Six Days Ahead Forecasting of Energy Production of Small Behind-the-Meter Solar Sites
Due to the growing penetration of behind-the-meter (BTM) photovoltaic (PV) installations, accurate solar energy forecasts are required for a reliable economic energy system operation. A new hybrid methodology is proposed in this paper with a sequence of one-step ahead models to accumulate 144 h for...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/3/1533 |
| _version_ | 1797624642162130944 |
|---|---|
| author | Hugo Bezerra Menezes Leite Hamidreza Zareipour |
| author_facet | Hugo Bezerra Menezes Leite Hamidreza Zareipour |
| author_sort | Hugo Bezerra Menezes Leite |
| collection | DOAJ |
| description | Due to the growing penetration of behind-the-meter (BTM) photovoltaic (PV) installations, accurate solar energy forecasts are required for a reliable economic energy system operation. A new hybrid methodology is proposed in this paper with a sequence of one-step ahead models to accumulate 144 h for a small-scale BTM PV site. Three groups of models with different inputs are developed to cover 6 days of forecasting horizon, with each group trained for each hour of the above zero irradiance. In addition, a novel dataset preselection is proposed, and neighboring solar farms’ power predictions are used as a feature to boost the accuracy of the model. Two techniques are selected: XGBoost and CatBoost. An extensive assessment for 1 year is conducted to evaluate the proposed method. Numerical results highlight that training the models with the previous, current, and 1 month ahead from the previous year referenced by the target month can improve the model’s accuracy. Finally, when solar energy predictions from neighboring solar farms are incorporated, this further increases the overall forecast accuracy. The proposed method is compared with the complete-history persistence ensemble (CH-PeEn) model as a benchmark. |
| first_indexed | 2024-03-11T09:45:27Z |
| format | Article |
| id | doaj.art-d4eb0259ab4341cb8052791e0d87ed2e |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-11T09:45:27Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-d4eb0259ab4341cb8052791e0d87ed2e2023-11-16T16:38:48ZengMDPI AGEnergies1996-10732023-02-01163153310.3390/en16031533Six Days Ahead Forecasting of Energy Production of Small Behind-the-Meter Solar SitesHugo Bezerra Menezes Leite0Hamidreza Zareipour1Department of Electrical and Software Engineering, University of Calgary, Calgary, AB T2N 1N4, CanadaDepartment of Electrical and Software Engineering, University of Calgary, Calgary, AB T2N 1N4, CanadaDue to the growing penetration of behind-the-meter (BTM) photovoltaic (PV) installations, accurate solar energy forecasts are required for a reliable economic energy system operation. A new hybrid methodology is proposed in this paper with a sequence of one-step ahead models to accumulate 144 h for a small-scale BTM PV site. Three groups of models with different inputs are developed to cover 6 days of forecasting horizon, with each group trained for each hour of the above zero irradiance. In addition, a novel dataset preselection is proposed, and neighboring solar farms’ power predictions are used as a feature to boost the accuracy of the model. Two techniques are selected: XGBoost and CatBoost. An extensive assessment for 1 year is conducted to evaluate the proposed method. Numerical results highlight that training the models with the previous, current, and 1 month ahead from the previous year referenced by the target month can improve the model’s accuracy. Finally, when solar energy predictions from neighboring solar farms are incorporated, this further increases the overall forecast accuracy. The proposed method is compared with the complete-history persistence ensemble (CH-PeEn) model as a benchmark.https://www.mdpi.com/1996-1073/16/3/1533photovoltaic (PV)forecastbehind-the-meter (BTM)spatio-temporalstrategic training |
| spellingShingle | Hugo Bezerra Menezes Leite Hamidreza Zareipour Six Days Ahead Forecasting of Energy Production of Small Behind-the-Meter Solar Sites Energies photovoltaic (PV) forecast behind-the-meter (BTM) spatio-temporal strategic training |
| title | Six Days Ahead Forecasting of Energy Production of Small Behind-the-Meter Solar Sites |
| title_full | Six Days Ahead Forecasting of Energy Production of Small Behind-the-Meter Solar Sites |
| title_fullStr | Six Days Ahead Forecasting of Energy Production of Small Behind-the-Meter Solar Sites |
| title_full_unstemmed | Six Days Ahead Forecasting of Energy Production of Small Behind-the-Meter Solar Sites |
| title_short | Six Days Ahead Forecasting of Energy Production of Small Behind-the-Meter Solar Sites |
| title_sort | six days ahead forecasting of energy production of small behind the meter solar sites |
| topic | photovoltaic (PV) forecast behind-the-meter (BTM) spatio-temporal strategic training |
| url | https://www.mdpi.com/1996-1073/16/3/1533 |
| work_keys_str_mv | AT hugobezerramenezesleite sixdaysaheadforecastingofenergyproductionofsmallbehindthemetersolarsites AT hamidrezazareipour sixdaysaheadforecastingofenergyproductionofsmallbehindthemetersolarsites |