Forecasting for battery storage: choosing the error metric
We describe our approach to the Western Power Distribution (WPD) Presumed Open Data (POD) 6 MWh battery storage capacity forecasting competition, in which we finished second. The competition entails two distinct forecasting aims to maximise the daily evening peak reduction and using as much solar ph...
| Main Authors: | , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
MDPI
2021
|
| _version_ | 1826273874988236800 |
|---|---|
| author | Singleton, C Grindrod, P |
| author_facet | Singleton, C Grindrod, P |
| author_sort | Singleton, C |
| collection | OXFORD |
| description | We describe our approach to the Western Power Distribution (WPD) Presumed Open Data (POD) 6 MWh battery storage capacity forecasting competition, in which we finished second. The competition entails two distinct forecasting aims to maximise the daily evening peak reduction and using as much solar photovoltaic energy as possible. For the latter, we combine a Bayesian (MCMC) linear regression model with an average generation distribution. For the former, we introduce a new error metric that allows even a simple weighted average combined with a simple linear regression model to score very well using the competition performance metric. |
| first_indexed | 2024-03-06T22:34:52Z |
| format | Journal article |
| id | oxford-uuid:598b6935-0680-422b-af22-060bad64fb7f |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T22:34:52Z |
| publishDate | 2021 |
| publisher | MDPI |
| record_format | dspace |
| spelling | oxford-uuid:598b6935-0680-422b-af22-060bad64fb7f2022-03-26T17:10:22ZForecasting for battery storage: choosing the error metricJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:598b6935-0680-422b-af22-060bad64fb7fEnglishSymplectic ElementsMDPI2021Singleton, CGrindrod, PWe describe our approach to the Western Power Distribution (WPD) Presumed Open Data (POD) 6 MWh battery storage capacity forecasting competition, in which we finished second. The competition entails two distinct forecasting aims to maximise the daily evening peak reduction and using as much solar photovoltaic energy as possible. For the latter, we combine a Bayesian (MCMC) linear regression model with an average generation distribution. For the former, we introduce a new error metric that allows even a simple weighted average combined with a simple linear regression model to score very well using the competition performance metric. |
| spellingShingle | Singleton, C Grindrod, P Forecasting for battery storage: choosing the error metric |
| title | Forecasting for battery storage: choosing the error metric |
| title_full | Forecasting for battery storage: choosing the error metric |
| title_fullStr | Forecasting for battery storage: choosing the error metric |
| title_full_unstemmed | Forecasting for battery storage: choosing the error metric |
| title_short | Forecasting for battery storage: choosing the error metric |
| title_sort | forecasting for battery storage choosing the error metric |
| work_keys_str_mv | AT singletonc forecastingforbatterystoragechoosingtheerrormetric AT grindrodp forecastingforbatterystoragechoosingtheerrormetric |