Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Managing Charging Induced Grid Stress and Battery Degradation in Electric Taxi Fleets

Michael Yuhas, Rajesh K. Ahir, Laksamana Vixell Tanjaya Hartono, Muhammad Dzaki Dwi Putranto, Arvind Easwaran, Suhono Harso Supangkat

TL;DR

The paper tackles charging-induced grid stress and battery degradation in EV taxi fleets by proposing a long-horizon simulator that jointly models ride demand, charging infrastructure, grid constraints, and multi-stage battery aging. It evaluates a PPO-RL charging policy against a baseline 80-20 rule, demonstrating improvements in grid stress, battery health, and long-run profitability, while using real-world NYC taxi data to ground the model. The core contribution is an integrated platform that enables end-to-end assessment of charging policies over multiple years, formalized through a Lagrangian-transformed reinforcement learning objective with constraints on grid power. This work offers a practical step toward operational planning and digital-twin development for EV taxi fleets, guiding policy design to balance fleet longevity, profitability, and grid stability.

Abstract

Operating fleets of electric vehicles (EVs) introduces several challenges, some of which are borne by the fleet operator, and some of which are borne by the power grid. To maximize short-term profit a fleet operator could always charge EVs at the maximum rate to ensure vehicles are ready to service ride demand. However, due to the stochastic nature of electricity demand, charging EVs at their maximum rate may potentially increase the grid stress and lead to overall instability. Furthermore, high-rate charging of EVs can accelerate battery degradation, thereby reducing the service lifespan of the fleet. This study aims to reconcile the conflicting incentives of fleet longevity, short-term profitability, and grid stability by simulating a taxi fleet throughout its lifespan in relation to its charging policies and service conditions. We develop an EV fleet simulator to evaluate the battery degradation due to unpredictable charging and ride demand. Consequently, the impact on the power grid through the charging infrastructure is assessed due to these activities. This simulation utilizes publicly accessible real-world travel data from the NYC taxi dataset. We compare a baseline 80-20 fleet charging policy with a reinforcement learning-based policy designed to prolong the fleet's service life and alleviate grid stress. We monitor grid stress, battery degradation, and profitability over five years and find that our learned policy outperforms the baseline. This simulator enables fleet operators to assess the impact of different charging policies on these indicators to make informed decisions in the future.

Managing Charging Induced Grid Stress and Battery Degradation in Electric Taxi Fleets

TL;DR

The paper tackles charging-induced grid stress and battery degradation in EV taxi fleets by proposing a long-horizon simulator that jointly models ride demand, charging infrastructure, grid constraints, and multi-stage battery aging. It evaluates a PPO-RL charging policy against a baseline 80-20 rule, demonstrating improvements in grid stress, battery health, and long-run profitability, while using real-world NYC taxi data to ground the model. The core contribution is an integrated platform that enables end-to-end assessment of charging policies over multiple years, formalized through a Lagrangian-transformed reinforcement learning objective with constraints on grid power. This work offers a practical step toward operational planning and digital-twin development for EV taxi fleets, guiding policy design to balance fleet longevity, profitability, and grid stability.

Abstract

Operating fleets of electric vehicles (EVs) introduces several challenges, some of which are borne by the fleet operator, and some of which are borne by the power grid. To maximize short-term profit a fleet operator could always charge EVs at the maximum rate to ensure vehicles are ready to service ride demand. However, due to the stochastic nature of electricity demand, charging EVs at their maximum rate may potentially increase the grid stress and lead to overall instability. Furthermore, high-rate charging of EVs can accelerate battery degradation, thereby reducing the service lifespan of the fleet. This study aims to reconcile the conflicting incentives of fleet longevity, short-term profitability, and grid stability by simulating a taxi fleet throughout its lifespan in relation to its charging policies and service conditions. We develop an EV fleet simulator to evaluate the battery degradation due to unpredictable charging and ride demand. Consequently, the impact on the power grid through the charging infrastructure is assessed due to these activities. This simulation utilizes publicly accessible real-world travel data from the NYC taxi dataset. We compare a baseline 80-20 fleet charging policy with a reinforcement learning-based policy designed to prolong the fleet's service life and alleviate grid stress. We monitor grid stress, battery degradation, and profitability over five years and find that our learned policy outperforms the baseline. This simulator enables fleet operators to assess the impact of different charging policies on these indicators to make informed decisions in the future.
Paper Structure (16 sections, 4 equations, 8 figures, 4 tables)

This paper contains 16 sections, 4 equations, 8 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Charge Scheduling
  4. Battery Degradation
  5. Fleet Simulation
  6. Long Horizon Modeling of Electric Taxi Fleets with a Simulator
  7. Vehicle Pool
  8. Traffic Model
  9. Demand Model
  10. Grid and Charging Model
  11. Scheduler
  12. Charge Scheduling with Reinforcement Learning
  13. Experiments
  14. Evaluation
  15. Cross-Environment Evaluation
  16. ...and 1 more sections

Figures (8)

  • Figure 1: A charge scheduler must decide where, when, and at what rate vehicles charge based on grid conditions, charger availability, ride demand, fleet location and health, and environmental conditions. Orange lines indicate the set of options the charge scheduler has for the selected vehicle.
  • Figure 2: High level block diagram of our simulator. Vehicles are persistent software objects that can be assigned to charge, service demand, or idle by the scheduler.
  • Figure 3: State diagrams of simulator entities
  • Figure 4: SoH across five years for simulated fleets charging with the baseline and PPO-RL charging policies. The shaded area indicates the IQR across all vehicles in the fleet.
  • Figure 5: Cumulative revenue of a fleet charging under the baseline and the PPO-RL policies over 5 years. PPO-RL maximizes revenue in the long run.
  • ...and 3 more figures