Forecasting Intraday Power Output by a Set of PV Systems using Recurrent Neural Networks and Physical Covariates
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909298612764672 |
|---|---|
| author | Bruneau, Pierrick Fiorelli, David Braun, Christian Koster, Daniel |
| author_facet | Bruneau, Pierrick Fiorelli, David Braun, Christian Koster, Daniel |
| contents | Accurate intraday forecasts of the power output by PhotoVoltaic (PV) systems are critical to improve the operation of energy distribution grids. We describe a neural autoregressive model that aims to perform such intraday forecasts. We build upon a physical, deterministic PV performance model, the output of which is used as covariates in the context of the neural model. In addition, our application data relates to a geographically distributed set of PV systems. We address all PV sites with a single neural model, which embeds the information about the PV site in specific covariates. We use a scale-free approach which relies on the explicit modeling of seasonal effects. Our proposal repurposes a model initially used in the retail sector and discloses a novel truncated Gaussian output distribution. An ablation study and a comparison to alternative architectures from the literature shows that the components in the best performing proposed model variant work synergistically to reach a skill score of 15.72% with respect to the physical model, used as a baseline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_08459 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Forecasting Intraday Power Output by a Set of PV Systems using Recurrent Neural Networks and Physical Covariates Bruneau, Pierrick Fiorelli, David Braun, Christian Koster, Daniel Machine Learning Accurate intraday forecasts of the power output by PhotoVoltaic (PV) systems are critical to improve the operation of energy distribution grids. We describe a neural autoregressive model that aims to perform such intraday forecasts. We build upon a physical, deterministic PV performance model, the output of which is used as covariates in the context of the neural model. In addition, our application data relates to a geographically distributed set of PV systems. We address all PV sites with a single neural model, which embeds the information about the PV site in specific covariates. We use a scale-free approach which relies on the explicit modeling of seasonal effects. Our proposal repurposes a model initially used in the retail sector and discloses a novel truncated Gaussian output distribution. An ablation study and a comparison to alternative architectures from the literature shows that the components in the best performing proposed model variant work synergistically to reach a skill score of 15.72% with respect to the physical model, used as a baseline. |
| title | Forecasting Intraday Power Output by a Set of PV Systems using Recurrent Neural Networks and Physical Covariates |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2303.08459 |