The aim of energy management according to DIN EN ISO 50001 is to increase energy-related performance - this is how the standard itself defines it. In addition, DIN ISO 50003: "Energy management systems - Requirements for bodies providing audit and certification of energy management systems" was published in 2016. Since then, organisations seeking a certification according to DIN EN ISO 50001 have been obliged to prove that energy-related performance has been increased.
What is energy-related performance?
In most cases, energy-related performance is equated with energy efficiency, as the yield, e.g. of a produced quantity in relation to the energy used. As long as the framework conditions remain the same, an improvement in energy efficiency can easily be read from consumption. If a car park lighting system is always switched on at the time of a calculated sunset and switched off again at the time of a calculated sunrise, two years can be directly compared - unless there is a leap year. Is there only one key variable that has a significant impact on energy consumption (e.g. the number of identical workpieces produced), a quotient (workpieces per kWh) can be helpful - at least as long as there is no basic consumption that is independent of capacity utilisation.
Complex determination of energy efficiency
Especially in the industrial environment, however, the correlations are usually much more complex. Different products, different raw materials and diverse external conditions such as outside temperature often have a significant influence on energy consumption. Without taking all these influencing variables into account, you cannot make any useful statements. Even in the administrative sector, it will be difficult in 2020 to make a simple comparison with previous years. Due to pandemic-related home offices, a key figure such as electricity consumption per employee loses its meaningfulness. It is therefore impossible to assess whether the new lighting has actually saved as much energy as was calculated.
How do you best assess energy efficiency?
You can make an accurate assessment of the development of energy efficiency by using suitable energy performance indicators (EnPIs) and, above all, sound energy baselines (EnBs). The energetic baseline is a quantitative reference point that serves as a basis for comparing energy-related performance. A detailed description of the procedure can be found in ISO 50006 "Energy management systems - Measurement of energy-related performance using energy baselines (EnBs) and energy performance indicators (EnPIs) - General principles and guidance". Although the standard leaves several ways to reach the goal, especially one approach is very popular among experienced energy managers: multidimensional regression.
Requirements for multidimensional regression
A prerequisite is that historical measurement data are available for a sufficiently long period of time both for the target variable, i.e. the actual measured value (e.g. power consumption of machine x or hall y), and for as many influencing variables as possible. The resolution of the measured data should be sufficiently high, for example in the form of ¼-h or daily values. In this way, the current values can be evaluated promptly. Influencing variables can also be represented by indirect measured values: If, for example, there are no finely resolved figures available on the exact production quantity, the number of forklift hours can instead provide an indication of how many pallets of finished product were transported away in one day.
To determine the correlation between each individual influencing variable and the target variable - but also the correlation between the individual influencing variables - statistical methods can be used . That way the relevant influencing variables are identified. The next step is to determine a formula that describes how the expected energy consumption can be calculated from given values of the relevant influencing variables. Expected in the sense that this consumption would have occurred during the reference period, from which the measurement series used to determine the formula originated, if the new values of the influencing variables had been available.
Such a formula can be used as an energetic starting point. For each period under consideration - e.g. one day - you can use it to calculate the consumption that would have occurred for the same energy output if all influencing variables were known.
The highlight for users of IngSoft InterWatt
So far the theory. In practice, many energy managers use Microsoft Excel to analyse the influencing variables and find the reference formula. To do this, they use the functionality integrated in the spreadsheet software.
So much for the theory. In everyday practice, many energy managers use Microsoft Excel to analyse the influencing variables and find the reference formula. To do this, they use the functionality integrated in the spreadsheet software. The procedure there is called OLS-Fit (Ordinary Least-Square Fit) - the coefficients of the influencing variables are selected so that the square of the deviations of the reference formula from the measured values is minimal.
Users of IngSoft InterWatt have long since saved themselves the trouble of copying the data back and forth. Instead, they use a one- or two-dimensional regression directly in the energy management software to calculate an energetic baseline. This provides the basis for a prompt and continuous comparison with the current measured value. IngSoft InterWatt also recognises different operating states based on schedules or measured values and treats them separately.
Multidimensional regression thought ahead
With our Release 20, planned to be released in September 2020, the toolbox for EnPIs integrated in the software will become even more powerful: In addition to multidimensional regression for the influencing variables selected by the user, advanced regression algorithms such as RIDGE and LASSO will then also be available.
In the case of LASSO regression, for example, the software automatically selects the influencing variables and reduces their number if possible and reasonable. The formula found this way is much closer to reality: On the one hand, the actual influence of an influencing variable can be read from this formula. On the other hand, the formula for the reference value found in this way is less susceptible to deviations in influencing variables. While OLS already finds the best possible fit for the reference period, RIDGE regression usually finds a solution that is closer to reality for future values as well. If a solution can be found that has fewer parameters due to the partial omission of interdependent influencing variables, the so-called overfitting is avoided: Although the function fits very well to the values in the reference period, at other times it lies further away from reality.
Thus a "one touch" multidimensional regression becomes reality. The IngSoft InterWatt user does not need to change the tool and receives an energetic baseline that takes into account all relevant measured influencing variables even in complex contexts. It delivers more accurate results than conventional OLS regression thanks to advanced algorithms. Thus, you can rely on timely and automatic realistic statements on the development of energy-related performance.
But also users who do not like to trust a black box will find new helpful functions in release 20 of IngSoft InterWatt. For example: the software automatically creates a correlation matrix from which statistically experienced users can read out the information they need to identify the relevant influencing variables themselves.