
w
i
n
d
-
c
h
ill
te
m
p
er
at
u
r
e,
h
u
m
id
it
y
,
w
i
n
d
s
p
ee
d
,
clo
u
d
c
o
v
er
,
an
d
p
r
e
cip
itatio
n
as
in
p
u
ts
.
Ma
d
asu
Han
m
a
n
d
lu
et
al.
[
9
]
,
p
r
o
p
o
s
ed
h
y
b
r
id
n
eu
r
al
n
et
w
o
r
k
s
to
f
o
r
ec
ast
h
o
u
r
l
y
l
o
ad
d
em
a
n
d
,
w
it
h
lo
ad
d
ata
an
d
w
ea
t
h
er
d
ata
co
m
p
r
i
s
i
n
g
te
m
p
er
at
u
r
e,
w
i
n
d
s
p
ee
d
an
d
r
elativ
e
h
u
m
id
it
y
.
Ni
Din
g
et
al.
[
1
0
]
,
p
r
o
p
o
s
ed
Gen
er
alize
d
Ne
u
r
al
Net
w
o
r
k
m
o
d
el,
w
it
h
lo
ad
d
ata,
te
m
p
er
atu
r
e
d
ata
an
d
co
s
t
f
u
n
ctio
n
(
m
i
n
i
m
izatio
n
)
as
in
p
u
t
p
ar
a
m
eter
s
.
Yiz
h
en
g
X
u
et
al.
[
1
1
]
,
ap
p
lied
A
N
N
an
d
Mo
n
te
C
ar
lo
Si
m
u
latio
n
s
tec
h
n
iq
u
e
to
p
r
ed
ict
lo
ad
a
d
ay
a
h
ea
d
u
s
i
n
g
lo
ad
d
ata,
te
m
p
er
atu
r
e,
h
u
m
id
it
y
a
n
d
w
i
n
d
s
p
ee
d
as
i
n
p
u
t
v
ar
iab
les.
Fil
ip
e
R
o
d
r
ig
u
es
et
a
l.
[
1
2
]
,
p
r
o
p
o
s
ed
Feed
-
f
o
r
w
ar
d
ANN
w
i
th
th
e
L
e
v
en
b
er
g
-
Ma
r
q
u
ar
d
t
lea
r
n
in
g
al
g
o
r
ith
m
.
I
n
p
u
t
v
ar
iab
les
ar
e
ar
ea
lo
ca
tio
n
,
n
u
m
b
er
o
f
co
n
s
u
m
er
s
an
d
co
n
s
u
m
p
tio
n
o
f
elec
tr
ical
ap
p
lian
ce
w
it
h
h
o
u
r
l
y
lo
ad
co
n
s
u
m
p
tio
n
w
er
e
co
n
s
id
er
ed
to
f
o
r
ec
ast
th
e
r
esid
e
n
tia
l
d
em
a
n
d
.
An
a
m
ik
a
et
al.
[
1
3
]
,
p
r
o
p
o
s
ed
m
u
ltil
a
y
er
f
ee
d
f
o
r
w
ar
d
n
et
w
o
r
k
w
it
h
te
n
h
id
d
en
la
y
er
s
a
n
d
L
e
v
en
b
er
g
Ma
r
q
u
ar
d
t
b
ac
k
p
r
o
p
ag
atio
n
lear
n
i
n
g
al
g
o
r
ith
m
f
o
r
tr
ain
in
g
t
h
e
n
et
w
o
r
k
.
T
h
e
in
p
u
t
to
t
h
e
n
et
w
o
r
k
is
h
al
f
h
o
u
r
l
y
lo
ad
d
ata.
T
h
e
ab
o
v
e
w
o
r
k
[
5
-
11
]
,
e
m
p
lo
y
s
eith
er
h
y
b
r
id
tech
n
iq
u
e
s
th
at
is
t
h
e
co
m
b
in
a
tio
n
o
f
d
if
f
er
en
t
AI
tech
n
iq
u
es
o
r
co
m
b
in
at
io
n
o
f
class
ical
an
d
A
I
tech
n
iq
u
es
o
r
u
tili
ze
s
m
o
r
e
th
a
n
t
w
o
i
n
p
u
t
p
ar
a
m
eter
s
to
f
o
r
ec
ast
t
h
e
lo
ad
d
e
m
a
n
d
an
d
[
1
2
-
1
3
]
,
th
o
u
g
h
e
m
p
lo
y
s
AN
N
tech
n
iq
u
e
s
w
it
h
L
e
v
en
b
er
g
-
Ma
r
q
u
ar
d
t
lear
n
in
g
alg
o
r
ith
m
b
u
t
d
o
es
n
o
t
p
r
o
v
id
es
an
y
in
f
o
r
m
at
io
n
r
e
g
ar
d
in
g
t
h
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
i
n
t
h
e
h
id
d
en
la
y
er
(
s
)
t
h
at
r
ep
r
esen
ts
t
h
e
ac
tu
al
ANN
m
o
d
el.
Hen
ce
,
th
e
p
r
esen
t
w
o
r
k
p
r
o
p
o
s
es
an
ANN
m
o
d
el
t
h
at
u
s
e
s
lo
ad
an
d
/o
r
te
m
p
er
atu
r
e
d
ata
f
o
r
tr
ain
i
n
g
t
h
e
n
et
w
o
r
k
to
p
r
ed
ict
d
aily
p
ea
k
lo
ad
d
em
a
n
d
w
it
h
o
p
ti
m
al
n
u
m
b
er
o
f
h
id
d
en
la
y
e
r
n
e
u
r
o
n
s
a
n
d
is
v
al
id
ated
o
n
B
E
SC
OM
p
o
w
er
s
y
s
te
m
s
.
2.
CO
NVEN
T
I
O
NA
L
T
E
CH
N
I
Q
U
E
S
T
h
e
s
i
m
p
lest
co
n
v
en
t
io
n
al
m
et
h
o
d
em
p
lo
y
ed
f
o
r
lo
ad
f
o
r
ec
asti
n
g
is
c
u
r
v
e
f
itti
n
g
tech
n
iq
u
es.
T
h
e
p
r
o
ce
d
u
r
e
o
f
d
eter
m
i
n
i
n
g
t
h
e
e
m
p
ir
ica
l
eq
u
atio
n
o
f
th
e
c
u
r
v
e
o
f
b
est
f
it
is
k
n
o
w
n
as
cu
r
v
e
f
itti
n
g
tech
n
iq
u
es.
So
m
e
o
f
t
h
e
cu
r
v
e
f
it tec
h
n
iq
u
es
u
s
ed
in
elec
tr
ic
al
lo
ad
f
o
r
ec
asti
n
g
ar
e
-
L
i
n
ea
r
:
=
+
-
E
x
p
o
n
en
t
ial:
=
-
L
o
g
ar
it
h
m
ic:
=
(
)
+
-
P
o
ly
n
o
m
ial:
=
2
+
+
-
P
o
w
er
:
=
W
h
er
e
A
,
B
an
d
C
ar
e
th
e
c
o
n
s
ta
n
ts
d
eter
m
in
ed
b
y
p
r
i
n
c
ip
le
o
f
least
s
q
u
ar
es.
L
et
x
b
e
th
e
i
n
d
ep
en
d
en
t
v
ar
iab
le
th
at
r
ep
r
esen
ts
d
a
y
s
o
f
a
m
o
n
t
h
an
d
y
b
e
t
h
e
d
ep
en
d
en
t
v
ar
iab
le
o
n
x
r
ep
r
ese
n
tin
g
t
h
e
f
o
r
ec
asted
d
em
a
n
d
s
u
ch
t
h
at
=
(
)
.
