Redundant VNF Mode Switching to Prevent Dual Active States
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network function virtualization (NFV) technologies face challenges in ensuring high availability and reliability due to communication disconnections between redundant virtual network functions (VNFs) or high availability controllers (HACs), leading to dual active or dual standby states and service disruptions.
Innovation Solution
A deep learning model is employed to predict and determine the operation mode of redundant VNFs, using information such as resource usage and packet data, to prevent dual states and ensure high availability by adaptively switching between active and standby modes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If redundant VNFs are deployed to ensure high availability, then service reliability is improved, but communication disconnections between redundant VNFs or HACs may occur leading to dual active or dual standby states
Solution Approach 1:
The patent implements a feedback mechanism where the HAC continuously monitors the operation modes of redundant VNFs and receives state information from them. When a state change is detected or predicted through deep learning analysis, the HAC sends control signals to adjust the operation modes, ensuring that only one VNF remains in active mode at any time. This closed-loop feedback system prevents dual active or dual standby states by continuously verifying and correcting the system state.
Solution Approach 2:
The patent employs deep learning models to perform preliminary analysis of VNF state information and predict potential state changes before they occur. By analyzing historical and real-time data, the system can anticipate failures or state transitions and proactively adjust the operation modes of redundant VNFs, preventing communication disconnections and dual states before they manifest, thereby maintaining service continuity.
2Measurement precision
If deep learning model is used to predict VNF states, then determination accuracy is improved, but system complexity increases
Solution Approach 1:
The patent introduces a deep learning model as an intermediary component that sits between the VNFs/HAC and the operation mode determination logic. This intermediary collects and analyzes state information from multiple sources, processes it through trained neural networks, and outputs predictions that guide the HAC's decisions. By delegating the complex analysis to the deep learning model, the system achieves high determination accuracy while keeping the core control logic relatively simple and modular.
Data Source
AI summary
A method performed by a network device in a communication system, includes: identifying information related to a first virtual network function (VNF); identifying a first operation mode of the first VNF; and determining a second operation mode of the first VNF, based on the information related to the first VNF and a deep learning model; and determining a third operation mode of the first VNF, based on the second operation mode of the first VNF and the first operation mode of the first VNF. The first VNF is redundant with a second VNF. The third operation mode is either an active mode or a standby mode.