In order to evaluate the best performance of the Orchestra model in comparison with market competitors, KPIs, or indicators, were identified that are useful in defining the success of the project. Among the various performance indicators examined and analyzed, two quantitative metrics were selected that can be measured objectively and describe the performance of the project optimally while also ensuring continuous monitoring of the achievement of the set goals.The two selected KPIs are: NMAE (Normalized Mean Absolute Error) and RMSE (Root Mean Squared Error).
The NMAE indicator allows quantification of the average error of the Orchestra model with respect to the maximum power that can be delivered by the considered plant (rated power, in the formula denoted as kWh(max)). This indicator is defined by the expression, for a given forecast horizon h:
Where yt|t-h is the value predicted by Omnienergy at time t-h relative to time t, yt the value of energy input at time t, and T represents the number of observations considered.
The RMSE metric, however, allows us to quantify the difference in model output from absolute output: larger errors have a greater proportional impact on the RMSE indicator. This indicator was chosen because it allows monitoring the forecast performance in real time and is defined, for each forecast horizon h, by the following formula: