Towards Intelligent Zone-Based Content Pre-Caching Approach in VANET for Congestion Control

. 2022 Nov 25;22(23):9157. doi: 10.3390/s22239157

Algorithm 3: Machine Learning-Based Content Pre-Caching

Input: Table 1, Algorithm 1,

V_{Z o R}

G e o c a s t N e t w o r k, D a t a_{t r a i n}

Output:

T a r g e t Z o R, M e s s a g e s D i s s i m i n a t i o n, N e t w o r k D e v e l o p m e n t

Steps:
Prepare Dataset
1.

Z_{i}

← Algorithm 1 ∴Get Zone from Algorithm 1
2.

Z O R_{i}

← Algorithm 2 ∴ZoR for dissemination from Algorithm 2
3.

D a t a_{V A N E T} \leftarrow (\begin{matrix} V i d e o, E m e r g y R o a d C o n d i t i o n s, t r a f f i c e \\ c o n d i t i o n s, C o n t r o l m e s s a g e s \end{matrix})

∴The originated data are captured and handled through the Manager
nodes with road and traffic conditions captured throughout every
incident vehicle.
4.

M N_{M}^{s t o r e} \leftarrow s t e p 3

∴Store data in the manager node from the real environment
5.

Initialize : V_{i \to j}^{0} & P_{i \to j}^{0}

∴Set initial velocity and position to the initial stage
Train Model
6. for

i = 1 t o D a t a_{t r a i n}

do ∴Set the training data for valuable variables
7. for

j = 1 t o N

do ∴Calculate the prediction value for every sample dataset
8.

c a l c u l a t e_e r r o r (p r e d i c t i o n V l a u e s)

∴Calculate the error
9.

i f (! s t e p 8)

10.

A p p l y (w e i g h t e d v a l u e s);

11.

M L_{V a n e t} \leftarrow T r a i n e d ()

12. End for
13. End for
14. Return:

M L_{M o d e l}^{p r e - c a c h e d} (T r a i n e d)

Test Model
15. Prepare:

D a t a_{T e s t i n g}^{p r e - c a c h e}

16. for

k = 1 t o M

do
17.

T e s t (D a t a_{T e s t i n g}^{p r e - c a c h e}) \leftarrow P r e d i c t i o n - R e s u l t s;

18.

C a p t u r e (\begin{matrix} p r e d i c t i o n a c c u r a c y, \\ a v e r a g e d e l a y, h i t r a t i o, t h r o u g h p u t \end{matrix});

19. End for
20. Return:

G r a p h i c a l R e s u l t s