kieker.tools.tslib.forecast.cs
Class CSForecaster

java.lang.Object
  kieker.tools.tslib.forecast.AbstractForecaster<Double>
      kieker.tools.tslib.forecast.AbstractRForecaster
          kieker.tools.tslib.forecast.cs.CSForecaster

All Implemented Interfaces:

IForecaster<Double>

public class CSForecaster
extends AbstractRForecaster

This is one of the forecasters used in the research paper on Self-adaptive workload classification and forecasting for proactive resource provisioning (http://dx.doi.org/10.1002/cpe.3224), authored by Herbst et al.

Since:

1.10

Author:

Nikolas Herbst Cubic splines are fitted to the univariate time series data to obtain a trend estimate and linear forecast function. Prediction intervals are constructed by use of a likelihood approach for estimation of smoothing parameters. The cubic splines method can be mapped to an ARIMA 022 stochastic process model with a restricted parameter space. Overhead below 100ms for less than 30 values (more values do not sig. improve accuracy)

Constructor Summary

CSForecaster(ITimeSeries<Double> historyTimeseries)

CSForecaster(ITimeSeries<Double> historyTimeseries, int confidenceLevel)

Method Summary

Methods inherited from class kieker.tools.tslib.forecast.AbstractRForecaster

forecast, removeNullValues

Methods inherited from class kieker.tools.tslib.forecast.AbstractForecaster

getConfidenceLevel, getTsOriginal

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

CSForecaster

public CSForecaster(ITimeSeries<Double> historyTimeseries)

Parameters:

historyTimeseries - timeseries used by forecating algo

CSForecaster

public CSForecaster(ITimeSeries<Double> historyTimeseries,
                    int confidenceLevel)

Parameters:

historyTimeseries - timeseries used by forecating algo

confidenceLevel - value of confidence