---
title: From Natural Language to Optimal Schedules: An LLM Interface for EV Charging
tags:  #ev charging #llm #optimization #smart grid #natural language interface  
author: [小平　大輔](https://www.docswell.com/user/daisuke-kodaira)
site: [Docswell](https://www.docswell.com/)
thumbnail: https://bcdn.docswell.com/page/YE9PKGQWJ3.jpg?width=480
description: 本研究では、ユーザーが「7時までにEVを充電したい」などの曖昧な自然言語で入力した要求から、到着時刻・出発時刻・目標SoC・最大充電電力・V2G有無といった必要パラメータをLLMが抽出します。抽出したパラメータを線形計画法（LP）オプティマイザに渡すことで、電力料金が低い時間帯を避けつつ所定の充電完了を保証する最適スケジュールを生成します。ケーススタディでは、ユーザーの要望を正確に反映したスケジュールが作成され、料金削減率が約65％（約28円）得られました。提案手法は、非技術者でも簡単にEV充電の最適化を利用できるようにし、今後はより複雑な要求やグリッド影響の指標提示、他の最適化モデルとの比較を検討します。
published: April 01, 26
canonical: https://www.docswell.com/s/daisuke-kodaira/K3J8PP-2026-04-01-161154
---
# Page. 1

![Page Image](https://bcdn.docswell.com/page/YE9PKGQWJ3.jpg)

From Natural Language to Optimal Schedules: An
LLM Interface for EV Charging
XUE Sihui, First-year Ph.D. Student
KODAIRA Daisuke, Assistant Professor
Graduate School of Science of Technology
Smart Grid Lab


# Page. 2

![Page Image](https://bcdn.docswell.com/page/GE8DRVGRED.jpg)

Background
Problem
Framework
Case study
Conclusion
“I want my EV to be
charged by 7 a.m.”
Incomplete config
Input
- Arrival time: Unknow
- Departure time: 7:00
- Target SoC: Full or 90%
Grid
- Max power: Unknow
···
Electric vehicle
Optimizer
- V2G: Unknow
Invalid input
• EV number increases, concentrated charging stresses the grid: load peaks
and price volatility.
• Optimization model (e.g., linear program) can schedule charging, but only
with complete, structured inputs.
• Natural language intent is incomplete and ambiguous, so it cannot be
executed by the optimizer directly.
-2-


# Page. 3

![Page Image](https://bcdn.docswell.com/page/LELMK5G27R.jpg)

Background
Problem
Framework
Case study
Conclusion
• Large language model (LLM) applications in energy systems:
mostly offline or advisory
Offline analysis
and reporting
Forecasting tasks
Operational support and
scheduling recommendations
Building and home
energy management
Grid operations and
fault diagnosis
Result explanation and
conversational interfaces
-3-


# Page. 4

![Page Image](https://bcdn.docswell.com/page/4JMY23Q9JW.jpg)

Background
Problem
Framework
Case study
Conclusion
• Problem statement
“I want my EV to be
charged by 7 a.m.”
Incomplete config
Input
- Arrival time: Unknow
- Departure time: 7:00
- Target SoC: Full or 90%
- Max power: Unknow
Optimizer
- V2G: Unknow
Invalid input
➢ Challenge 1: Natural language requests are incomplete and ambiguous,
important parameters may be missing.
➢ Challenge 2: Optimizers require validated, structured inputs.
-4-


# Page. 5

![Page Image](https://bcdn.docswell.com/page/PJR9MQ8979.jpg)

Background
Problem
Framework
Case study
Conclusion
• From natural language to optimal schedules
I want my EV to be fully charged by 7 a.m.,
preferably avoiding high-price periods, and
the charging power should stay below 7 kW,
save my money.
User
② Extracted config
- Arrival: 18:00
- Departure: 7:00
① Natural-language
- Target SoC: 100%
request
- Max power: 7 kW
⑥ Explanation
LLM agent
③ Model
config
- V2G: on
⑤ Results
④ Schedule
EV
Optimizer (LP)
-5-


# Page. 6

![Page Image](https://bcdn.docswell.com/page/PEXQV583JX.jpg)

Background
Problem
Framework
Case study
Conclusion
• Case study setup (LP model, ChatGPT-5-mini model)
Time-of-Use
price
Battery capacity 60
kWh
Timestep
1 hour
Battery SoC between
20% to 90%
Battery efficiency
0.95
• Validated LLM-extracted parameters enable effective LP scheduling.
(a) Charging power profiles of the two
strategies
(b) SoC trajectories of the two
strategies
-6-


# Page. 7

![Page Image](https://bcdn.docswell.com/page/3EK9Q6KNED.jpg)

Background
Problem
Framework
Case study
Conclusion
• Experimental process of the case study
Agent-User
interaction
User:
I will arrive home around 6
p.m. and leave at 8 a.m.
tomorrow. Please charge my
EV from about 20% to at
least 80% by departure,
avoid high-price periods as
much as possible.
Extracted
configuration
- Initial SoC: 0.2,
- Target SoC: 0.8,
- Start Hour: 18,
- End Hour: 8,
- V2G: false
Explanation
Agent:
Schedule generated.
64.9% (¥28.00) saved by
shifting charging to the
23:00–06:00 valley.
Target 80% SoC ensured
by 08:00.
-7-


# Page. 8

![Page Image](https://bcdn.docswell.com/page/L73WP6ZZ75.jpg)

Background
Problem
Framework
Case study
Conclusion
• Summary
➢ We proposes an LLM-based framework that converts EV charging requests
in natural-language into a structured parameters and drives the LP optimizer
effectively.
➢ It makes the optimization model easier for non-technical people to use.
• Future work
➢ User side: better handling of more complex user requests
➢ Grid side: show simple indicators of grid impact
➢ Compare different optimization model for charging based on our framework.
-8-


# Page. 9

![Page Image](https://bcdn.docswell.com/page/87DKLVR4JG.jpg)

Thank you all for listening.
XUE Sihui xue.sihui.tbk_gb@u.tsukuba.ac.jp
KODAIRA Daisuke kodaira.daisuke.gf@u.tsukuba.ac.jp
Graduate School of Science of Technology
Smart Grid Lab