Recent advancements in the field of Natural Language Processing (NLP) and Large Language Models (LLMs) have opened new avenues for processing qualitative data. This development is particularly interesting for power systems as they have an enormous amount of untapped qualitative data.
Decision-making in the power system sector has relied on quantitative data. However, qualitative data such as textual information hold untapped potential to provide valuable insights and act as decision support tools in multiple tasks, including forecasting. The challenge lies in effectively processing these qualitative data for such tasks.
In this paper, we propose an approach to address this challenge. We perform sentiment analysis using LLMs on system operator comments from the Alberta Interconnected Electric System and apply it to transmission loss forecasting.
Authors: Gideon Egharevba, Arne Dankers, Hamidreza Zareipour
Read the full paper on Ieeexplore
