Energy-efficient optimized computing offloading method for vehicular edge computing network and system thereof
The present disclosure relates to an energy-efficient optimized computing offloading method for a vehicular edge computing network and a system thereof; the method comprises: calculating the energy efficiency cost EEC of local computing; calculating the energy efficiency cost EEC of mobile edge computing; determining an optimal offloading decision based on the energy efficiency cost of local computing and the energy efficiency cost of mobile edge computing; determining an optimal CPU frequency and an optimal transmit power of the vehicle based on the optimal offloading decision; and determining the optimal offloading time of the vehicle based on the optimal CPU frequency and the optimal transmit power of the vehicle. The method of the present disclosure can improve the computing offloading efficiency.
1. An energy-efficient optimized computing offloading method for a vehicular edge computing network, comprising:
calculating an energy efficiency cost EEC of local computing, wherein the calculating comprises:
calculating a local computing latency;
determining an energy consumption of local computing based on the local computing latency; and
determining an energy efficiency cost EEC of local computing based on the energy consumption and the local computing latency;
calculating an energy efficiency cost EEC of mobile edge computing, wherein the calculating comprises:
calculating a distance between a vehicle n and a base station BS;
determining a channel gain between the vehicle n and the base station based on the distance;
determining a real-time transmission rate from the vehicle n to the base station based on the channel gain;
determining a task offloading time based on the real-time transmission rate;
calculating a computing time of an MEC server;
determining a total latency of mobile edge computing based on the task offloading time and the computing time of the MEC server;
calculating an energy consumption of mobile edge computing; and
determining the energy efficiency cost EEC of mobile edge computing based on the energy consumption of mobile edge computing and the total latency of mobile edge computing;
determining an optimal offloading decision based on the energy efficiency cost of local computing and the energy efficiency cost of mobile edge computing, wherein the determining adopts the following formula:
a
n
*
=
{
1
,
if
Cost
n
o
<
Cost
n
l
&
T
n
o
<
c
n
0
,
otherwise
where a* n represents the optimal offloading decision,
c
n
=
△
R
max
2
-
D
2
-
x
n
v
n
represents a maximum communication time between the vehicle and the base station, R max represents a maximum communication coverage of the base station BS, D represents a vertical distance between the base station and a road, x n represents an initial position of the vehicle n on the road, v n represents a moving speed of the vehicle
n
,
Cost
n
l
=
△
Z
n
l
+
λ
n
L
n
C
n
f
n
l
represents a computing cost of local computing,
Cost
n
o
=
△
Z
n
o
+
λ
n
(
t
n
ot
+
L
n
C
n
f
MEC
)
represents a computing cost of mobile edge computing, λ n represents a Lagrange multiplier corresponding to the latency constraint (1−a n )T n l +a n T n o ≤T n,max , a n represents a decision variable, T n,max represents a maximum tolerable latency, L n represents a data size of a task R n , C n represents the computational complexity of the task R n , f n l represents a computing speed of the vehicle n, T n l represents the local computing latency, T n o represents the total latency of mobile edge computing, Z n o represents the energy efficiency cost EEC of mobile edge computing, and Z n l represents the energy efficiency cost EEC of local computing;