No
w
co
n
s
i
d
er
th
e
n
th
p
o
l
y
n
o
m
ial
f
u
n
ctio
n
(
)
=
0
+
∑
=
1
(
1
)
I
n
(
1
)
,
th
e
co
n
s
ta
n
t
a
0
i
s
t
h
e
i
n
ter
ce
p
to
r
o
f
y
-
a
x
i
s
w
h
ic
h
r
e
p
r
esen
ts
th
e
b
ase
lo
ad
.
I
n
p
r
e
s
en
t
w
o
r
k
,
f
o
r
i
=
1
,
2
t
h
e
o
t
h
er
co
n
s
tan
t
s
a
1
an
d
a
2
ar
e
th
e
ex
o
g
en
o
u
s
f
ac
to
r
s
.
W
it
h
t
h
e
k
n
o
w
n
p
ar
a
m
eter
s
y
(
h
i
s
to
r
ical
lo
ad
)
an
d
x
(
d
ay
)
t
h
e
b
est f
i
t c
an
b
e
d
o
n
e
to
ev
alu
ate
t
h
ese
c
o
n
s
ta
n
ts
w
i
th
lea
s
t e
r
r
o
r
.
3.
ARTI
F
I
CI
AL
N
E
URA
L
NE
T
WO
RK
T
E
CH
NI
Q
U
E
S
A
f
u
ll
y
co
n
n
ec
ted
m
u
lt
ila
y
er
f
ee
d
-
f
o
r
w
ar
d
n
eu
r
al
n
et
w
o
r
k
m
o
d
el
s
h
o
w
n
i
n
F
ig
u
r
e
1
is
e
m
p
lo
y
ed
f
o
r
d
ail
y
p
ea
k
lo
ad
f
o
r
ec
asti
n
g
o
f
th
e
m
o
n
t
h
.
T
h
e
in
p
u
t
la
y
er
co
n
s
is
ts
o
f
2
4
n
o
d
es
co
r
r
esp
o
n
d
in
g
to
t
w
o
in
p
u
t
p
ar
am
eter
s
v
iz.
,
1
2
in
p
u
t
n
o
d
es,
ea
ch
n
o
d
e
r
ep
r
esen
tin
g
a
m
o
n
t
h
an
d
h
a
s
a
m
a
x
i
m
u
m
o
f
3
1
d
aily
p
ea
k
lo
ad
d
ata
r
ep
r
esen
ts
t
h
e
co
r
r
esp
o
n
d
in
g
d
a
y
s
o
f
a
p
ar
tic
u
lar
m
o
n
th
a
n
d
s
i
m
ilar
l
y
a
n
o
th
er
1
2
i
n
p
u
t
n
o
d
es
f
o
r
d
ail
y
p
ea
k
te
m
p
er
at
u
r
e
d
ata.
T
h
e
o
u
tp
u
t
la
y
er
co
n
s
i
s
ts
o
f
1
2
n
o
d
es
ea
ch
n
o
d
e
co
r
r
esp
o
n
d
s
to
a
m
o
n
th
an
d
h
as
a
m
ax
i
m
u
m
o
f
3
1
d
ail
y
p
ea
k
f
o
r
ec
asted
lo
ad
r
ep
r
esen
tin
g
d
ay
s
o
f
t
h
e
m
o
n
t
h
.
T
h
e
s
i
n
g
le
h
id
d
en
la
y
er
i
s
u
s
ed
w
it
h
v
ar
iab
le
n
u
m
b
er
o
f
n
o
d
es
to
v
er
i
f
y
t
h
e
d
ep
en
d
en
c
y
u
p
o
n
t
h
e
co
r
r
ec
t
p
er
ce
n
tag
e
o
f
f
o
r
ec
asti
n
g
a
n
d
r
ep
ea
tab
ilit
y
i
n
co
n
v
er
g
e
n
ce
.
T
h
e
o
u
tp
u
t
f
u
n
ctio
n
o
f
ea
ch
u
n
it
in
t
h
e
h
id
d
en
a
n
d
o
u
tp
u
t
l
a
y
er
s
is
n
o
n
-
li
n
ea
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t 2
0
1
9
:
2
2
5
6
-
2263
2258
(
s
ig
m
o
id
)
.
I
n
p
u
ts
to
th
e
p
r
o
p
o
s
ed
m
o
d
el
ar
e
a
1,
a
2…
a
12
,
d
ai
l
y
p
ea
k
lo
ad
g
r
o
w
t
h
d
ata
a
n
d
a
13
,
a
14
…a
24
,
d
ail
y
p
ea
k
te
m
p
er
atu
r
e
d
ata
o
f
t
h
e
co
r
r
esp
o
n
d
in
g
m
o
n
t
h
.
T
h
e
o
u
tp
u
ts
o
f
in
p
u
t la
y
er
f
o
r
=
1
,
2
…
2
4
is
g
iv
e
n
b
y
(
2
)
.
=
(
2
)
T
h
e
o
u
tp
u
ts
o
f
th
e
h
id
d
en
la
y
er
(
ℎ
)
an
d
o
u
tp
u
t
la
y
er
(
)
ar
e
r
ep
r
esen
ted
b
y
(
3
)
an
d
(
4
)
r
esp
ec
tiv
el
y
f
o
r
=
1
,
2
…
m
a
n
d
=
1
,
2
..
.
1
2
ℎ
=
{
∑
ℎ
−
ℎ
24
=
1
}
(
3
)
=
{
∑
ℎ
=
1
−
}
(
4
)
W
h
er
e,
ℎ
an
d
r
ep
r
esen
ts
w
e
i
g
h
t
s
o
f
th
e
li
n
k
s
f
o
r
in
p
u
t
-
h
id
d
en
la
y
er
s
a
n
d
h
id
d
en
-
o
u
tp
u
t
la
y
er
s
r
esp
ec
tiv
el
y
a
n
d
ℎ
an
d
ar
e
th
e
b
ias
ter
m
s
o
f
h
id
d
en
an
d
o
u
t
p
u
t
la
y
er
s
r
esp
ec
ti
v
el
y
.
T
h
e
o
u
tp
u
t
s
o
f
th
e
n
et
w
o
r
k
co
r
r
esp
o
n
d
to
b
1
, b
2
…
b
12
ar
e
th
e
d
ail
y
p
ea
k
lo
ad
f
o
r
ec
ast o
f
th
e
co
r
r
esp
o
n
d
in
g
m
o
n
th
.
Fig
u
r
e
1
.
Mu
ltil
a
y
er
f
ee
d
-
f
o
r
war
d
n
eu
r
al
n
et
w
o
r
k
m
o
d
el
f
o
r
d
ail
y
p
ea
k
lo
ad
f
o
r
ec
ast
4.
I
NP
UT
D
AT
A
S
E
L
E
C
T
I
O
N
I
n
t
h
e
p
r
esen
t
w
o
r
k
,
th
e
h
o
u
r
l
y
p
ea
k
lo
ad
d
ata
f
o
r
m
o
r
e
th
an
f
i
v
e
y
ea
r
s
i.e
.
,
f
r
o
m
J
a
n
2
0
1
2
to
Ma
r
ch
2
0
1
7
is
co
llected
f
r
o
m
B
a
n
g
a
lo
r
e
E
lectricity
S
u
p
p
ly
C
o
mp
a
n
y
an
d
th
e
h
o
u
r
l
y
p
ea
k
te
m
p
er
at
u
r
e
d
ata
f
r
o
m
J
an
2
0
1
6
t
o
Ma
r
ch
2
0
1
7
is
co
llected
f
r
o
m
Meteo
r
o
lo
g
i
ca
l
C
en
tr
e
,
B
an
g
alo
r
e.
