| Autor: |
Grishina, L. S., Zhigalov, A. Yu., Parfenov, D. I., Bolodurina, I. P., Legashev, L. V. |
| Předmět: |
|
| Zdroj: |
AIP Conference Proceedings; 2023, Vol. 2700 Issue 1, p1-7, 7p |
| Abstrakt: |
Within the framework of this work, a hybrid model has been developed for the efficient placement of initial and intermediate data in wireless transport networks with a dynamic VANET topology, using a structural representation of software-defined networks and tools for conducting edge calculations. In addition, an RD algorithm has been developed - a protocol for transferring and processing intermediate data. To carry out clustering of the vehicles on the network segment, the unsupervised learning method DBSCAN was used. A preliminary analysis of abnormal traffic was carried out based on RNN neural network models with short-term memory. The results of the experiments showed that the hybrid model with edge computing has the lowest average network latency, which confirms the high efficiency of the proposed approach and the need to implement and scale the presented model in practice. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
