TR2022-100

Transformer Networks for Predictive Group Elevator Control


Abstract:

We propose a Predictive Group Elevator Scheduler by using predictive information of passengers arrivals from a Transformer based destination predictor and a linear regression model that predicts remaining time to destinations. Through extensive empirical evaluation, we find that the savings of Average Waiting Time (AWT) could be as high as above 50% for light arrival streams and around 15% for medium arrival streams in afternoon down-peak traffic regimes. Such results can be obtained after carefully setting the Predicted Probability of Going to Elevator (PPGE) threshold, thus avoiding a majority of false predictions for people heading to the elevator, while achieving as high as 80% of true predictive elevator landings as early as after having seen only 60% of the whole trajectory of a passenger.

 

  • Related Publication

  •  Zhang, J., Tsiligkaridis, A., Taguchi, H., Raghunathan, A., Nikovski, D., "Transformer Networks for Predictive Group Elevator Control", arXiv, August 2022.
    BibTeX arXiv
    • @article{Zhang2022aug,
    • author = {Zhang, Jing and Tsiligkaridis, Athanasios and Taguchi, Hiroshi and Raghunathan, Arvind and Nikovski, Daniel},
    • title = {Transformer Networks for Predictive Group Elevator Control},
    • journal = {arXiv},
    • year = 2022,
    • month = aug,
    • url = {https://arxiv.org/abs/2208.08948}
    • }