Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.11050 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915340540182528 |
|---|---|
| author | Bi, Zhaoge Huang, Linghan Jin, Haolin Zeng, Qingwen Chen, Huaming |
| author_facet | Bi, Zhaoge Huang, Linghan Jin, Haolin Zeng, Qingwen Chen, Huaming |
| contents | Electricity price forecasting is a critical component of modern energy-management systems, yet existing approaches heavily rely on numerical histories and ignore contemporaneous textual signals. We introduce NSW-EPNews, the first benchmark that jointly evaluates time-series models and large language models (LLMs) on real-world electricity-price prediction. The dataset includes over 175,000 half-hourly spot prices from New South Wales, Australia (2015-2024), daily temperature readings, and curated market-news summaries from WattClarity. We frame the task as 48-step-ahead forecasting, using multimodal input, including lagged prices, vectorized news and weather features for classical models, and prompt-engineered structured contexts for LLMs. Our datasets yields 3.6k multimodal prompt-output pairs for LLM evaluation using specific templates. Through compresive benchmark design, we identify that for traditional statistical and machine learning models, the benefits gain is marginal from news feature. For state-of-the-art LLMs, such as GPT-4o and Gemini 1.5 Pro, we observe modest performance increase while it also produce frequent hallucinations such as fabricated and malformed price sequences. NSW-EPNews provides a rigorous testbed for evaluating grounded numerical reasoning in multimodal settings, and highlights a critical gap between current LLM capabilities and the demands of high-stakes energy forecasting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_11050 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NSW-EPNews: A News-Augmented Benchmark for Electricity Price Forecasting with LLMs Bi, Zhaoge Huang, Linghan Jin, Haolin Zeng, Qingwen Chen, Huaming Machine Learning Electricity price forecasting is a critical component of modern energy-management systems, yet existing approaches heavily rely on numerical histories and ignore contemporaneous textual signals. We introduce NSW-EPNews, the first benchmark that jointly evaluates time-series models and large language models (LLMs) on real-world electricity-price prediction. The dataset includes over 175,000 half-hourly spot prices from New South Wales, Australia (2015-2024), daily temperature readings, and curated market-news summaries from WattClarity. We frame the task as 48-step-ahead forecasting, using multimodal input, including lagged prices, vectorized news and weather features for classical models, and prompt-engineered structured contexts for LLMs. Our datasets yields 3.6k multimodal prompt-output pairs for LLM evaluation using specific templates. Through compresive benchmark design, we identify that for traditional statistical and machine learning models, the benefits gain is marginal from news feature. For state-of-the-art LLMs, such as GPT-4o and Gemini 1.5 Pro, we observe modest performance increase while it also produce frequent hallucinations such as fabricated and malformed price sequences. NSW-EPNews provides a rigorous testbed for evaluating grounded numerical reasoning in multimodal settings, and highlights a critical gap between current LLM capabilities and the demands of high-stakes energy forecasting. |
| title | NSW-EPNews: A News-Augmented Benchmark for Electricity Price Forecasting with LLMs |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2506.11050 |