Cargando…
Sensorless PV Power Forecasting in Grid-Connected Buildings through Deep Learning
Existing works in photovoltaic (PV) power generation focus on accurately predicting the PV power output on a forecast horizon. As the solar power generation is heavily influenced by meteorological conditions such as solar radiation, the weather forecast is a critical input in the prediction performa...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2018
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6111307/ https://www.ncbi.nlm.nih.gov/pubmed/30072641 http://dx.doi.org/10.3390/s18082529 |
_version_ | 1783350630517047296 |
---|---|
author | Son, Junseo Park, Yongtae Lee, Junu Kim, Hyogon |
author_facet | Son, Junseo Park, Yongtae Lee, Junu Kim, Hyogon |
author_sort | Son, Junseo |
collection | PubMed |
description | Existing works in photovoltaic (PV) power generation focus on accurately predicting the PV power output on a forecast horizon. As the solar power generation is heavily influenced by meteorological conditions such as solar radiation, the weather forecast is a critical input in the prediction performance. However, the weather forecast is traditionally considered to have coarse granularity, so many are compelled to use on-site meteorological sensors to complement it. However, the approach involving on-site sensors has several issues. First, it incurs the cost in the installation, operation, and management of the sensors. Second, the physical model of the sensor dynamics itself can be a source of forecast errors. Third, it requires an accumulation of sensory data that represent all seasonal variations, which takes time to collect. In this paper, we take an alternative approach to use a relatively large deep neural network (DNN) instead of the on-site sensors to cope with the coarse-grained weather forecast. With historical PV output power data from our grid-connected building with a rooftop PV power generation facility and the publicly available weather forecast history data, we demonstrate that we can train a six-layer feedforward DNN for the day-ahead forecast. It achieves the average mean absolute error (MAE) of 2.9%, comparable to that of the conventional model, but without involing the on-site sensors. |
format | Online Article Text |
id | pubmed-6111307 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2018 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-61113072018-08-30 Sensorless PV Power Forecasting in Grid-Connected Buildings through Deep Learning Son, Junseo Park, Yongtae Lee, Junu Kim, Hyogon Sensors (Basel) Article Existing works in photovoltaic (PV) power generation focus on accurately predicting the PV power output on a forecast horizon. As the solar power generation is heavily influenced by meteorological conditions such as solar radiation, the weather forecast is a critical input in the prediction performance. However, the weather forecast is traditionally considered to have coarse granularity, so many are compelled to use on-site meteorological sensors to complement it. However, the approach involving on-site sensors has several issues. First, it incurs the cost in the installation, operation, and management of the sensors. Second, the physical model of the sensor dynamics itself can be a source of forecast errors. Third, it requires an accumulation of sensory data that represent all seasonal variations, which takes time to collect. In this paper, we take an alternative approach to use a relatively large deep neural network (DNN) instead of the on-site sensors to cope with the coarse-grained weather forecast. With historical PV output power data from our grid-connected building with a rooftop PV power generation facility and the publicly available weather forecast history data, we demonstrate that we can train a six-layer feedforward DNN for the day-ahead forecast. It achieves the average mean absolute error (MAE) of 2.9%, comparable to that of the conventional model, but without involing the on-site sensors. MDPI 2018-08-02 /pmc/articles/PMC6111307/ /pubmed/30072641 http://dx.doi.org/10.3390/s18082529 Text en © 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Son, Junseo Park, Yongtae Lee, Junu Kim, Hyogon Sensorless PV Power Forecasting in Grid-Connected Buildings through Deep Learning |
title | Sensorless PV Power Forecasting in Grid-Connected Buildings through Deep Learning |
title_full | Sensorless PV Power Forecasting in Grid-Connected Buildings through Deep Learning |
title_fullStr | Sensorless PV Power Forecasting in Grid-Connected Buildings through Deep Learning |
title_full_unstemmed | Sensorless PV Power Forecasting in Grid-Connected Buildings through Deep Learning |
title_short | Sensorless PV Power Forecasting in Grid-Connected Buildings through Deep Learning |
title_sort | sensorless pv power forecasting in grid-connected buildings through deep learning |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6111307/ https://www.ncbi.nlm.nih.gov/pubmed/30072641 http://dx.doi.org/10.3390/s18082529 |
work_keys_str_mv | AT sonjunseo sensorlesspvpowerforecastingingridconnectedbuildingsthroughdeeplearning AT parkyongtae sensorlesspvpowerforecastingingridconnectedbuildingsthroughdeeplearning AT leejunu sensorlesspvpowerforecastingingridconnectedbuildingsthroughdeeplearning AT kimhyogon sensorlesspvpowerforecastingingridconnectedbuildingsthroughdeeplearning |