Learning short-term past as predictor of human behavior in commercial buildings
This work addresses energy efficiency and occupant comfort in building management, but it is incremental as it focuses on optimizing time-window selection for an existing prediction task.
This paper tackled the problem of predicting future window opening actions in commercial buildings by identifying the optimal short-term past time-window from indoor climate data, finding that using 60 time-steps (minutes) as input achieved the best predictive performance, with F1 scores dropping from 0.51 to 0.27 as prediction targets shifted from 10 to 60 minutes into the future.
This paper addresses the question of identifying the time-window in short-term past from which the information regarding the future occupant's window opening actions and resulting window states in buildings can be predicted. The addressed sequence duration was in the range between 30 and 240 time-steps of indoor climate data, where the applied temporal discretization was one minute. For that purpose, a deep neural network is trained to predict the window states, where the input sequence duration is handled as an additional hyperparameter. Eventually, the relationship between the prediction accuracy and the time-lag of the predicted window state in future is analyzed. The results pointed out, that the optimal predictive performance was achieved for the case where 60 time-steps of the indoor climate data were used as input. Additionally, the results showed that very long sequences (120-240 time-steps) could be addressed efficiently, given the right hyperprameters. Hence, the use of the memory over previous hours of high-resolution indoor climate data did not improve the predictive performance, when compared to the case where 30/60 minutes indoor sequences were used. The analysis of the prediction accuracy in the form of F1 score for the different time-lag of future window states dropped from 0.51 to 0.27, when shifting the prediction target from 10 to 60 minutes in future.