Abstract
In this paper, we present the concept and formulation of a short-term Markov corrector to an underlying day-ahead building load forecasting model. The models and the correctors are then integrated to the building supervision, control and data acquisition system to automate the self-updating and retraining processes. The proposed Markov corrector is experimentally proven to significantly improve the reactivity of the forecasting models with respect to untaught variations. Developed in a discrete manner over a continuous forecasting model, the corrector also helps to capture better the consumption peaks during the activity days. A proof-of-concept is demonstrated via the case study of the GreenER building, where the impact of the Markov correctors to the performance of the existing day-ahead load forecasting system (based on Prophet model) was analyzed during the 2021/2022 winter, under the influences of the Omicron wave of the COVID-19 pandemic.