Workload Identification via ML Time Series Similarity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional time series analysis approaches face challenges in accuracy and scalability when identifying workloads contributing to system performance degradation in dynamic systems.
Innovation Solution
Implementing a machine learning algorithm that calculates similarity measurements between primary and candidate time series using covariance, dynamic time warping, and shape-based distance metrics, and assigns weights to candidate time series based on their similarity, to generate a similarity score and identify contributing workloads.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional time series analysis approaches are used, then the system can identify workloads contributing to performance degradation, but the accuracy and scalability are insufficient
Solution Approach 1:
The patent segments the time series analysis into multiple distinct similarity measurements (covariance, dynamic time warping, shape-based distance) that are calculated independently and then combined. This segmentation allows each measurement to focus on specific aspects of time series similarity, improving overall accuracy while maintaining computational efficiency through modular processing
Solution Approach 2:
The patent merges multiple similarity measurements into a comprehensive workload identification framework. By combining covariance, dynamic time warping, and shape-based distance metrics, the system achieves higher measurement precision than any single method could provide alone, while the unified approach improves scalability through consolidated processing
2Measurement precision
If multiple similarity measurements are calculated using machine learning techniques, then the accuracy of workload identification is improved, but the computational complexity increases
Solution Approach 1:
The computational complexity is managed by segmenting the analysis into distinct similarity measurement components (covariance, dynamic time warping, shape-based distance). Each component processes specific aspects of the time series data independently, allowing for optimized computation of each metric rather than a monolithic complex calculation
Solution Approach 2:
The patent applies parameter changes by using machine learning techniques to dynamically adjust and weight the multiple similarity measurements. This allows the system to adapt the computational resources allocated to each measurement type based on the specific characteristics of the data, improving accuracy while managing computational complexity through intelligent resource allocation
Data Source
AI summary
Methods, apparatus, and processor-readable storage media for automatic identification of workloads contributing to system performance degradation are provided herein. An example computer-implemented method includes obtaining, in connection with a system exhibiting performance degradation, a primary time series and a set of multiple candidate time series; calculating, using machine learning, similarity measurements between the primary time series and each time series in the set; for each measurement, assigning weights to the time series based on similarity to the primary time series relative to the other time series in the set; generating, for each time series in the set, a similarity score based on the weights assigned across the similarity measurements; and outputting, based on the similarity scores, identification of a candidate time series for use in automated actions.