Root Mean Square Error or deviation is a measure of how much error or deviation there is between two data streams. In Info360 this can be used to validate any prediction or smoothing equations that are used.

The equation for RMSE is shown below, where x1 and x2 are two data streams that are being compared, and n is the period.


The input values in Info360 are as follows:



Input Data*

Defines the time series data fed into the function. This can be a sensor ID or another function.


Number of data intervals considered in the function.

Reference Data Stream

Defines the time series data to be compared against for the given time period.

*Input data is optional in most cases. If Info360 detects that the first input is time series data, it will be applied to the function. Otherwise, the current active sensor's data will be used, which is often the case in Reference Charts.

Example Usage as an Expression:

RMSE(Sensor('Sensor_A'),12,'Sensor_B') - Calculates the RMSE between Sensor_A and Sensor_B over the previous 12 data points.

RMSE(Average(),12,'Sensor_B') - Calculates the RMSE between the Average current sensor value and the default sample of Sensor_B over the previous 12 data points.

Examples Reference Chart:

The following example shows a comparison of measured tank levels against outputs from InfoWater that have been pushed to an Updatable Sensor. RMSE is often used to validate model calibration, and in this case it can be automated between InfoWater or InfoSWMM and Info360 measured data.


For information on setting up custom equations and syntax, please refer to Analytical Functions.