determining an optimal CPU frequency and an optimal transmit power of the vehicle based on the optimal offloading decision, where the determining comprises:
when a* n =0, determining the optimal CPU frequency of the vehicle by the following formula:
f
n
l
*
=
{
β
n
T
+
λ
n
2
β
n
E
k
3
,
if
0
≤
β
n
T
+
λ
n
2
β
n
E
k
3
≤
f
n
,
max
l
f
n
,
max
l
,
otherwise
where f n,max l represents a maximum CPU frequency of the vehicle n, f n l *-represents the optimal CPU frequency of the vehicle, β n T represents a latency weight parameter, λ n represents a Lagrange multiplier corresponding to a latency constraint, β n E represents an energy consumption weight factor, and k represents an effective switched capacitor coefficient,
when a* n =1, determining the optimal transmit power of vehicle n by the following formula:
p
n
*
=
{
0
,
if
p
^
n
<
0
p
^
n
,
if
0
≤
p
^
n
≤
p
n
,
max
p
n
,
max
,
if
p
^
n
>
p
n
,
max
where p n,max represents a maximum transmit power of the vehicle n, {circumflex over (p)} n is the unique solution of the equation β n E t n ot −χ n φ′(p n ,t n ot )=0, χ n represents a Lagrange multiplier corresponding to the constraint
a
n
L
n
≤
φ
(
p
n
,
T
n
ot
)
,
φ
(
p
n
,
t
n
ot
)
=
Δ
∫
0
t
n
ot
r
n
(
τ
)
d
τ
,
φ
′
(
p
n
,
t
n
ot
)
=
Δ
∂
φ
(
p
n
,
t
n
ot
)
∂
p
n
,
t
n
ot
represents a task transmission time, p n >0 represents a transmit power of the vehicle n, and r n (t) represents a real-time transmission rate from the vehicle n to the base station;
determining an optimal offloading time of the vehicle based on the optimal CPU frequency and the optimal transmit power of the vehicle, wherein determining the optimal offloading time comprises:
determining the cost function; wherein the cost function is the energy efficiency cost function for the vehicle to complete the computing task, and wherein determining the cost function adopts the following formula:
ζ
(
t
n
ot
)
=
∑
n
=
1
N
{
β
n
T
[
(
1
-
a
n
*
)
L
n
C
n
f
n
l
*
+
a
n
*
(
t
n
ot
+
L
n
C
n
f
MEC
)
]
+
β
n
E
[
(
1
-
a
n
*
)
kL
n
C
n
(
f
n
l
*
)
2
+
a
n
*
p
n
*
t
n
ot
]
}
;
where β n E represents an energy consumption weight factor, p* n represents the optimal transmit power of vehicle, and f MEC represents a computing capacity of the MEC server; and
determining the optimal offloading time of the vehicle using a one-dimensional linear search method based on the cost function.
2. The energy-efficient optimized computing offloading method for a vehicular edge computing network according to claim 1 ,
wherein calculating the local computing latency adopts the following formula:
T
n
l
=
L
n
C
n
f
n
l
where f n l represents a CPU frequency of the vehicle n, L n represents a data size of the task R n , and C n represents a computational complexity of the task R n ;
wherein determining the energy consumption of local computing based on the local computing latency adopts the following formula:
E n l =kT n l ( f n l ) 3 =kL n C n ( f n l ) 2
where k represents effective switching capacitance coefficient, T n l represents the local computing latency, f n l represents the CPU frequency of the vehicle n, L n represents the data size of the task R n , and C n represents the computational complexity of the task R n ; and
wherein determining the energy efficiency cost EEC of local computing based on the energy consumption and latency of local computing adopts the following formula:
Z n l =β n T T n l +β n E E n l
where 0≤β n T ≤1 and 0≤β n E ≤1 represent weight factors of latency and energy consumption, respectively, T n l represents the latency of local computing, and E n l represents the energy consumption of local computing.