Usi
n
g
th
e
d
ail
y
p
ea
k
lo
ad
d
ata
f
r
o
m
2
0
1
2
to
2
0
1
6
,
th
e
a
v
er
ag
e
lo
ad
d
ata
f
o
r
2
0
1
7
is
c
alcu
lated
to
o
b
tai
n
t
h
e
e
m
p
ir
ic
al
cu
r
v
e
f
it e
q
u
atio
n
in
co
n
v
e
n
tio
n
a
l
m
et
h
o
d
.
Fo
r
A
NN
tec
h
n
iq
u
e,
th
e
lo
ad
g
r
o
w
t
h
d
ata
f
o
r
2
0
1
7
is
esti
m
ated
,
w
it
h
th
e
lo
ad
g
r
o
w
t
h
d
ata
o
f
2
0
1
7
an
d
t
h
e
te
m
p
er
at
u
r
e
d
ata,
th
e
d
ail
y
p
ea
k
lo
ad
as
p
er
th
e
r
eq
u
ir
e
m
e
n
ts
ca
n
b
e
f
o
r
ec
asted
ah
ea
d
.
No
r
m
a
lizatio
n
o
f
d
ata,
t
h
e
i
n
p
u
t
d
ata
f
o
r
th
e
n
eu
r
al
n
et
w
o
r
k
w
il
l
h
a
v
e
v
er
y
w
id
e
r
an
g
es
i
f
th
e
ac
t
u
al
lo
ad
d
ata
is
d
ir
ec
tly
u
s
ed
.
T
h
i
s
m
a
y
ca
u
s
e
co
n
v
er
g
e
n
ce
p
r
o
b
le
m
[
1
4
]
d
u
r
in
g
t
h
e
lear
n
in
g
p
r
o
ce
s
s
.
T
o
av
o
id
th
is
,
t
h
e
i
n
p
u
t
d
ata
w
er
e
n
o
r
m
alize
d
s
u
c
h
t
h
at
t
h
e
y
w
er
e
w
it
h
in
th
e
r
a
n
g
e
o
f
0
to
1
.
Fo
r
th
i
s
p
u
r
p
o
s
e,
th
e
lo
ad
an
d
te
m
p
er
atu
r
e
d
ata
ar
e
n
o
r
m
alize
d
u
s
i
n
g
(
5
)
.
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:
2
0
8
8
-
8708
Da
ily
p
ea
k
lo
a
d
fo
r
ec
a
s
t u
s
in
g
a
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
k
(
R
a
mesh
K
u
ma
r
V
.
)
2259
=
(
,
)
(
5
)
W
h
er
e,
is
th
e
n
o
r
m
alize
d
lo
ad
/te
m
p
er
atu
r
e
d
ata
w
h
ich
i
s
u
s
ed
as
in
p
u
t
to
th
e
n
et,
(
,
)
is
th
e
ac
tu
al
lo
ad
g
r
o
w
t
h
/te
m
p
er
atu
r
e
d
ata,
i
=
1
to
n
,
n
(
n
u
m
b
er
o
f
d
ay
s
)
=
1
,
2
…3
1
an
d
j
=
1
to
m
,
m
(
n
u
m
b
er
o
f
m
o
n
t
h
s
)
=
1
,
2
,
….
.
1
2
an
d
is
th
e
m
ax
i
m
u
m
lo
ad
/te
m
p
er
atu
r
e
o
f
a
p
ar
ticu
lar
m
o
n
th
.
T
h
u
s
,
th
e
i
n
p
u
t
m
atr
i
x
w
ill
b
e
in
t
h
e
o
r
d
er
o
f
3
1
x
1
2
an
d
u
s
in
g
th
e
s
e
d
ata
th
e
d
ail
y
p
ea
k
lo
ad
f
o
r
an
y
p
ar
ticu
lar
m
o
n
th
o
r
co
m
p
lete
y
ea
r
ca
n
b
e
f
o
r
ec
ast
ed
.
5.
T
RAI
NIN
G
T
H
E
NE
T
WO
R
K
T
r
ain
in
g
o
f
th
e
n
et
w
o
r
k
is
co
m
p
letel
y
b
ased
o
n
t
h
e
ac
t
u
al
l
o
ad
d
ata
an
d
te
m
p
er
atu
r
e
d
ata
co
llected
f
r
o
m
t
h
e
r
esp
ec
ti
v
e
au
t
h
o
r
it
y
o
n
h
o
u
r
l
y
b
asis
.
Fro
m
t
h
e
co
ll
ec
ted
d
ata,
th
e
d
ata
f
o
r
m
o
r
e
th
an
f
i
v
e
y
ea
r
s
h
a
v
e
b
ee
n
an
al
y
ze
d
f
o
r
th
e
p
er
ce
n
tag
e
g
r
o
w
th
f
r
o
m
y
ea
r
t
o
y
ea
r
,
m
o
n
th
to
m
o
n
t
h
an
d
h
o
u
r
to
h
o
u
r
.
Af
ter
u
n
d
er
s
ta
n
d
in
g
th
e
p
er
ce
n
tag
e
g
r
o
w
th
,
t
h
e
tr
ain
i
n
g
f
i
l
e
f
o
r
th
e
n
e
u
r
al
n
et
w
o
r
k
h
as
b
ee
n
p
r
ep
ar
ed
an
d
u
s
ed
to
p
r
ed
ict
th
e
f
u
t
u
r
e
lo
ad
d
e
m
a
n
d
.
T
h
e
s
ize
o
f
th
e
tr
ai
n
in
g
f
ile
w
it
h
te
m
p
er
atu
r
e
p
ar
am
eter
i
n
cl
u
d
ed
,
f
o
r
en
tire
y
ea
r
w
ill
b
e
in
t
h
e
o
r
d
er
o
f
3
1
x
2
4
an
d
test
in
g
f
ile
s
iz
e
ca
n
b
e
s
a
m
e
as
t
h
at
o
f
tr
ai
n
i
n
g
f
ile
o
r
s
u
b
s
e
t
o
f
tr
ain
i
n
g
f
ile
as p
er
th
e
d
e
m
an
d
to
b
e
f
o
r
ec
asted
.
T
h
e
n
et
w
o
r
k
i
s
tr
ain
ed
u
s
i
n
g
L
e
v
en
b
er
g
-
Ma
r
q
u
ar
d
t
tr
ain
i
n
g
al
g
o
r
ith
m
f
o
r
2
0
0
0
e
p
o
ch
s
an
d
th
r
es
h
o
ld
o
n
er
r
o
r
,
s
et
to
a
v
er
y
lo
w
v
al
u
e
o
f
1
0
-
5
.
T
h
e
lear
n
i
n
g
r
ate
p
ar
a
m
eter
an
d
m
o
m
en
tu
m
f
ac
to
r
s
ar
e
0
.
1
an
d
0
.
9
r
esp
ec
tiv
e
l
y
[
1
5
]
.
T
r
a
in
i
n
g
i
s
ca
r
r
ied
o
u
t
u
n
ti
l
th
e
t
o
tal
s
u
m
o
f
m
ea
n
s
q
u
ar
es
er
r
o
r
r
ea
ch
es
eit
h
er
th
e
d
esire
d
er
r
o
r
lim
it
o
f
1
0
-
5
o
r
till
t
h
e
co
m
p
letio
n
o
f
2
0
0
0
ep
o
ch
s
.
T
h
e
n
et
w
o
r
k
w
a
s
i
n
i
tiall
y
tr
ai
n
ed
w
it
h
v
ar
y
i
n
g
n
u
m
b
er
o
f
n
o
d
es
i
n
t
h
e
h
id
d
en
la
y
er
.
