Mesh Network Clock Syntonization with Probe-Based Drift Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current clock synchronization methods in networked systems, such as data centers and distributed ledgers, face limitations in achieving nanosecond-level accuracy due to frequency drift caused by environmental factors, leading to inefficiencies and fairness issues in transaction processing, and require expensive specialized hardware.
Innovation Solution
A system and method for improving clock synchronization accuracy by continuously estimating and adjusting for both offset and frequency drift using advanced filtering techniques and machine learning models, allowing for precise synchronization of commodity clocks without additional hardware, ensuring clocks remain within specific bounds of synchronization error.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If specialized hardware is used throughout the network for clock synchronization, then nanosecond-level accuracy is achieved, but device complexity and cost increase significantly
Solution Approach 1:
The patent replaces specialized hardware clock synchronization systems with a software-based solution using commodity clocks. The invention uses software algorithms including adaptive filtering and machine learning models to achieve nanosecond-level synchronization accuracy without requiring specialized hardware components throughout the network.
Solution Approach 2:
The invention enables the use of inexpensive commodity clocks instead of expensive specialized hardware. By applying software-based frequency drift correction and adaptive filtering to standard off-the-shelf clock components, the system achieves high precision synchronization at significantly lower cost.
2Device complexity
If millisecond-level synchronization algorithms are used, then device complexity is reduced, but clock synchronization accuracy deteriorates to millisecond-level
Solution Approach 1:
The patent implements dynamic frequency drift correction by continuously monitoring and adjusting clock frequencies in real-time. The system uses adaptive filtering that dynamically adapts to changing environmental conditions and clock behavior, allowing commodity clocks to maintain nanosecond-level synchronization without specialized hardware.
Solution Approach 2:
The invention employs feedback mechanisms where clock synchronization performance is continuously monitored and used to adjust frequency drift corrections. Machine learning models analyze synchronization errors and feed back adjustment parameters to maintain accurate timing, enabling high precision with standard hardware.
3Device complexity
If clock frequency drift is not corrected, then device complexity remains low, but clock synchronization reliability deteriorates due to frequency drift from environmental factors
Solution Approach 1:
The patent implements self-service frequency drift correction where each clock system autonomously monitors its own frequency drift and applies corrections using locally computed adjustment parameters. The system automatically adapts to environmental changes without external intervention, maintaining reliable synchronization through self-correction mechanisms.
Solution Approach 2:
The invention dynamically changes clock frequency parameters to compensate for environmental drift. By continuously adjusting frequency offset parameters based on monitored conditions and machine learning predictions, the system maintains reliable synchronization despite temperature and other environmental variations.
Data Source
AI summary
Systems and methods are disclosed herein for syntonizing machines in a network. A coordinator accesses probe records for probes transmitted at different times between pairs of machines in the mesh network. For different pairs of machines, the coordinator estimates the drift between the pair of machines based on the transit times of probes transmitted between the pair of machines as indicated by the probe records. For different loops of at least three machines in the mesh network, the coordinator calculates a loop drift error based on a sum of the estimated drifts between pairs of machines around the loop and adjusts the estimated absolute drifts of the machines based on the loop drift errors. Here, the absolute drift is defined relative to a drift of a reference machine.