Holt-Winters Forecast: Machine Performance Check Output Variation

Rodriguez B and Dosiou K

Published on: 2023-06-10

Abstract

Background: Machine Performance Check (MPC) is an automated TrueBeam quality control (QC) tools to verify beam output, isocenter, and uniformity. The goal of this study was to model the beam output based on Holt-Winters additive and multiplicative approach.

Materials and Methods: Daily MPC output data were obtained over a month and analyzed through a triple-exponential method based on a Holt-Winters (additive and multiplicative) model after TG-51 and baseline data have been established. The model performance was assessed via three standard errors measures: the mean squared error (MSE), mean absolute percentage error (MAPE), and mean absolute deviation (MAE). The aim was achieved using a nonlinear multistart solver Excel platform.

Results: The results showed that both additive and multiplicative Holt-Winters models are energy and model dependent and were suitable for MPC output data forecasting. MSE, MAPE and MAD are found to be well within acceptable limits.

Conclusion: A Holt-Winters model was able to accurately forecast the MPC output variation.