T
h
e
s
m
alles
t
s
u
m
o
f
s
q
u
ar
es
er
r
o
r
(
1
0
-
5
)
w
a
s
o
b
tain
ed
f
o
r
t
h
e
n
et
w
o
r
k
s
tr
u
ct
u
r
e
w
i
th
2
4
N
i
,
2
1
N
h
an
d
1
2
N
o
i
n
p
u
t
la
y
er
,
h
i
d
d
en
la
y
er
a
n
d
o
u
tp
u
t
la
y
er
r
e
s
p
ec
tiv
el
y
.
Fi
g
u
r
e
2
s
h
o
w
s
t
h
e
tr
en
d
i
n
th
e
tr
ai
n
i
n
g
er
r
o
r
f
o
r
ea
ch
ep
o
ch
f
o
r
2
1
n
o
d
es in
th
e
h
id
d
en
la
y
er
f
o
r
Ma
r
ch
2
0
1
7
.
Fig
u
r
e
2
.
T
r
ain
in
g
er
r
o
r
cu
r
v
e
f
o
r
Ma
r
ch
2
0
1
7
6.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
NS
6
.
1
.
Dem
a
n
d f
o
re
ca
s
t
ing
us
i
ng
co
nv
ent
io
na
l
m
et
ho
ds
I
n
t
h
is
m
eth
o
d
,
t
h
e
tr
e
n
d
i
n
th
e
h
i
s
to
r
ical
lo
ad
d
ata
p
o
in
t
s
is
p
lo
tted
w
it
h
th
e
u
s
e
o
f
l
in
ea
r
a
n
d
p
o
ly
n
o
m
ia
l
o
f
s
ec
o
n
d
o
r
d
er
f
u
n
ct
io
n
to
o
b
tain
th
e
eq
u
atio
n
o
f
e
m
p
ir
ical
c
u
r
v
e
f
i
t.
T
h
e
co
ef
f
icien
ts
v
al
u
es
o
f
th
e
f
it
ted
cu
r
v
e
ar
e
g
iv
e
n
b
y
least
s
q
u
ar
e
ap
p
r
o
ac
h
.
T
h
e
er
r
o
r
w
ill
m
in
i
m
u
m
f
o
r
th
e
b
est
f
it,
w
h
e
n
th
e
g
o
o
d
n
ess
o
f
f
it
i.e
.
R
2
ten
d
s
to
w
ar
d
s
o
n
e.
T
h
e
co
ef
f
icie
n
t
a
0
r
ep
r
esen
ts
t
h
e
b
ase
lo
a
d
an
d
o
th
er
a
1
,
a
2
r
ep
r
esen
ts
th
e
ex
o
g
en
o
u
s
f
ac
t
o
r
s
.
T
h
e
lin
ea
r
an
d
p
o
ly
n
o
m
ia
l
f
it
f
o
r
Ma
r
ch
2
0
1
7
is
s
h
o
w
n
in
F
i
g
u
r
e
3
an
d
th
e
co
r
r
esp
o
n
d
in
g
e
m
p
ir
ical
c
u
r
v
e
f
it e
q
u
atio
n
is
g
iv
e
n
b
y
(
6
a)
an
d
(
6
b
)
,
r
esp
ec
tiv
el
y
.
Y
=
3
.
7762x
+
4011
.
8
MW
(
6
a)
Y
=
−
0
.
1816
x
2
+
9
.
5869x
+
3979
.
8
MW
(
6
b
)
W
h
er
e,
Y
is
f
o
r
ec
asted
lo
ad
in
MW
an
d
x
is
th
e
d
a
y
o
f
th
e
m
o
n
th
.
T
h
e
d
em
an
d
f
o
r
ec
ast
ca
lcu
l
ated
b
y
u
s
in
g
ab
o
v
e
eq
u
ati
o
n
s
an
d
p
er
ce
n
tag
e
er
r
o
r
is
ca
lcu
lated
u
s
i
n
g
(
7
)
is
tab
u
lated
i
n
T
ab
le
1
.
T
h
e
r
esu
lt
s
h
o
w
s
t
h
at
f
o
r
ec
asted
v
al
u
e
s
b
y
th
e
s
e
m
et
h
o
d
s
h
as
lar
g
e
er
r
o
r
d
u
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t 2
0
1
9
:
2
2
5
6
-
2263
2260
to
th
e
n
o
n
-
li
n
ea
r
it
y
o
f
lo
ad
.
T
h
e
lin
ea
r
f
it
h
a
s
t
h
e
m
ax
i
m
u
m
er
r
o
r
o
f
1
3
%
an
d
m
i
n
i
m
u
m
o
f
2
.
8
2
%,
w
h
ile
p
o
l
y
n
o
m
ial
f
it
h
a
s
m
ax
i
m
u
m
o
f
1
3
.
0
6
%
an
d
m
i
n
i
m
u
m
o
f
2
.
5
5
%
er
r
o
r
o
f
ac
tu
al
d
e
m
an
d
.
T
h
e
p
lo
t
o
f
ac
tu
al
d
e
m
a
n
d
ag
ai
n
s
t
t
h
e
f
o
r
ec
asted
lo
ad
o
f
li
n
ea
r
a
n
d
p
o
l
y
n
o
m
ial
f
i
t
i
s
s
h
o
w
n
i
n
F
i
g
u
r
e
4
a
an
d
4
b
r
esp
ec
tiv
el
y
.
T
h
is
m
et
h
o
d
r
eq
u
ir
es
o
n
e
eq
u
atio
n
f
o
r
a
m
o
n
th
a
n
d
1
2
eq
u
atio
n
s
f
o
r
a
y
ea
r
an
d
h
e
n
ce
t
h
e
p
r
o
ce
s
s
b
ec
o
m
e
s
co
m
p
lex
an
d
ted
io
u
s
.
Fu
r
t
h
er
th
e
n
u
m
b
e
r
o
f
eq
u
atio
n
s
r
eq
u
ir
ed
ca
n
b
e
r
ed
u
ce
d
to
o
n
e
eq
u
atio
n
f
o
r
a
y
ea
r
b
y
ta
k
i
n
g
av
er
a
g
e
o
f
co
r
r
esp
o
n
d
in
g
d
ail
y
p
ea
k
lo
ad
o
v
er
a
co
m
p
lete
y
ea
r
.
W
ith
t
h
e
r
ed
u
ctio
n
in
n
u
m
b
er
o
f
eq
u
at
i
o
n
s
,
th
e
p
er
ce
n
ta
g
e
er
r
o
r
in
cr
ea
s
es d
r
asti
ca
ll
y
.
%
=
|
−
|
×
100
(
7
)
T
ab
le
1
.
Daily
lo
ad
f
o
r
ec
ast r
e
s
u
lt
s
f
o
r
Ma
r
ch
2
0
1
7
D
a
y
A
c
t
u
a
l
L
o
a
d
(
M
W
)
F
o
r
e
c
a
st
e
d
L
o
a
d
(
M
W
)
w
i
t
h
l
i
n
e
a
r
f
i
t
%
Er
r
o
r
F
o
r
e
c
a
st
e
d
L
o
a
d
(
M
W
)
w
i
t
h
P
o
l
y
n
o
mi
a
l
f
i
t
%
Er
r
o
r
A
N
N
F
o
r
e
c
a
st
e
d
L
o
a
d
(
M
W
)
W
i
t
h
o
u
t
T
e
mp
e
r
a
t
u
r
e
%
Er
r
o
r
W
i
t
h
T
e
mp
e
r
a
t
u
r
e
%
Er
r
o
r
1
4
4
3
8
4
0
1
6
9
.
5
2
3
9
8
9
1
0
.
1
1
4
4
7
1
-
0
.
