Transformer Networks for Predictive Group Elevator Control

TL;DR

This paper introduces a predictive elevator control system using Transformer-based passenger arrival prediction and linear regression, significantly reducing waiting times during peak hours.

Contribution

It presents a novel predictive scheduler combining Transformer models and linear regression for improved elevator efficiency.

Findings

Up to 50% reduction in average waiting time for light traffic.

Approximately 15% reduction in waiting time during medium traffic.

Achieves 80% accurate early predictions with only 60% of passenger trajectory observed.

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.