VNF State Scaling via Probabilistic Trajectory Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network function virtualization (NFV) technologies face challenges in scaling virtual network functions (VNFs) to support mission-critical use cases involving mobile wireless devices, particularly in maintaining ultra-low latency and ultra-high reliability while handling sporadic and low-bandwidth Machine-Type Communications (MTC) traffic, and in efficiently managing the VNF state across multiple Points-of-Presence (PoPs) without introducing significant latency or resource overhead.
Innovation Solution
The method involves proactively scaling the VNF state to potential PoPs based on probabilistic estimates of the mobile device's trajectory, using a VNF state scaling manager to pre-process and fragment state information for efficient assembly at downstream PoPs, thereby maintaining state consistency and reducing latency and resource consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the VNF state is scaled to multiple PoPs to support mobile WDs, then the service continuity and reliability are improved, but the network resource consumption and system complexity increase
Solution Approach 1:
The VNF state is segmented into multiple state fragments that can be independently managed and distributed across different PoPs. This segmentation allows the system to maintain state information in a distributed manner without requiring complex coordination between PoPs, thus improving service continuity while managing system complexity.
Solution Approach 2:
The VNF state fragments are proactively scaled to candidate PoPs before the WD actually moves to those locations. This preliminary action ensures that state information is already available at the destination PoP when the WD arrives, enabling seamless service continuity without requiring complex real-time state synchronization mechanisms.
2Loss of time
If the VNF state is scaled proactively to candidate PoPs, then the handover latency is reduced, but the network resource consumption increases
Solution Approach 1:
Instead of scaling the complete VNF state to all possible candidate PoPs, the system scales only partial state fragments to selected candidate PoPs based on probabilistic trajectory estimates. This partial action approach reduces network resource consumption while still achieving low handover latency for the most likely migration paths.
Solution Approach 2:
The system dynamically adjusts the scaling parameters (which state fragments to scale, to which PoPs, and when) based on changing conditions such as WD trajectory predictions, network resource availability, and mobility patterns. This allows optimization of the trade-off between handover latency and resource consumption.
3Productivity
If the VNF state is fragmented and pre-processed for scaling, then the assembly efficiency at downstream PoPs is improved, but the initial processing complexity increases
Solution Approach 1:
The VNF state is divided into standardized state fragments with well-defined structures and interfaces. This segmentation enables efficient parallel processing and distribution of fragments to multiple PoPs, improving assembly efficiency at downstream locations while the standardization manages the initial processing complexity.
Solution Approach 2:
The state fragment structure is designed to be universal and reusable across different VNF types and migration scenarios. This universality allows the same fragmentation and assembly mechanisms to handle various cases, improving efficiency while avoiding the need for complex custom processing logic for each scenario.
4Reliability
If the VNF supports mission-critical use cases with ultra-low latency requirements, then the service quality is improved, but the system resource requirements increase
Solution Approach 1:
The system provides different levels of state replication and processing capability at different PoPs based on local requirements and resource availability. PoPs serving mission-critical applications receive prioritized state fragments and allocate sufficient resources for ultra-low latency processing, while other PoPs use standard configurations, thus achieving high service quality where needed without universally increasing resource requirements.
Data Source
AI summary
A method and apparatus for scaling a VNF on a first PoP associated with at least one wireless device (WD) to a second PoP. A probabilistic estimate of a likelihood that the WD(s) will be handed over to at least one candidate PoP is generated and a VNF state associated with such candidate(s) is scaled and populated with state context information related to a handover of the WD(s) from the first PoP to the candidate(s). The second PoP is identified from the candidate(s) prior to handover using the probabilistic estimate. Thereafter the VNF is scaled from the first PoP to the second PoP, followed by handover of the WD(s) from the first PoP to the second PoP.