7
4
4
4
5
6
-
0
.
4
0
2
4
4
9
0
4
0
1
9
1
0
.
4
8
3
9
9
8
1
0
.
9
5
4
5
6
0
-
1
.
5
7
4
5
3
6
-
1
.
0
2
3
4
5
2
7
4
0
2
3
1
1
.
1
3
4
0
0
7
1
1
.
4
9
4
5
4
5
-
0
.
4
0
4
5
3
7
-
0
.
2
2
4
4
4
9
9
4
0
2
7
1
0
.
4
9
4
0
1
5
1
0
.
7
5
4
6
1
9
-
2
.
6
8
4
6
0
9
-
2
.
4
4
5
4
2
4
6
4
0
3
1
5
.
0
7
4
0
2
3
5
.
2
5
4
4
2
0
-
4
.
1
0
4
4
1
3
-
3
.
9
4
6
4
4
1
9
4
0
3
4
8
.
7
0
4
0
3
1
8
.
7
9
4
2
9
8
2
.
7
3
4
2
9
7
2
.
7
6
7
4
4
1
7
4
0
3
8
8
.
5
8
4
0
3
8
8
.
5
8
4
5
2
0
-
2
.
3
4
4
5
1
1
-
2
.
1
2
8
4
4
5
5
4
0
4
2
9
.
2
7
4
0
4
5
9
.
2
1
4
3
6
5
2
.
0
1
4
3
5
9
2
.
1
5
9
4
4
2
0
4
0
4
6
8
.
4
7
4
0
5
1
8
.
3
4
4
5
2
9
-
2
.
4
7
4
5
1
3
-
2
.
1
1
10
4
4
3
1
4
0
5
0
8
.
6
1
4
0
5
8
8
.
4
3
4
5
8
2
-
3
.
4
0
4
5
6
4
-
3
.
0
1
11
4
3
9
0
4
0
5
3
7
.
6
7
4
0
6
3
7
.
4
4
4
5
7
5
-
4
.
2
1
4
5
6
4
-
3
.
9
6
12
4
1
7
5
4
0
5
7
2
.
8
2
4
0
6
9
2
.
5
5
4
3
6
8
-
4
.
6
1
4
3
5
9
-
4
.
4
0
13
4
2
9
6
4
0
6
1
5
.
4
7
4
0
7
4
5
.
1
7
4
4
6
7
-
3
.
9
7
4
4
4
8
-
3
.
5
3
14
4
2
4
9
4
0
6
5
4
.
3
4
4
0
7
8
4
.
0
1
4
4
5
2
-
4
.
7
8
4
4
3
3
-
4
.
3
2
15
4
5
4
6
4
0
6
8
1
0
.
5
0
4
0
8
3
1
0
.
1
9
4
3
2
8
4
.
8
1
4
4
2
6
2
.
6
5
16
4
5
2
3
4
0
7
2
9
.
9
7
4
0
8
7
9
.
6
5
4
3
3
6
4
.
1
4
4
4
3
3
2
.
0
0
17
4
5
5
0
4
0
7
6
1
0
.
4
1
4
0
9
0
1
0
.
0
9
4
4
4
3
2
.
3
3
4
4
3
8
2
.
4
6
18
4
6
0
5
4
0
8
0
1
1
.
4
1
4
0
9
4
1
1
.
1
1
4
5
0
8
2
.
1
0
4
5
0
7
2
.
1
2
19
4
3
2
4
4
0
8
4
5
.
5
6
4
0
9
6
5
.
2
6
4
4
7
5
-
3
.
4
9
4
4
6
5
-
3
.
2
6
20
4
6
6
7
4
0
8
7
1
2
.
4
2
4
0
9
9
1
2
.
1
7
4
6
2
3
0
.
9
5
4
6
2
1
0
.
9
8
21
4
5
4
1
4
0
9
1
9
.
9
1
4
1
0
1
9
.
6
9
4
7
1
3
-
3
.
7
8
4
6
8
4
-
3
.
1
5
22
4
7
0
7
4
0
9
5
1
3
.
0
0
4
1
0
3
1
2
.
8
4
4
7
2
2
-
0
.
3
3
4
7
1
2
-
0
.
1
2
23
4
5
5
4
4
0
9
9
1
0
.
0
0
4
1
0
4
9
.
8
8
4
7
2
8
-
3
.
8
3
4
7
2
1
-
3
.
6
7
24
4
6
3
5
4
1
0
2
1
1
.
4
9
4
1
0
5
1
1
.
4
3
4
6
6
7
-
0
.
6
8
4
6
5
7
-
0
.
4
8
25
4
6
2
6
4
1
0
6
1
1
.
2
4
4
1
0
6
1
1
.
2
4
4
5
1
6
2
.
3
7
4
5
1
6
2
.
3
7
26
4
4
3
5
4
1
1
0
7
.
3
3
4
1
0
6
7
.
4
1
4
4
0
6
0
.
6
5
4
4
0
4
0
.
6
9
27
4
7
2
3
4
1
1
4
1
2
.
9
0
4
1
0
6
1
3
.
0
6
4
5
7
3
3
.
1
8
4
6
7
0
1
.
1
2
28
4
6
5
2
4
1
1
8
1
1
.
4
9
4
1
0
6
1
1
.
7
4
4
6
0
5
1
.
0
2
4
6
0
6
1
.
0
0
29
4
4
3
4
4
1
2
1
7
.
0
5
4
1
0
5
7
.
4
2
4
6
2
0
-
4
.
2
0
4
5
9
3
-
3
.
5
8
30
4
4
3
4
4
1
2
5
6
.
9
7
4
1
0
4
7
.
4
4
4
6
1
0
-
3
.
9
8
4
5
9
4
-
3
.
6
2
31
4
6
0
5
4
1
2
9
1
0
.
3
4
4
1
0
2
1
0
.
9
1
4
6
6
3
-
1
.
2
5
4
6
4
1
-
0
.
7
9
Fig
u
r
e
3
.
L
in
ea
r
f
it a
n
d
p
o
ly
n
o
m
ial
f
it f
o
r
Ma
r
ch
2
0
1
7
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:
2
0
8
8
-
8708
Da
ily
p
ea
k
lo
a
d
fo
r
ec
a
s
t u
s
in
g
a
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
k
(
R
a
mesh
K
u
ma
r
V
.
)
2261
(
a)
(
b
)
Fig
u
r
e
4
.
a.
C
o
m
p
ar
is
o
n
o
f
ac
t
u
al
an
d
f
o
r
ec
asted
lo
ad
cu
r
v
e
o
f
lin
ea
r
f
it f
o
r
Ma
r
ch
2
0
1
7
b.
C
o
m
p
ar
is
o
n
o
f
ac
t
u
al
&
f
o
r
ec
asted
lo
ad
cu
r
v
e
o
f
p
o
l
y
n
o
m
ial
f
it
f
o
r
Ma
r
ch
2
0
1
7
6
.
2
.
Dem
a
n
d f
o
re
ca
s
t
ing
us
i
ng
dev
elo
ped
ANN
m
o
del
MA
T
L
A
B
co
d
e
is
w
r
itte
n
t
o
tr
ain
an
d
test
th
e
p
r
o
p
o
s
ed
A
N
N
m
o
d
el
to
f
o
r
ec
ast
t
h
e
d
em
a
n
d
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
ANN
m
o
d
el
h
a
s
b
ee
n
test
ed
f
o
r
Ma
r
ch
2
0
1
7
.
T
h
e
p
er
ce
n
tag
e
o
f
co
r
r
ec
t
p
r
ed
ictio
n
o
b
tain
ed
f
r
o
m
th
e
A
NN
m
o
d
el
w
it
h
v
ar
y
i
n
g
n
u
m
b
er
o
f
n
o
d
es
in
th
e
h
id
d
en
la
y
er
h
a
s
b
ee
n
p
er
f
o
r
m
ed
.