3. The energy-efficient optimized computing offloading method for a vehicular edge computing network according to claim 1 ,
wherein calculating the distance between the vehicle n and the base station BS adopts the following formula:
d
n
(
t
)
=
H
2
+
D
2
+
(
x
n
+
v
n
t
)
2
where H represents an antenna height of the base station, D represents the vertical distance between the base station and the road, x n represents the initial position of the vehicle n on the road, and v n represents the moving speed of the vehicle n;
wherein determining the channel gain between the vehicle n and the base station based on the distance adopts the following formula:
G
n
(
t
)
=
β
0
d
n
(
t
)
-
θ
=
β
0
[
H
2
+
D
2
+
(
x
n
+
v
n
t
)
2
]
θ
2
where β 0 represents a gain at a reference distance d 0 =1 m, and θ represents a path loss factor of a V2I link;
wherein determining the real-time transmission rate from the vehicle n to the base station based on the channel gain adopts the following formula:
r
n
(
t
)
=
W
log
2
(
1
+
p
n
G
n
(
t
)
σ
2
)
=
W
log
2
(
1
+
p
n
ρ
0
[
H
2
+
D
2
+
(
x
n
+
v
n
t
)
2
]
θ
2
)
where W represents a channel bandwidth, p n >0 represents the transmit power of the vehicle n, ρ 0 =β 0 /σ 2 , σ 2 represents a noise power of a BS receiver, and G n (t) represents the channel gain between the vehicle n and the base station;
wherein determining task offloading time based on the real-time transmission rate adopts the following formula:
∫ 0 t n ot r n ( t ) dt=L n
where t n ot represents the task offloading time, L n represents the data size of the task R n , and r n (t) represents the real-time transmission rate from the vehicle n to the base station;
wherein calculating the computing time of the MEC server adopts the following formula:
t
n
oe
=
L
n
C
n
f
MEC
where f MEC represents the computing capacity of the MEC server, and C n represents the computational complexity of the task R n ;
wherein determining the total latency of mobile edge computing based on the task offloading time and the computing time of the MEC server adopts the following formula:
T n o =t n ot +t n oe
where t n oe represents the computing time of the MEC server, and t n ot represents the task offloading time;
wherein calculating the energy consumption of mobile edge computing adopts the following formula:
E n o =p n t n ot ; and
wherein determining the energy efficiency cost EEC of mobile edge computing based on the energy consumption of mobile edge computing and the total latency of mobile edge computing adopts the following formula:
Z n o =β n T T n o +β n E E n o
where T n o represents the total latency of mobile edge computing, E n o represents the energy consumption of mobile edge computing, β n T represents a latency weight factor, and β n E represents the energy consumption weight factor.
4. The energy-efficient optimized computing offloading method for a vehicular edge computing network according to claim 1 , wherein
determining the optimal offloading time of the vehicle using a one-dimensional linear search method based on the cost function adopts the following formula:
min
f
n
ot
ζ
(
t
n
ot
)
s
.
t
.
0
≤
t
n
ot
≤
c
n
where c n represents the maximum communication time between the vehicle and the BS, t n ot represents the task offloading time, and ζ(t n ot ) represents the energy efficiency cost function for the vehicle to complete the calculation task.
5. An energy-efficient optimized computing offloading system in a vehicular edge computing network, the system comprising:
a module for calculating energy efficiency cost of local computing, which is configured to:
calculate a local computing latency;
determine an energy consumption of local computing based on the local computing latency; and
determine the energy efficiency cost EEC of local computing based on the energy consumption of local computing;
a module for calculating energy efficiency cost of mobile edge computing, which is configured to:
calculate a distance between a vehicle n and a base station BS;
determine a channel gain between the vehicle n and the base station based on the distance;
determine a real-time transmission rate from the vehicle n to the base station based on the channel gain;
determine task offloading time based on the real-time transmission rate;
calculate a computing time of an MEC server;
