Service Chain Placement Using Mobility Pattern Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Optimal service chain placement in mobile computing systems is challenging due to dynamic and heterogeneous infrastructure, time-sensitive services, and high costs associated with frequent migrations of service components, which existing solutions fail to address effectively, especially in scenarios involving advanced driver assistance systems and augmented reality.
Innovation Solution
A hybrid descriptive and analytical model that uses multi-attribute utility theory to compute the benefits of possible placement solutions, integrating mobility patterns and cost considerations to pre-place service components closer to mobile resources, thereby optimizing service chain placement and minimizing disruptions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If service components are frequently migrated to follow mobile resources, then service quality and latency are improved, but operational costs and system complexity increase significantly
Solution Approach 1:
The system performs pre-computation of optimal service chain placements using a hybrid descriptive and analytical model that incorporates mobility patterns. By calculating and preparing placement decisions in advance, the system can proactively migrate service components before mobile resources move, ensuring continuous service quality without reactive frequent migrations that increase complexity
Solution Approach 2:
The system dynamically adapts service chain placements based on predicted mobility patterns of mobile resources. The hybrid model continuously updates placement decisions according to changing mobility characteristics, allowing the system to optimize for reliability while adapting to dynamic conditions without requiring excessive complexity
2Loss of time
If service components are migrated frequently to maintain optimal placement, then latency is reduced, but operational costs increase
Solution Approach 1:
The system pre-computes optimal service chain placements by analyzing mobility patterns and predicting future positions of mobile resources. This allows the system to perform migrations proactively at optimal moments rather than reactively, reducing the frequency of migrations while maintaining low latency, thereby lowering operational costs
Solution Approach 2:
The hybrid descriptive and analytical model changes the parameters used for placement decisions by incorporating mobility pattern analysis. Instead of making placement decisions based solely on current positions, the system uses predicted future positions and mobility characteristics to determine optimal migration timing, reducing unnecessary migrations and associated costs
3Ease of manufacture
If existing service chain placement solutions are used, then implementation is simpler, but they fail to address time-sensitive services in mobile scenarios effectively
Solution Approach 1:
The system segments the service chain into multiple components that can be independently placed and managed. The hybrid model evaluates placement options for different service chain components separately, allowing for targeted optimization of time-sensitive services while maintaining a manageable implementation structure through modular decision-making
Data Source
AI summary
There is disclosed in one example a computing apparatus, including: a hardware platform; and a service chain pre-placement analyzer to operate on the hardware platform and configured to: receive a total utility input for a service chain placement; predict a mobility pattern for the service chain placement; and compute an average utility for the service chain placement, wherein the average utility is a product of the total utility and the mobility pattern.