Application of Deep Q Learning with Simulation Results for Elevator Optimization

TL;DR

This paper develops a Deep Q Learning approach to optimize elevator wait times using simulation data, comparing it to a naive model and analyzing the limitations of MDP assumptions in complex elevator control systems.

Contribution

It introduces a Deep Q Learning method for elevator optimization and evaluates its performance against a naive control model using realistic simulation data.

Findings

Deep Q Learning closely matches naive model performance

MDP assumptions may not fully capture elevator system stochasticity

Simulation results highlight potential improvements in elevator control strategies

Abstract

This paper presents a methodology for combining programming and mathematics to optimize elevator wait times. Based on simulated user data generated according to the canonical three-peak model of elevator traffic, we first develop a naive model from an intuitive understanding of the logic behind elevators. We take into consideration a general array of features including capacity, acceleration, and maximum wait time thresholds to adequately model realistic circumstances. Using the same evaluation framework, we proceed to develop a Deep Q Learning model in an attempt to match the hard-coded naive approach for elevator control. Throughout the majority of the paper, we work under a Markov Decision Process (MDP) schema, but later explore how the assumption fails to characterize the highly stochastic overall Elevator Group Control System (EGCS).