machine learning capabilities, limits, related functions - Simple Log Service

Simple Log Service features machine learning capabilities that support various algorithms and calling methods. You can use analytic statements and machine learning functions to analyze the characteristics of one or more fields over time. Various analysis algorithms are offered to address time series data challenges, such as predicting trends, detecting anomalies, decomposing series, and clustering multiple series. These algorithms are compatible with standard SQL functions, simplifying usage and enhancing troubleshooting efficiency.

Features

Various smooth operations for single-time series data.
Algorithms for prediction, anomaly detection, change point detection, inflection point detection, and multi-period estimation of single-time series data.
Decomposition operations for analyzing single-time series data.
Various clustering algorithms for multi-time series data.
Multi-field pattern mining based on sequences of numeric data or text.

Limits

Time series data must be sampled at the same interval.
The data cannot contain multiple samples from the same point in time.

Processing capacity must not exceed the maximum limits listed below:

Item	Limit
Capacity of the time-series data processing	Data can be collected from a maximum of 150,000 consecutive points in time. If the data volume exceeds the processing capacity, you must aggregate the data or reduce the sampling amount.
Capacity of the density-based clustering algorithm	Up to 5,000 time series curves can be clustered simultaneously, with each curve limited to 1,440 points in time.
Capacity of the hierarchical clustering algorithm	Up to 2,000 time series curves can be clustered simultaneously, with each curve limited to 1,440 points in time.

Machine learning functions

Category		Function	Description
Time series	Smooth function	ts_smooth_simple	Uses the Holt Winters algorithm to smooth time series data.
		ts_smooth_fir	Uses the finite impulse response (FIR) filter to smooth time series data.
		ts_smooth_iir	Uses the infinite impulse response (IIR) filter to smooth time series data.
	Multi-period estimation function	ts_period_detect	Estimates time series data by period.
	Change point detection function	ts_cp_detect	Detects intervals with differing statistical features, identifying the interval endpoints as change points.
	Change point detection function	ts_breakout_detect	Detects the points in time at which data experiences dramatic changes.
	Maximum value detection function	ts_find_peaks	Detects the local maximum value of time series data in a specified window.
	Prediction and anomaly detection function	ts_predicate_simple	Uses default parameters to model time series data, predict time series data, and detect anomalies.
		ts_predicate_ar	Uses an autoregressive (AR) model to model time series data, predict time series data, and detect anomalies.
		ts_predicate_arma	Uses an autoregressive moving average (ARMA) model to model time series data, predict time series data, and detect anomalies.
		ts_predicate_arima	Uses an autoregressive integrated moving average (ARIMA) model to model time series data, predict time series data, and detect anomalies.
		ts_regression_predict	Predicts the long-run trend for a single periodic time series.
	Sequence decomposition function	ts_decompose	Uses the Seasonal and Trend decomposition using Loess (STL) algorithm to decompose time series data.
	Time series clustering function	ts_density_cluster	Uses a density-based clustering method to cluster multiple time series.
		ts_hierarchical_cluster	Uses a hierarchical clustering method to cluster multiple time series.
		ts_similar_instance	Queries time series curves similar to a specified time series curve.
	Kernal density estimation functions	kernel_density_estimation	Fits observed data points using a smooth peak function to simulate the actual probability distribution curve.
	Time series padding function	series_padding	Pads data points missing in a time series.
	Anomaly comparison function	anomaly_compare	Compares the degree of difference of an observed object in two periods of time.
Pattern mining	Frequent pattern statistical function	pattern_stat	Mines representative combinations of attributes among the given multi-attribute field samples to obtain frequent statistical patterns.
	Differential pattern statistical function	pattern_diff	Identifies the pattern that causes differences between two collections in specified conditions.
	Root cause analysis function	rca_kpi_search	Analyzes the subdimension attributes that cause anomalies of the monitoring metric.
	Correlation analysis functions	ts_association_analysis	Identifies the metrics correlated to a specified metric among multiple observed metrics in the system.
	Correlation analysis functions	ts_similar	Identifies the metrics correlated to specified time series data among multiple observed ones in the system.
	Request URL classification function	url_classify	Classifies a request URL and assigns a tag to it, along with a regular expression that defines the tag's pattern.