Probabilistic PV Power Forecasting by a Multi-Modal Method using GPT-Agent to Interpret Weather Conditions

Traditionally Photovoltaic (PV) power generation forecasting is based on numeric meteorological vectors to capture weather conditions, which generally misses valuable multi-modal information such as those contained in linguistic weather descriptions. In the light of the recent success of large langu...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE Conference on Industrial Electronics and Applications (Online) s. 1 - 6
Hlavní autoři: Yan, Ziming, Zhenyuan, Du, Xu, Yan, Zhou, Ziyan
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 05.08.2024
Témata:
GPT-Agent
Linguistics
multi-modal forecasting
Photovoltaic systems
Predictive models
Probabilistic logic
Probabilistic PV forecasting
Transformers
Vectors
Weather forecasting
ISSN:2158-2297
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Traditionally Photovoltaic (PV) power generation forecasting is based on numeric meteorological vectors to capture weather conditions, which generally misses valuable multi-modal information such as those contained in linguistic weather descriptions. In the light of the recent success of large language models (LLM), this paper presents a new method for probabilistic PV power forecasting that integrates a generative pre-trained transformer (GPT) agent to interpret the linguistic descriptions of weather. The GPT-Agent interprets the descriptions of weather conditions from a specialized API such as Openweather and transforms them into estimated numeric vectors representing the likelihood of cloud coverage. Then, a compact multi-modal feature input is constructed combining numeric meteorological data and the interpreted weather conditions. Using this multi-modal input, two XGBoost models are hierarchically trained for probabilistic PV irradiance and power forecasting. With the first layer of XGBoost model to forecast the expected value of the PV irradiance and second layer of XGBoost model to forecast its variance, a probabilistic irradiance interval is constructed, and subsequently the PV power generation can be calculated and probabilistically forecasted. The multi-modal approach offers a holistic perspective on environmental factors affecting PV generation, resulting in more accurate results. Furthermore, the GPT-agent offers interpretability of PV forecasting by indicating the reasons of forecasting the PV output based on the weather. Simulation testing results demonstrate the effectiveness and advantage of the proposed method.
ISSN:2158-2297
DOI:10.1109/ICIEA61579.2024.10665072