determine a total latency of mobile edge computing based on the task offloading time and the computing time of the MEC server;
calculate an energy consumption of mobile edge computing; and
determine the energy efficiency cost EEC of mobile edge computing based on the energy consumption of mobile edge computing and the total latency of mobile edge computing;
an optimal offloading decision determining module, which is configured to:
determine an optimal offloading decision based on the energy efficiency cost of local computing and the energy efficiency cost of mobile edge computing according to the following formula:
a
n
*
=
{
1
,
if
Cost
n
o
<
Cost
n
l
&
T
n
o
<
c
n
0
,
otherwise
where a* n represents the optimal offloading decision,
c
n
=
Δ
R
max
2
-
D
2
-
x
n
v
n
represents a maximum communication time between the vehicle and the base station, R max represents a maximum communication coverage of the base station BS, D represents a vertical distance between the base station and a road, x n represents an initial position of the vehicle n on the road, v n represents a moving speed of the vehicle n,
Cost
n
l
=
Δ
Z
n
l
+
λ
n
L
n
C
n
f
n
l
represents a computing cost of local computing,
Cost
n
o
=
Δ
Z
n
o
+
λ
n
(
t
n
ot
+
L
n
C
n
f
MEC
)
represents a computing cost of mobile edge computing, λ n represents a Lagrange multiplier corresponding to the latency constraint (1−a n )T n l +a n T n o ≤T n,max , a n represents a decision variable, T n,max represents a maximum tolerable latency, L n represents a data size of the task R n , C n represents a computational complexity of the task R n , f n l represents a computing speed of the vehicle n, T n l represents the local computing latency, T n o represents the total latency of mobile edge computing, Z n o represents the energy efficiency cost EEC of mobile edge computing, and Z n l represents the energy efficiency cost EEC of local computing;
an optimal CPU frequency and optimal transmit power determining module, which is configured to:
determine an optimal CPU frequency and an optimal transmit power of the vehicle based on the optimal offloading decision, wherein:
when a* n =0, determine the optimal CPU frequency of the vehicle by the following formula:
f
n
l
*
=
{
β
n
T
+
λ
n
2
β
n
E
k
3
,
if
0
≤
β
n
T
+
λ
n
2
β
n
E
k
3
≤
f
n
,
max
l
f
n
,
max
l
,
otherwise
where f n,max l represents a maximum CPU frequency of the vehicle n, f n l * represents the optimal CPU frequency of the vehicle, β n T represents a latency weight parameter, λ n represents a Lagrange multiplier corresponding to a latency constraint, β n E represents an energy consumption weight factor, and k represents an effective switched capacitor coefficient;
when a* n =1, determine the optimal transmit power of vehicle n by the following formula:
p
n
*
=
{
0
if
p
n
^
<
0
p
n
^
,
if
0
≤
p
n
^
≤
p
n
,
max
p
n
,
max
,
if
p
n
^
>
p
n
,
max
where p n,max represents a maximum transmit power of the vehicle n, {circumflex over (p)} n is a unique solution of the equation β n E t n ot −χ n φ′(p n , t n ot )=0, χ n represents a Lagrange multiplier corresponding to the constraint a n L n ≤φ(p n , T n ot ), φ(p n , t n ot ) ∫ 0 t n ot r n (τ)dτ,
φ
′
(
p
n
,
t
n
ot
)
=
Δ
∂
φ
(
p
n
,
t
n
ot
)
∂
p
n
,
t n ot represents a task transmission time, p n >0 represents a transmit power of the vehicle n, and r n (t) represents a real-time transmission rate from the vehicle n to the base station;
an optimal offloading time determining module, which is configured to:
determine the optimal offloading time of the vehicle based on the optimal CPU frequency and the optimal transmit power of the vehicle;
determine the cost function, wherein the cost function is the energy efficiency cost function for the vehicle to complete the calculation task, and wherein determining the cost function adopts the following formula:
ζ
(
t
n
ot
)
=
∑
n
=
1
N
{
β
n
T
[
(
1
-
a
n
*
)
L
n
C
n
f
n
l
*
+
a
n
*
(
t
n
ot
+
L
n
C
n
f
MEC
)
]
+
β
n
E
[
(
1
-
a
n
*
)
kL
n
C
n
(
f
n
l
*
)
2
+
a
n
*
p
n
*
t
n
ot
]
}
;
where β n T represents a latency weight factor, p* n represents the optimal transmit power of the vehicle, and f MEC represents a computing capacity of the MEC server; and
determine the optimal offloading time of the vehicle using a one-dimensional linear search method based on the cost function.