I
t
is
o
b
s
er
v
ed
th
at
th
e
n
e
t
w
o
r
k
s
tr
u
ctu
r
e
w
ith
2
1
n
o
d
es
in
t
h
e
h
id
d
en
la
y
er
g
a
v
e
th
e
m
o
s
t
ac
cu
r
ate
f
o
r
ec
ast,
tr
ain
ed
w
it
h
te
m
p
er
at
u
r
e
as
s
h
o
w
n
i
n
T
ab
le
2
.
T
h
e
f
o
r
ec
asted
d
ail
y
p
ea
k
lo
ad
f
o
r
Ma
r
ch
2
0
1
7
is
co
m
p
ar
ed
w
it
h
th
e
ac
tu
al
lo
ad
d
ata
an
d
s
h
o
w
n
i
n
F
ig
u
r
e
5
.
T
h
e
p
e
r
ce
n
tag
e
er
r
o
r
ca
lcu
lated
u
s
in
g
(
7
)
is
ta
b
u
lated
in
T
ab
le
1
.
T
h
e
p
r
o
p
o
s
ed
A
NN
m
o
d
el,
w
h
e
n
tr
ain
ed
w
i
th
o
n
l
y
lo
ad
d
ata
as
its
in
p
u
t
p
ar
a
m
eter
p
r
ed
icted
th
e
d
e
m
a
n
d
w
it
h
m
ax
i
m
u
m
p
er
ce
n
tag
e
er
r
o
r
o
f
4
.
8
1
an
d
m
i
n
i
m
u
m
o
f
-
0
.
3
3
.
T
h
e
s
am
e
A
NN
m
o
d
el
o
n
tr
ain
in
g
w
it
h
b
o
th
lo
ad
an
d
te
m
p
er
atu
r
e
d
ata
a
s
i
ts
i
n
p
u
t
p
ar
a
m
eter
s
g
av
e
f
u
r
t
h
er
ac
cu
r
ate
p
r
ed
ictio
n
w
it
h
m
ax
i
m
u
m
o
f
-
4
.
4
0
%
er
r
o
r
an
d
m
in
i
m
u
m
o
f
-
0
.
1
2
%
er
r
o
r
as
s
h
o
w
n
in
T
ab
le
1
.
T
h
e
r
esu
lt
s
s
h
o
w
t
h
at
o
n
e
o
f
t
h
e
in
f
l
u
e
n
tial
f
ac
to
r
s
s
u
c
h
as
te
m
p
er
at
u
r
e
h
as
an
i
m
p
ac
t
o
n
th
e
d
e
m
a
n
d
f
o
r
ec
ast.
Fig
u
r
e
6
s
h
o
w
s
th
e
co
m
p
ar
is
o
n
o
f
f
o
r
ec
asted
d
em
a
n
d
b
y
co
n
v
e
n
tio
n
al
m
e
th
o
d
s
an
d
p
r
o
p
o
s
ed
A
NN
m
o
d
el.
T
h
e
A
NN
m
o
d
el
g
i
v
es
m
o
r
e
ac
cu
r
ate
p
r
ed
ictio
n
a
s
co
m
p
ar
ed
to
th
e
e
m
p
ir
ical
cu
r
v
e
f
itt
in
g
tech
n
i
q
u
e
an
d
also
i
t
ca
n
h
a
n
d
le
lar
g
e
n
u
m
b
er
o
f
n
o
n
-
lin
ea
r
lo
ad
d
ata
w
ith
ea
s
e.
U
s
i
n
g
th
e
s
a
m
e
tr
ain
in
g
f
ile
t
h
e
p
r
o
p
o
s
ed
A
NN
m
o
d
el
ca
n
f
o
r
ec
ast
th
e
d
ail
y
p
ea
k
d
em
a
n
d
f
o
r
co
m
p
lete
y
ea
r
.
T
ab
le
2
.
Ma
x
i
m
u
m
p
er
ce
n
ta
g
e
er
r
o
r
f
o
r
d
if
f
er
en
t
Neu
r
al
Net
w
o
r
k
s
tr
u
ct
u
r
e
S
L
N
o
N
e
u
r
a
l
N
e
t
w
o
r
k
S
t
r
u
c
t
u
r
e
M
a
x
i
m
u
m
%
Er
r
o
r
N
o
o
f
I
n
p
u
t
L
a
y
e
r
N
e
u
r
o
n
s (
)
N
o
o
f
H
i
d
d
e
n
l
a
y
e
r
N
e
u
r
o
n
s (
ℎ
)
N
o
o
f
O
u
t
p
u
t
l
a
y
e
r
N
e
u
r
o
n
s (
)
1
24
20
12
-
4
.
6
1
2
24
21
12
-
4
.
4
0
3
24
22
12
-
4
.
7
8
Fig
u
r
e
5
.
C
o
m
p
ar
is
o
n
o
f
ac
t
u
a
l &
f
o
r
ec
asted
lo
ad
cu
r
v
e
o
f
ANN
m
o
d
el
f
o
r
Ma
r
c
h
2
0
1
7
Fig
u
r
e
6
.
C
o
m
p
ar
is
o
n
o
f
co
n
v
en
tio
n
al
&
A
N
N
m
et
h
o
d
f
o
r
Ma
r
ch
2
0
1
7
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t 2
0
1
9
:
2
2
5
6
-
2263
2262
7.
CO
NCLU
SI
O
NS
T
h
e
co
n
v
en
tio
n
al
an
d
A
r
ti
f
ic
ial
Neu
r
al
Net
w
o
r
k
b
a
s
ed
ap
p
r
o
ac
h
h
as
b
ee
n
ap
p
lied
f
o
r
d
ail
y
p
ea
k
lo
ad
f
o
r
ec
asti
n
g
an
d
d
etailed
s
tu
d
y
h
a
s
b
ee
n
ca
r
r
ied
o
u
t
in
ter
m
s
o
f
tr
ai
n
i
n
g
a
n
d
test
i
n
g
t
h
e
n
e
u
r
al
n
et
w
o
r
k
w
it
h
h
is
to
r
ical
d
ail
y
p
ea
k
lo
ad
d
ata
p
er
tain
in
g
to
t
h
e
B
an
g
alo
r
e
E
lec
tr
icit
y
S
u
p
p
l
y
C
o
m
p
an
y
L
i
m
ited
.
T
h
e
A
NN
m
o
d
el
i
s
tr
ai
n
ed
b
y
v
ar
y
i
n
g
t
h
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
i
n
t
h
e
h
id
d
en
la
y
er
a
n
d
it
is
f
o
u
n
d
t
h
at
th
e
f
o
r
ec
asted
v
al
u
es
ar
e
in
g
o
o
d
ag
r
ee
m
en
t
w
it
h
t
h
e
ac
tu
al
v
alu
e
s
f
o
r
o
p
tim
a
l
n
e
u
r
o
n
s
.
T
h
e
A
NN
m
o
d
el
p
r
o
p
o
s
ed
in
t
h
e
p
r
ese
n
t
w
o
r
k
r
esu
lt
s
i
n
ac
c
u
r
ate
p
r
ed
ictio
n
o
f
d
ail
y
p
ea
k
lo
a
d
as
co
m
p
ar
e
d
to
ac
tu
al
d
e
m
a
n
d
.
T
h
e
co
n
v
e
n
tio
n
al
m
e
th
o
d
g
i
v
es
h
i
g
h
er
v
al
u
e
o
f
er
r
o
r
d
u
e
to
n
o
n
li
n
ea
r
b
eh
a
v
io
r
o
f
m
o
s
t
o
f
t
h
e
lo
ad
s
.
