Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.04521 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913825591132160 |
|---|---|
| author | Cheung, Kuen Sum Kaul, Mayuri Jahangirova, Gunel Mousavi, Mohammad Reza Zie, Eric |
| author_facet | Cheung, Kuen Sum Kaul, Mayuri Jahangirova, Gunel Mousavi, Mohammad Reza Zie, Eric |
| contents | Large Language Models (LLM) have significantly transformed various domains, including software development. These models assist programmers in generating code, potentially increasing productivity and efficiency. However, the environmental impact of utilising these AI models is substantial, given their high energy consumption during both training and inference stages. This research aims to compare the energy consumption of manual software development versus an LLM-assisted approach, using Codeforces as a simulation platform for software development. The goal is to quantify the environmental impact and propose strategies for minimising the carbon footprint of using LLM in software development. Our results show that the LLM-assisted code generation leads on average to 32.72 higher carbon footprint than the manual one. Moreover, there is a significant correlation between task complexity and the difference in the carbon footprint of the two approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_04521 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Comparative Analysis of Carbon Footprint in Manual vs. LLM-Assisted Code Development Cheung, Kuen Sum Kaul, Mayuri Jahangirova, Gunel Mousavi, Mohammad Reza Zie, Eric Software Engineering Large Language Models (LLM) have significantly transformed various domains, including software development. These models assist programmers in generating code, potentially increasing productivity and efficiency. However, the environmental impact of utilising these AI models is substantial, given their high energy consumption during both training and inference stages. This research aims to compare the energy consumption of manual software development versus an LLM-assisted approach, using Codeforces as a simulation platform for software development. The goal is to quantify the environmental impact and propose strategies for minimising the carbon footprint of using LLM in software development. Our results show that the LLM-assisted code generation leads on average to 32.72 higher carbon footprint than the manual one. Moreover, there is a significant correlation between task complexity and the difference in the carbon footprint of the two approaches. |
| title | Comparative Analysis of Carbon Footprint in Manual vs. LLM-Assisted Code Development |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2505.04521 |