
AI optimises charging schedules for electric bus fleets by analysing vehicle schedules, battery levels, and electricity prices. This enables flexible charging strategies that reduce energy costs and prevent grid overload.
The electrification of public transportation is an important step toward reducing greenhouse gas emissions and improving air quality in cities. Electric buses are increasingly being adopted by public transit agencies worldwide as an alternative to diesel-powered buses. While electric buses offer significant environmental benefits, they also introduce new operational challenges related to charging infrastructure and energy management. Bus depots often operate large fleets that must be charged within limited time windows, usually overnight or during off-peak hours. If charging is not managed efficiently, it can lead to high electricity costs, grid overload, and inefficient utilisation of charging infrastructure.
Artificial Intelligence (AI) provides a powerful solution for managing electric bus charging systems more efficiently. AI-enabled charging platforms analyse operational data from bus fleets, charging stations, and electricity markets to optimise charging schedules. These systems consider several factors, including bus arrival and departure schedules, battery state-of-charge, route energy requirements, electricity tariffs, and grid constraints.
For additional context and detailed documentation of this use case, please refer to pages 40-43 in the attached Casebook.
© 2026 - Copyright AIKosh. All rights reserved. This portal is developed by National e-Governance Division for AIKosh mission.