Hen
ce
th
e
p
r
o
p
o
s
ed
A
NN
m
o
d
el
g
iv
e
s
b
etter
r
esu
lt
s
in
co
m
p
a
r
is
o
n
w
ith
co
n
v
e
n
tio
n
a
l
m
et
h
o
d
s
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
Au
t
h
o
r
s
ar
e
g
r
atef
u
l
to
th
e
P
r
o
Vice
C
h
an
ce
llo
r
&
Ma
n
ag
e
m
e
n
t
o
f
Sch
o
o
l
o
f
E
n
g
i
n
ee
r
in
g
&
T
ec
h
n
o
lo
g
y
,
J
A
I
N
(
Dee
m
ed
-
to
-
be
-
U
n
iv
er
s
it
y
)
-
B
en
g
al
u
r
u
,
th
e
P
r
in
cip
al
&
Ma
n
a
g
e
m
en
t
o
f
Do
n
B
o
s
co
I
n
s
tit
u
te
o
f
T
ec
h
n
o
lo
g
y
,
B
en
g
alu
r
u
,
t
h
e
P
r
in
cip
al
&
Ma
n
a
g
e
m
en
t
o
f
M.
S.
R
a
m
aia
h
I
n
s
ti
t
u
t
e
o
f
T
ec
h
n
o
lo
g
y
,
B
en
g
al
u
r
u
,
f
o
r
th
e
ir
co
n
s
ta
n
t
s
u
p
p
o
r
t
an
d
e
n
co
u
r
ag
e
m
e
n
t
in
ca
r
r
y
in
g
o
u
t
t
h
is
r
e
s
ea
r
ch
w
o
r
k
a
n
d
t
h
e
B
E
SC
OM
&
Me
teo
r
o
lo
g
ical
c
en
ter
,
B
en
g
al
u
r
u
,
f
o
r
p
r
o
v
id
in
g
th
e
d
ata.
RE
F
E
R
E
NC
E
S
[1
]
L
o
a
d
G
e
n
e
ra
ti
o
n
Ba
lan
c
e
Re
p
o
rt
,
G
o
v
e
rn
m
e
n
t
o
f
In
d
ia,
M
i
n
istry
o
f
P
o
w
e
r,
Ce
n
tra
l
e
lec
tricity a
u
th
o
rity
,
2
0
1
6
-
1
7
.
[2
]
IEE
E
Co
m
m
it
tee
R
e
p
o
rt,
"
L
o
a
d
f
o
re
c
a
stin
g
b
ib
li
o
g
ra
p
h
y
"
.
IEE
E
T
ra
n
s.
o
n
Po
we
r
Ap
p
a
ra
t
u
s
S
y
ste
ms
,
v
o
l.
9
9
,
n
o
.
1
,
p
p
.
5
3
-
5
8
,
1
9
8
0
.
[3
]
Da
m
it
h
a
K.
Ra
n
a
we
e
ra
,
G
e
o
rg
e
G
.
Ka
r
a
d
y
,
Rich
a
rd
G.
F
a
rm
e
r.
"
Eco
n
o
m
ic
im
p
a
c
t
a
n
a
l
y
sis
of
lo
a
d
f
o
re
c
a
stin
g
,"
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Po
we
r S
y
st
e
ms
,
v
o
l.
1
2
,
n
o
.
3
,
p
p
.
1
3
8
8
-
1
3
9
2
,
1
9
7
7
.
[4
]
Ra
m
e
sh
Ku
m
a
r
V
.
,
P
ra
d
i
p
k
u
m
a
r
Dix
it
,
"
On
e
d
a
y
a
h
e
a
d
e
lec
tri
c
a
l
l
o
a
d
f
o
re
c
a
sti
n
g
u
sin
g
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
,"
2
nd
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
In
fo
rm
a
t
io
n
&
Co
mm
u
n
ica
ti
o
n
E
n
g
i
n
e
e
rin
g
(
IRD
In
d
i
a
)
;
v
o
l
.
2
,
n
o
.
1
,
p
p
.
9
-
12
,
A
u
g
2
0
1
3
.
[5
]
T
o
m
o
n
o
b
u
S
e
n
jy
u
,
Hito
sh
i
T
a
k
a
r
a
,
Ka
tsu
m
i
Ue
z
a
to
,
T
o
sh
ih
isa
F
u
n
a
b
a
sh
i
,
"
On
e
-
h
o
u
r
-
a
h
e
a
d
lo
a
d
f
o
re
c
a
stin
g
u
sin
g
n
e
u
ra
l
n
e
tw
o
rk
,"
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
P
o
we
r S
y
ste
ms
,
v
o
l.
17
,
n
o
.
1
,
p
p
.
1
1
3
-
1
1
8
,
F
e
b
2
0
0
2
.
[6
]
V
it
o
r
Hu
g
o
F
e
rre
ira,
A
lex
a
n
d
re
P
.
A
lv
e
s
d
a
S
il
v
a
,
"
T
o
wa
rd
e
stim
a
ti
n
g
a
u
to
n
o
m
o
u
s
n
e
u
ra
l
n
e
tw
o
rk
-
b
a
se
d
e
lec
tri
c
lo
a
d
f
o
re
c
a
ste
rs
,"
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
P
o
we
r S
y
ste
ms
,
v
o
l.
22
,
n
o
.
4
,
p
p
.
1
5
5
4
-
1
5
6
2
,
No
v
2
0
0
7
.
[7
]
Z.
A
.
Ba
sh
ir,
M
.
E.
El
-
Ha
w
a
r
y
,
"
A
p
p
ly
in
g
wa
v
e
lets
to
sh
o
rt
-
term
lo
a
d
f
o
re
c
a
stin
g
u
sin
g
p
so
-
b
a
se
d
n
e
u
ra
l
n
e
tw
o
rk
s
,"
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Po
we
r S
y
ste
ms
,
2
4
,
n
o
.
1
,
p
p
.
20
-
27
,
F
e
b
2
0
0
9
.
[8
]
Yin
g
Ch
e
n
,
P
e
ter
B.
L
u
h
,
Ch
e
Gu
a
n
,
Yig
e
Zh
a
o
,
L
a
u
re
n
t
D.
M
ich
e
l,
M
a
tt
h
e
w
A
.
Co
o
lb
e
th
,
P
e
ter
B.
F
ried
lan
d
a
n
d
S
tep
h
e
n
J.
Ro
u
rk
e
.
,
"
S
h
o
rt
-
term
l
o
a
d
f
o
re
c
a
stin
g
:
sim
il
a
r
d
a
y
-
b
a
s
e
d
w
a
v
e
let
n
e
u
ra
l
n
e
tw
o
rk
s
,"
IEE
E
T
ra
n
s
a
c
ti
o
n
s
o
n
P
o
we
r S
y
ste
ms
,
v
o
l.
25
,
n
o
.
1
,
p
p
.
3
2
2
-
330
,
F
e
b
2
0
1
0
.
[9
]
M
a
d
a
su
Ha
n
m
a
n
d
lu
,
Bh
a
v
e
sh
K
u
m
a
r
Ch
a
u
h
a
n
,
"
L
o
a
d
f
o
re
c
a
stin
g
u
sin
g
h
y
b
rid
m
o
d
e
ls
,
"
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Po
we
r S
y
ste
ms
,
v
o
l.
26
,
n
o
.
1
,
p
p
.
20
-
2
9
,
F
e
b
2
0
1
1
.
