Excitation system and method for cooperative computing of intelligent connected automobiles

By designing an incentive system for intelligent connected vehicles in intelligent connected vehicles, using points incentive mechanism and multi-model collaborative learning, the problem of low enthusiasm for idle vehicles to participate in task unloading is solved, and efficient utilization of computing resources and improvement of task unloading efficiency is achieved.

CN119728681AActive Publication Date: 2025-03-28EDGE INTELLIGENCE RES INST NANJING CO LTD
4 Cites 0 Cited by

Patent Information

Application Number
CN202411825935.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-12
Publication Date
2025-03-28
Estimated Expiration
2044-12-12

AI Technical Summary

Technical Problem

In intelligent connected vehicles, idle vehicles are not very enthusiastic about participating in task unloading, resulting in the inadequate use of surplus computing resources.

Method used

An incentive system for intelligent connected vehicles was designed. Through a three-layer architecture of the cloud server layer, the edge server layer and the vehicle layer, a points incentive mechanism was introduced to encourage vehicles to participate in task offloading, and the global correlation of decisions was enhanced through multi-model collaborative learning.

Benefits of technology

It improves the enthusiasm of vehicles to participate in task unloading, optimizes the allocation and utilization rate of computing resources, reduces the total cost of the system, and improves the efficiency of vehicle networking tasks unloading.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of combination of edge computing and artificial intelligence, and provides an excitation system and method oriented to cooperative computing of intelligent networked vehicles, which integrate computing resources of idle vehicles into a task unloading network of the Internet of Vehicles, perform cooperative computing by using the idle vehicles, further improve the resource utilization rate of the vehicles, and improve the resource utilization rate of the vehicles. The total cost of the system is effectively reduced; according to the method, the integral excitation system is introduced, the integral is used as a medium to quantify the unloading income, the unloading decision of a calculation task between idle vehicles can be guided, the enthusiasm of the idle vehicles to participate in task unloading is fully aroused, the configuration of calculation resources between the vehicles is optimized, and the task unloading efficiency of the Internet of Vehicles is improved; according to the method, multi-agent collaborative learning is fused into a cloud edge-end collaborative architecture, and an experience pool is arranged in a cloud server, so that global training samples can be comprehensively obtained, the global relevance of decision making is enhanced, and the model performance is further improved.
Need to check novelty before this filing date? Find Prior Art