Synthetic Time Series Query Implementation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional data management systems face challenges in efficiently handling and combining large quantities of data from applications, particularly in aligning and processing time series data without losing fidelity, especially when dealing with hundreds or thousands of data streams.
Innovation Solution
A system that includes a compiler and executor to perform high-fidelity combination of data by generating synthetic time series, allowing for efficient query implementation and data alignment while maintaining high fidelity, and handling both discrete and continuous data streams.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional SQL join operations are performed on hundreds or thousands of time series, then query results can be obtained, but the computational cost and processing time become prohibitively expensive
Solution Approach 1:
The patent segments the query processing into two distinct phases: a compilation phase that generates a synthetic time series representing the query criteria, and an execution phase that efficiently compares actual time series against this synthetic representation. This segmentation transforms an O(n²) join operation into an O(n) comparison operation, dramatically improving productivity while reducing computational energy consumption.
Solution Approach 2:
The patent creates a synthetic time series as a copy or representation of the query criteria rather than directly comparing all time series pairs. This synthetic copy encapsulates the query conditions and can be reused for efficient comparison against multiple time series, eliminating redundant computations and reducing both processing time and energy consumption.
2Reliability
If data streams are combined using conventional gridding methods, then alignment is achieved, but data fidelity and integrity are lost
Solution Approach 1:
Instead of forcing data streams to conform to a fixed grid structure (conventional approach), the patent inverts the approach by generating a synthetic time series that adapts to the query criteria and compares it against the actual time series. This inversion preserves the original data fidelity while achieving the necessary alignment for meaningful comparisons.
Solution Approach 2:
The patent changes the fundamental parameter of alignment from fixed grid-based time stamps to flexible query-criteria-based synthetic time series generation. This parameter change allows the system to maintain data fidelity by not forcing data into predetermined grid structures, instead adapting the comparison mechanism to preserve information integrity.
3Productivity
If conventional monitoring techniques are used for applications generating large quantities of data, then system status can be tracked, but scalability and efficiency are limited
Solution Approach 1:
The patent creates a universal query implementation mechanism that works across diverse time series data sources and query types through the synthetic time series approach. This multi-functional system can handle various query conditions (thresholds, patterns, time ranges) using a single efficient mechanism, improving productivity without proportionally increasing system complexity or reducing scalability.
Data Source
AI summary
Techniques described herein perform implement a query using a synthetic time series (STS), for example applying an STS on time series data to obtain an answer to the query. In an embodiment, a method receives a times series and query relating to the time series. The method translates the query into a synthetic time series. The method executes a reduce operation on the STS and the time series. The method then returns the result of the operation as an answer to the query. A result of the reduce operation is returned as an answer to the query.