[1
0
]
Ni
Din
g
,
Clem
e
n
ti
n
e
Be
n
o
it
,
G
u
il
lau
m
e
F
o
g
g
ia,
Y
v
o
n
Be
sa
n
g
e
r
,
F
re
d
e
ric
W
u
rtz
,
"
Ne
u
ra
l
n
e
t
w
o
rk
-
b
a
se
d
m
o
d
e
l
d
e
sig
n
f
o
r
sh
o
rt
-
term
lo
a
d
f
o
re
c
a
st
in
d
istri
b
u
t
io
n
sy
st
e
m
s
,"
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
P
o
we
r
S
y
ste
ms
,
v
o
l.
31
,
n
o
.
1
,
p
p
.
72
-
81
,
Ja
n
2
0
1
6
.
[1
1
]
Yiz
h
e
n
g
X
u
,
Jo
v
ica
V
.
M
il
a
n
o
v
ic
,
"
Da
y
-
a
h
e
a
d
p
re
d
ictio
n
a
n
d
sh
a
p
in
g
o
f
d
y
n
a
m
ic
re
sp
o
n
se
o
f
d
e
m
a
n
d
a
t
b
u
lk
su
p
p
ly
p
o
i
n
ts
,"
IEE
E
T
ra
n
sa
c
ti
o
n
s o
n
P
o
we
r S
y
ste
ms
,
v
o
l.
31
,
n
o
.
4
,
p
p
.
3
1
0
0
-
3
1
0
8
,
Ju
l
2
0
1
6
.
[1
2
]
F
il
ip
R
o
d
rig
u
e
s,
C.
Ca
rd
e
ira,
J.
M
.
F
.
Ca
lad
o
,
"
T
h
e
d
a
il
y
a
n
d
h
o
u
rly
e
n
e
rg
y
c
o
n
su
m
p
ti
o
n
a
n
d
l
o
a
d
f
o
re
c
a
stin
g
u
sin
g
a
rti
f
icia
l
n
e
u
ra
l
n
e
t
w
o
rk
m
e
th
o
d
:
a
c
a
s
e
stu
d
y
u
sin
g
a
se
t
o
f
9
3
h
o
u
se
h
o
l
d
s
in
P
o
r
tu
g
a
l
,"
El
se
v
ier
.
v
o
l.
62
,
n
o
.
1
,
p
p
.
2
2
0
-
2
2
9
,
2
0
1
4
.
[1
3
]
A
n
a
m
i
k
a
S
in
g
h
,
V
.
Ku
m
a
r
T
rip
a
th
i
,
"
L
o
a
d
f
o
re
c
a
stin
g
u
sin
g
m
u
lt
i
-
la
y
e
r
p
e
rc
e
p
tro
n
n
e
u
ra
l
n
e
tw
o
rk
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
rin
g
S
c
ien
c
e
a
n
d
C
o
mp
u
ti
n
g
,
v
o
l.
6
,
n
o
.
5
,
p
p
.
5
4
6
3
-
5
4
6
6
,
M
a
y
2
0
1
6
.
[1
4
]
Ra
m
e
sh
Ku
m
a
r
V
,
P
ra
d
i
p
k
u
m
a
r
Dix
it
,
"
A
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
m
o
d
e
l
f
o
r
h
o
u
rly
p
e
a
k
lo
a
d
f
o
re
c
a
st,"
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
n
e
rg
y
Eco
n
o
mic
s
a
n
d
P
o
li
c
y
,
v
o
l.
8
,
n
o
.
5
,
p
p
.
1
5
5
-
1
6
0
,
S
e
p
2
0
1
8
.
[1
5
]
P
ra
d
ip
k
u
m
a
r
Dix
it
,
H
.
G
.
G
o
p
a
l
,
"
A
N
N
b
a
se
d
th
re
e
sta
g
e
c
las
si
f
i
c
a
ti
o
n
o
f
a
rc
g
r
a
d
ien
t
o
f
c
o
n
ta
m
i
n
a
ted
p
o
rc
e
lai
n
in
su
lato
rs,"
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
S
o
li
d
Die
lec
trics
,
Fra
n
c
e
,
v
o
l.
1
,
n
o
.
1
,
p
p
.
4
2
7
-
4
3
0
,
Ju
l
2
0
0
4
.
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:
2
0
8
8
-
8708
Da
ily
p
ea
k
lo
a
d
fo
r
ec
a
s
t u
s
in
g
a
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
k
(
R
a
mesh
K
u
ma
r
V
.
)
2263
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Ra
m
e
sh
K
u
m
a
r
V
r
e
c
e
i
v
e
d
th
e
B.
E.
d
e
g
re
e
in
El
e
c
tri
c
a
l
&
El
e
c
tr
o
n
ics
En
g
in
e
e
rin
g
a
n
d
M
.
E
d
e
g
re
e
in
P
o
w
e
r
&
En
e
rg
y
S
y
ste
m
s
f
ro
m
UV
CE
(Ba
n
g
a
lo
re
Un
iv
e
rsit
y
),
Be
n
g
a
lu
ru
,
I
n
d
ia,
in
2
0
0
1
a
n
d
2
0
0
4
,
re
sp
e
c
ti
v
e
ly
.
He
is
c
u
rre
n
tl
y
p
u
rsu
in
g
P
h
.
D.
a
t
JA
IN
(De
e
m
e
d
-
to
-
be
-
Un
iv
e
rsity
),
Be
n
g
a
lu
r
u
.
He
is
w
o
rk
in
g
a
s
A
s
sista
n
t
P
r
o
f
e
s
so
r
a
t
Do
n
Bo
sc
o
I
n
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
,
Be
n
g
a
lu
ru
.
His
re
se
a
rc
h
in
tere
st
is
in
th
e
a
re
a
o
f
A
rti
f
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
a
n
d
th
e
ir
a
p
p
li
c
a
ti
o
n
s
to
v
a
rio
u
s
P
o
w
e
r
S
y
ste
m
s
p
ro
b
lem
s.
Pra
d
i
p
k
u
m
a
r
Dix
it
re
c
e
iv
e
d
th
e
B.
E.
d
e
g
re
e
in
El
e
c
tri
c
a
l
a
n
d
E
lec
tro
n
ics
En
g
in
e
e
rin
g
i
n
1
9
8
9
f
ro
m
M
y
so
re
Un
iv
e
rsit
y
,
M
.
T
e
c
h
in
P
o
w
e
r
a
n
d
En
e
rg
y
S
y
ste
m
s
in
1
9
9
5
f
ro
m
M
a
n
g
a
lo
re
Un
iv
e
rsit
y
a
n
d
P
h
.
D.
in
Hig
h
V
o
lt
a
g
e
En
g
in
e
e
ri
n
g
in
2
0
0
9
f
ro
m
V
isv
e
s
v
a
ra
y
a
Tec
h
n
o
l
o
g
ica
l
Un
iv
e
rsit
y
,
Be
lag
a
v
i
.
He
is
c
u
rre
n
tl
y
w
o
rk
in
g
a
s
P
ro
f
e
s
so
r
in
El
e
c
tri
c
a
l
&
El
e
c
tro
n
ics
En
g
in
e
e
rin
g
De
p
a
rt
m
e
n
t
o
f
M
S
RIT
,
Be
n
g
a
lu
ru
.
His
a
re
a
s
o
f
in
tere
st
a
re
h
ig
h
v
o
lt
a
g
e
e
n
g
in
e
e
rin
g
,
o
u
td
o
o
r
i
n
su
lati
o
n
,
li
g
h
tn
i
n
g
p
ro
tec
ti
o
n
,
e
lec
tro
m
a
g
n
e
ti
c
c
o
m
p
a
ti
b
il
it
y
,
a
n
d
e
lec
tri
c
p
o
w
e
r
q
u
a
li
t
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.