Vertical handoff algorithm based on implicit naive Bayes classification method under internet of vehicles environment

Abstract

The invention relates to a vertical handoff algorithm based on an implicit naive Bayes classification method under internet of vehicles environment. The algorithm sufficiently considers the dependencyrelation between the prior network attributes, the contact between the network handoff judgment variables is considered, the performance reduction caused by the attribute condition independent assumption in the naive Bayes classification method is weakened, and the complexity of the original algorithm is maintained at the same time. A speed self-adaptive condition weighting probability is imported, so that the algorithm better considers the influence on the network performance by the speed, thereby better adapting to continuously changed speed of the vehicle node. Compared with the original algorithm based on the naive Bayes decision, the algorithm improves the handoff efficiency, and reduces the Ping-Pong effect produced in the handoff; and meanwhile, the speed of the vehicle node can beself-adaptively matched, the network not meeting the speed can be evaded, and the condition of accessing to the network with unmatched speed is avoided.

Description

technical field [0001] The invention belongs to the technical field of Internet of Vehicles, and more particularly, relates to an adaptive vertical switching algorithm based on a hidden naive Bayesian classification method in the Internet of Vehicles environment. Background technique [0002] The uninterrupted connection between the vehicle and the network is a key issue in the research related to the Internet of Vehicles. The network connection directly determines whether the vehicle nodes can obtain the relevant information in a timely and accurate manner in the Internet of Vehicles. How to maintain a stable, efficient and safe transportation network appears especially important. [0003] Vehicle nodes have the characteristics of high speed, fast change, strong randomness, etc. Some network characteristics are difficult to meet the connection, resulting in too short connection time of communication link, or even interruption of connection, resulting in unbalanced network l...

AI Technical Summary

Problems solved by technology

[0003] Vehicle nodes have the characteristics of high speed, fast change, and strong randomness. Some network characteristics are also difficult to meet the connection, resulting in too short connection time for communication links, and even connection interruptions, resulting in unbalanced network loads and other phenomena.

Images