Driving Assistant Server Selection Using Latency-Aware Workload Balancing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing driving assistant systems face workload imbalance among servers due to varying latency and processing capabilities, particularly when vehicles are concentrated in specific areas or have different distances from servers, leading to uneven server workloads and delayed responses.
Innovation Solution
A driving assistant device that adds latency information to data transmitted to servers, allowing for dynamic allocation of processing tasks based on required latency, ensuring that vehicles are controlled based on assistance information received from servers that meet latency requirements, thereby equalizing server workloads.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If processing is performed using multiple servers to handle multiple vehicles, then the number of accommodated vehicles increases, but server workload becomes uneven due to varying distances and processing capabilities
Solution Approach 1:
The system dynamically selects which server processes each vehicle's data based on real-time factors including distance from vehicle to server, server processing capability, and communication latency. This dynamic allocation prevents static workload imbalance by continuously adapting server assignments to current system conditions, ensuring efficient utilization of multiple servers while accommodating numerous vehicles.
Solution Approach 2:
The patent introduces latency information as a key parameter in server selection decisions. By considering communication latency alongside processing capability and distance, the system optimizes the balance between quick response times and efficient server utilization. This parameter-based selection mechanism allows the system to handle varying vehicle concentrations and server capacities effectively.
2Loss of time
If edge servers are used to reduce communication latency, then response time improves, but the number of vehicles that can be accommodated is limited
Solution Approach 1:
The system segments the server infrastructure into multiple servers with different characteristics (edge servers with low latency, cloud servers with high capacity). By dividing the processing workload across this segmented infrastructure and selectively assigning vehicles to appropriate servers, the system achieves both low latency for time-critical operations and high accommodation capacity for the overall vehicle fleet.
Solution Approach 2:
The patent creates a universal server selection mechanism that can accommodate both edge servers and cloud servers within the same system. The server selection process universally considers multiple factors (latency, capacity, distance) to determine optimal server assignment, allowing the system to flexibly utilize different server types for different vehicles based on their specific requirements rather than being constrained to a single server architecture.
3Loss of time
If servers are located close to vehicles to reduce latency, then response time improves, but server workload becomes concentrated in specific areas
Solution Approach 1:
The system applies local quality by allowing different regions to utilize different server configurations based on their specific needs. Areas with high vehicle concentration can leverage local edge servers for low-latency responses, while other areas can utilize cloud servers. The server selection process considers the local context including vehicle density, distance to servers, and regional processing requirements, creating optimized local solutions rather than forcing a uniform architecture.
Data Source
AI summary
An assistant device according to the present disclosure includes a memory, and a hardware processor coupled to the memory. The hardware processor being configured to: add latency information indicating required latency to data that is transmitted to a server of a plurality of servers via a communication line and used for an assistance process performed by the server; transmit data for external processing to which the latency information is added, and receive assistance information including a processing result of the server based on the data for external processing; and control a vehicle based on the assistance information.