Cloud Application Service Processing for Low-Delay Edge Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge of efficiently allocating edge servers to user terminals in cloud applications, such as cloud gaming, to ensure low network delay and high network stability, is not adequately addressed by existing methods that focus on single dimensions, leading to potential server overload or underutilization during peak usage.
Innovation Solution
A cloud application management system that evaluates multiple dimensions of edge servers, including network quality, resource availability, and operation cost, to determine a connection reference score, ensuring that only appropriate servers are allocated to user terminals, balancing server load and user experience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple edge servers are deployed to serve more users, then network coverage and user accessibility are improved, but server allocation complexity and load balancing difficulty increase
Solution Approach 1:
The system continuously monitors network quality, server load, and user terminal states, using this feedback to dynamically adjust edge server allocations. The management server receives real-time data from edge servers and terminals, processes this information through the scoring mechanism, and reallocates resources accordingly, creating a closed-loop control system that adapts to changing conditions.
Solution Approach 2:
The patent transforms the complex multi-dimensional allocation problem into a simplified scoring system where multiple parameters (network quality, server load, user terminal performance) are converted into a single connection reference score. This parameter transformation enables straightforward comparison and selection of optimal edge servers without managing complex multi-parameter optimization.
2Speed
If edge servers are allocated based on single dimension (e.g., closest distance), then allocation speed is improved, but allocation accuracy and service quality deteriorate
Solution Approach 1:
The patent creates a composite evaluation index (connection reference score) that integrates multiple dimensions including network quality, server load, and terminal performance into a single comprehensive metric. This composite approach combines the advantages of multiple allocation criteria while maintaining computational efficiency, enabling fast yet accurate server selection.
Solution Approach 2:
The system adds multiple evaluation dimensions (network quality, server load, terminal score) to the traditional single-dimension allocation approach. By transforming the allocation criterion from a single parameter to a multi-dimensional scoring system, the patent achieves both speed and accuracy through efficient score calculation and comparison.
3Ease of operation
If edge servers are allocated without comprehensive evaluation, then allocation simplicity is maintained, but server overload and resource underutilization occur
Solution Approach 1:
The system enables edge servers to self-evaluate their suitability for serving specific terminals through the scoring mechanism. Each edge server's characteristics (network quality, current load, resources) are automatically assessed and converted into a connection reference score, eliminating the need for manual allocation decisions while ensuring balanced resource distribution.
Solution Approach 2:
The patent performs preliminary evaluation of edge servers by pre-calculating connection reference scores based on current server states and user terminal characteristics. This advance assessment allows the system to make informed allocation decisions before actual service delivery, preventing server overload and ensuring optimal resource utilization from the outset.
4Measurement precision
If comprehensive multi-dimensional evaluation is performed for edge server allocation, then allocation accuracy and service quality are improved, but computational complexity and processing time increase
Solution Approach 1:
The patent divides the comprehensive evaluation process into separate, independently calculable components: network quality assessment, server load evaluation, and terminal performance scoring. Each component can be calculated separately and then combined into the final connection reference score, reducing computational complexity while maintaining evaluation comprehensiveness.
Data Source
AI summary
A service processing method, performed by a cloud application management server, includes: upon receiving an allocation request from a target terminal, acquiring N pieces of selection reference information corresponding to a pending edge server and related to the target terminal and running reference information, the pending edge server being one of P edge servers connected to the cloud application management server; upon determining that the pending edge server meets a requirement of providing a running service of a target cloud application for the target terminal, determining a connection reference score corresponding to the pending edge server; storing the connection reference score and identification information about the pending edge server into a candidate set; and transmitting the candidate set to the target terminal.